g2c_git.Rmd

---
title: "G2C data"
author: "<p>Jon Kawatachi</p>"
date:  "`r format(Sys.time(), '%d %B, %Y')`"
output:
  html_document:
    theme: flatly
    highlight: pygments
    #css: styles.css
    number_sections: false
    fig_caption: true

---

```{r global_options, include=FALSE}
knitr::opts_chunk$set(warning=FALSE)
```

```{r message=FALSE, warning=FALSE, include=FALSE}
#Load library
library(Hmisc)
library(summarytools)
library(tidyverse)
library(readxl)
library(dplyr)
library(likert)
library(kableExtra)
library(formattable)
library(janitor)
library(openxlsx)

```

# Content

Studies: 
Assessing Adolescents' Access to Food Assistance Programs during COVID-19 Pandemic - Adolescent Food Insecurity (Vanguard)
The influence of health on employment among young people in Baltimore - HEYBMORE (G2C)

1. Food Insecurity
2. Anxiety
3. PTSD / Trauma
4. Depression
5. Housing

## 1. Food Insecurity
```{r message=FALSE, warning=FALSE, include=FALSE}
# Import G2C REDCap data for comparison to Vanguard
redcap_g2c_labels=read.csv('/Users/jon/Downloads/TheInfluenceOfHealth_DATA_LABELS_2021-08-25_1547.csv')
redcap_g2c_raw1 = read.csv('/Users/jon/Downloads/TheInfluenceOfHealth_DATA_2021-08-25_1547.csv')
redcap_g2c_raw2 = dplyr::filter(redcap_g2c_raw1, heybmore_survey_complete==2)
redcap_g2c_raw2$name_first <- redcap_g2c_raw2$info_fn
redcap_g2c_raw2$name_last <- redcap_g2c_raw2$info_ln
redcap_g2c_raw2$dob <- redcap_g2c_raw2$dob
# ETO data - Cycle 2
eto2_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Demographics")
eto2_demo$subjectid <- eto2_demo$`Subject.Unique.Identifier`
eto2_demo$cycle <- eto2_demo$`Cycle:`
eto2_demo$name_first <- eto2_demo$`First.Name`
eto2_demo$name_last <- eto2_demo$`Last.Name`
eto2_demo$gender <- eto2_demo$`Gender_3753`
eto2_demo$ethnic <- eto2_demo$`Ethnicity-Custom`
eto2_demo$race <- eto2_demo$`Race-Custom`
eto2_demo$dob <- eto2_demo$DOB
eto2_demo$source <- "eto2"
eto2_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Enrolled Current Program")
eto2_prog$subjectid <- eto2_prog$ID
eto2_prog$program <- eto2_prog$`Current.Program`
# ETO data - Cycle 3
eto3_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Demographics")
eto3_demo$subjectid <- eto3_demo$`Subject.Id`
eto3_demo$cycle <- eto3_demo$`Cycle:`
eto3_demo$name_first <- eto3_demo$`First.Name`
eto3_demo$name_last <- eto3_demo$`Last.Name`
eto3_demo$gender <- eto3_demo$`Gender_3753`
eto3_demo$ethnic <- eto3_demo$`Ethnicity-Custom`
eto3_demo$race <- eto3_demo$`Race-Custom`
eto3_demo$dob <- eto3_demo$DOB
eto3_demo$source <- "eto3"
eto3_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Training")
eto3_prog$subjectid <- eto3_prog$SubjectID
eto3_prog$program <- eto3_prog$`Program.Name`
# Salesforce data
salesforce1 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210208 - unlocked.xlsx')
salesforce2 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210209 - unlocked.xlsx')
salesforce2$name_first <- salesforce2$`Contact:.First.Name`
salesforce2$name_last <- salesforce2$`Contact:.Last.Name`
salesforce2$gender_sales <- salesforce2$`Gender`
salesforce2$ethnic_sales <- salesforce2$`Ethnicity`
salesforce2$race_sales <- salesforce2$`Race`
salesforce2$source_sales <- "salesforce"
# Select variables from Salesforce data
salesforce3 <- dplyr::select(salesforce2, name_first, name_last, gender_sales, ethnic_sales, race_sales, source_sales)
# Select variables from ETO data
eto2_demo_select <- dplyr::select(eto2_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto2_prog_select <- dplyr::select(eto2_prog, subjectid, `program`)
eto2 <- left_join(eto2_demo_select, eto2_prog_select, by="subjectid")
eto3_demo_select <- dplyr::select(eto3_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto3_prog_select <- dplyr::select(eto3_prog, subjectid, `program`)
eto3 <- left_join(eto3_demo_select, eto3_prog_select, by="subjectid")
# All ETO data
eto_data <- rbind(eto2, eto3)
# Merge REDCap data with ETO and Salesforce data
redcap_g2c_raw3 <- left_join(redcap_g2c_raw2, eto_data, by=c("name_first", "name_last"))
redcap_g2c_raw4 <- left_join(redcap_g2c_raw3, salesforce3, by=c("name_first", "name_last"))
redcap_g2c_raw <- unique(redcap_g2c_raw4)
redcap_g2c_raw$gender_merge <- if_else((is.na(redcap_g2c_raw$gender)), redcap_g2c_raw$gender_sales, redcap_g2c_raw$gender)
# Manually replace missing gender and cycle data
redcap_g2c_raw[redcap_g2c_raw$name_last=="Porter" & redcap_g2c_raw$name_first=="Jared","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Johnson" & redcap_g2c_raw$name_first=="Jamyra","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Baker" & redcap_g2c_raw$name_first=="Amori","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","cycle.y"] <- "Cycle 2"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","program"] <- "Civic Works"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Gladney" & redcap_g2c_raw$name_first=="Kayla","gender_merge"] <- "Female"
# Handle cycle 
redcap_g2c_raw$cycle1<- ifelse(is.na(redcap_g2c_raw$cycle.y), "Undetermined", redcap_g2c_raw$cycle.y)
```

```{r include=FALSE}
# Import Vanguard data from REDCap project
redcap_labels=read.csv('/Users/jon/Downloads/AssessingAdolescents_DATA_LABELS_2021-08-26_1656.csv')
redcap_raw_van = read.csv('/Users/jon/Downloads/AssessingAdolescents_DATA_2021-08-26_1656.csv')
redcap_van_survey <- filter(redcap_raw_van, redcap_event_name=="youth_arm_1" | redcap_event_name=="youth_arm_2" | redcap_event_name=="youth_arm_3" | redcap_event_name=="youth_arm_4")

redcap_van_survey$arm <- if_else(redcap_van_survey$redcap_event_name=="youth_arm_1", "Youth Arm 1", if_else(redcap_van_survey$redcap_event_name=="youth_arm_2", "Youth Arm 2", if_else(redcap_van_survey$redcap_event_name=="youth_arm_3", "Youth Arm 3", if_else(redcap_van_survey$redcap_event_name=="youth_arm_4", "Youth Arm 4", "NA"))))
```

```{r include=FALSE}
# Food variables for the Vanguard Study only
food_van1 <- dplyr::select(redcap_van_survey, arm, q13a_foodsec,	q13b_foodsec,	q13c_foodsec,	q13d_foodsec, q13e_foodsec, q13f_foodsec, q13g_foodsec, q13h_foodsec, q13i_foodsec)
# Assign labels to choices
food_van1$q13a_foodsec <- if_else(food_van1$q13a_foodsec==2, "A lot", if_else(food_van1$q13a_foodsec==1,"Sometimes", if_else(food_van1$q13a_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13b_foodsec <- if_else(food_van1$q13b_foodsec==2, "A lot", if_else(food_van1$q13b_foodsec==1,"Sometimes", if_else(food_van1$q13b_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13c_foodsec <- if_else(food_van1$q13c_foodsec==2, "A lot", if_else(food_van1$q13c_foodsec==1,"Sometimes", if_else(food_van1$q13c_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13d_foodsec <- if_else(food_van1$q13d_foodsec==2, "A lot", if_else(food_van1$q13d_foodsec==1,"Sometimes", if_else(food_van1$q13d_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13e_foodsec <- if_else(food_van1$q13e_foodsec==2, "A lot", if_else(food_van1$q13e_foodsec==1,"Sometimes", if_else(food_van1$q13e_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13f_foodsec <- if_else(food_van1$q13f_foodsec==2, "A lot", if_else(food_van1$q13f_foodsec==1,"Sometimes", if_else(food_van1$q13f_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13g_foodsec <- if_else(food_van1$q13g_foodsec==2, "A lot", if_else(food_van1$q13g_foodsec==1,"Sometimes", if_else(food_van1$q13g_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13h_foodsec <- if_else(food_van1$q13h_foodsec==2, "A lot", if_else(food_van1$q13h_foodsec==1,"Sometimes", if_else(food_van1$q13h_foodsec==0,"Never", "Prefer not to answer")))
food_van1$q13i_foodsec <- if_else(food_van1$q13i_foodsec==2, "A lot", if_else(food_van1$q13i_foodsec==1,"Sometimes", if_else(food_van1$q13i_foodsec==0,"Never", "Prefer not to answer")))
# Assign variable names
food_van1$"...did you worry that food at home would run out before you/your household got money to buy more?" <-food_van1$q13a_foodsec 
food_van1$"...did the food that you/your household bought run out, and you didnt have money to get more?" <- food_van1$q13b_foodsec 
food_van1$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"<- food_van1$q13c_foodsec 
food_van1$"...were you not able to eat a balanced meal because you/your household didnt have enough money?"<- food_van1$q13d_foodsec 
food_van1$"...did you have to eat less because you/your household didnt have enough money to buy food?" <- food_van1$q13e_foodsec 
food_van1$"...has the size of your meals been cut because you/your household didnt have enough money for food?"<- food_van1$q13f_foodsec 
food_van1$"...did you have to skip a meal because you/your household didnt have enough money for food?"<- food_van1$q13g_foodsec 
food_van1$"...were you hungry but didnt eat because you/your household didnt have enough food?"<- food_van1$q13h_foodsec 
food_van1$"...did you not eat for a whole day because you/your household didnt have enough money for food?"<- food_van1$q13i_foodsec 
# Select only the new variable names
food_van <- dplyr::select(food_van1, arm,
 "...did you worry that food at home would run out before you/your household got money to buy more?" 
,"...did the food that you/your household bought run out, and you didnt have money to get more?" 
,"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"
,"...were you not able to eat a balanced meal because you/your household didnt have enough money?"
,"...did you have to eat less because you/your household didnt have enough money to buy food?" 
,"...has the size of your meals been cut because you/your household didnt have enough money for food?"
,"...did you have to skip a meal because you/your household didnt have enough money for food?"
,"...were you hungry but didnt eat because you/your household didnt have enough food?"
,"...did you not eat for a whole day because you/your household didnt have enough money for food?")

# Assign an order to the variables
food_van$"...did you worry that food at home would run out before you/your household got money to buy more?"  = factor(food_van$"...did you worry that food at home would run out before you/your household got money to buy more?" , levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...did the food that you/your household bought run out, and you didnt have money to get more?" = factor(food_van$"...did the food that you/your household bought run out, and you didnt have money to get more?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?" = factor(food_van$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...were you not able to eat a balanced meal because you/your household didnt have enough money?" = factor(food_van$"...were you not able to eat a balanced meal because you/your household didnt have enough money?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...did you have to eat less because you/your household didnt have enough money to buy food?" = factor(food_van$"...did you have to eat less because you/your household didnt have enough money to buy food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...has the size of your meals been cut because you/your household didnt have enough money for food?" = factor(food_van$"...has the size of your meals been cut because you/your household didnt have enough money for food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...did you have to skip a meal because you/your household didnt have enough money for food?" = factor(food_van$"...did you have to skip a meal because you/your household didnt have enough money for food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...were you hungry but didnt eat because you/your household didnt have enough food?" = factor(food_van$"...were you hungry but didnt eat because you/your household didnt have enough food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_van$"...did you not eat for a whole day because you/your household didnt have enough money for food?" = factor(food_van$"...did you not eat for a whole day because you/your household didnt have enough money for food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
```
## {.tabset}
### Vanguard graphs
<p><strong>Vanguard Survey – Food Security Questions
<br>"The next set of questions will ask you about food in your household.
<br><strong> How often..."</p>
```{r echo=FALSE}
# Vanguard Food Insecurity plot all variables
food_van_likert1 <- likert(food_van[,2:5])
plot(food_van_likert1, wrap=50)
food_van_likert2 <- likert(food_van[,6:10])
plot(food_van_likert2, wrap=50)

```
<p><strong>Vanguard Survey – Food Security Questions, by Youth Arm variable
<br>"The next set of questions will ask you about food in your household.
<br><strong> How often..."</p>
```{r echo=FALSE}
# Vanguard food questions, BY CATEGORY
food_van_cat1 <- likert(food_van[,2:4], grouping=food_van$arm)
plot(food_van_cat1, wrap=50, col= c("darkseagreen", "azure2", "dodgerblue4"))
food_van_cat1 <- likert(food_van[,5:7], grouping=food_van$arm)
plot(food_van_cat1, wrap=50, col= c("darkseagreen", "azure2", "dodgerblue4"))
food_van_cat1 <- likert(food_van[,8:10], grouping=food_van$arm)
plot(food_van_cat1, wrap=50, col= c("darkseagreen", "azure2", "dodgerblue4"))
```

### Vanguard Tables
```{r echo=FALSE}
# Table of Vanguard Food Insequrity variables
foodvan_table1 <- food_van1 %>% tabyl(arm, q13a_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table1 <- dplyr::select(foodvan_table1, arm,"NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table2 <- food_van1 %>% tabyl(arm, q13b_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table2 <- dplyr::select(foodvan_table2, arm,"NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table3 <- food_van1 %>% tabyl(arm, q13c_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table3 <- dplyr::select(foodvan_table3, arm, "NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table4 <- food_van1 %>% tabyl(arm, q13d_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table4 <- dplyr::select(foodvan_table4, arm, "NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table5 <- food_van1 %>% tabyl(arm, q13e_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table5 <- dplyr::select(foodvan_table5, arm,"NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table6 <- food_van1 %>% tabyl(arm, q13f_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table6 <- dplyr::select(foodvan_table6, arm,"NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table7 <- food_van1 %>% tabyl(arm, q13g_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table7 <- dplyr::select(foodvan_table7, arm, "NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table8 <- food_van1 %>% tabyl(arm, q13h_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table8 <- dplyr::select(foodvan_table8, arm, "NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodvan_table9 <- food_van1 %>% tabyl(arm, q13i_foodsec) %>% adorn_totals(c("row", "col"))
foodvan_table9 <- dplyr::select(foodvan_table9, arm, "NA_", "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
```
<br>"The next set of questions will ask you about food in your household.
<br><strong> How often..."</p></strong>
<br>
<strong>"...did you worry that food at home would run out before you/your household got money to buy more?" </strong>
```{r echo=FALSE}
formattable(foodvan_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did the food that you/your household bought run out, and you didnt have money to get more?" </strong>
```{r echo=FALSE}
formattable(foodvan_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"</strong>
```{r echo=FALSE}
formattable(foodvan_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...were you not able to eat a balanced meal because you/your household didnt have enough money?"</strong>
```{r echo=FALSE}
formattable(foodvan_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did you have to eat less because you/your household didnt have enough money to buy food?"  </strong>
```{r echo=FALSE}
formattable(foodvan_table5 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...has the size of your meals been cut because you/your household didnt have enough money for food?"</strong>
```{r echo=FALSE}
formattable(foodvan_table6 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did you have to skip a meal because you/your household didnt have enough money for food?"</strong>
```{r echo=FALSE}
formattable(foodvan_table7 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...were you hungry but didnt eat because you/your household didnt have enough food?"</strong>
```{r echo=FALSE}
formattable(foodvan_table8 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did you not eat for a whole day because you/your household didnt have enough money for food?"</strong>
```{r echo=FALSE}
formattable(foodvan_table9 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```

```{r echo=FALSE}
# food for G2C Study only
food_g2c1 <- dplyr::select(redcap_g2c_raw, cycle1, q20a,	q20b,	q20c,	q20d, q20e, q20f, q20g, q20h, q20i)
# Assign labels to choices
food_g2c1$q20a <- if_else(food_g2c1$q20a==2, "A lot", if_else(food_g2c1$q20a==1,"Sometimes", if_else(food_g2c1$q20a==0,"Never", "Prefer not to answer")))
food_g2c1$q20b <- if_else(food_g2c1$q20b==2, "A lot", if_else(food_g2c1$q20b==1,"Sometimes", if_else(food_g2c1$q20b==0,"Never", "Prefer not to answer")))
food_g2c1$q20c <- if_else(food_g2c1$q20c==2, "A lot", if_else(food_g2c1$q20c==1,"Sometimes", if_else(food_g2c1$q20c==0,"Never", "Prefer not to answer")))
food_g2c1$q20d <- if_else(food_g2c1$q20d==2, "A lot", if_else(food_g2c1$q20d==1,"Sometimes", if_else(food_g2c1$q20d==0,"Never", "Prefer not to answer")))
food_g2c1$q20e <- if_else(food_g2c1$q20e==2, "A lot", if_else(food_g2c1$q20e==1,"Sometimes", if_else(food_g2c1$q20e==0,"Never", "Prefer not to answer")))
food_g2c1$q20f <- if_else(food_g2c1$q20f==2, "A lot", if_else(food_g2c1$q20f==1,"Sometimes", if_else(food_g2c1$q20f==0,"Never", "Prefer not to answer")))
food_g2c1$q20g <- if_else(food_g2c1$q20g==2, "A lot", if_else(food_g2c1$q20g==1,"Sometimes", if_else(food_g2c1$q20g==0,"Never", "Prefer not to answer")))
food_g2c1$q20h <- if_else(food_g2c1$q20h==2, "A lot", if_else(food_g2c1$q20h==1,"Sometimes", if_else(food_g2c1$q20h==0,"Never", "Prefer not to answer")))
food_g2c1$q20i <- if_else(food_g2c1$q20i==2, "A lot", if_else(food_g2c1$q20i==1,"Sometimes", if_else(food_g2c1$q20i==0,"Never", "Prefer not to answer")))
# Assign variable names
food_g2c1$"...did you worry that food at home would run out before you/your household got money to buy more?" <-food_g2c1$q20a 
food_g2c1$"...did the food that you/your household bought run out, and you didnt have money to get more?" <- food_g2c1$q20b 
food_g2c1$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"<- food_g2c1$q20c 
food_g2c1$"...were you not able to eat a balanced meal because you/your household didnt have enough money?"<- food_g2c1$q20d 
food_g2c1$"...did you have to eat less because you/your household didnt have enough money to buy food?" <- food_g2c1$q20e 
food_g2c1$"...has the size of your meals been cut because you/your household didnt have enough money for food?"<- food_g2c1$q20f 
food_g2c1$"...did you have to skip a meal because you/your household didnt have enough money for food?"<- food_g2c1$q20g 
food_g2c1$"...were you hungry but didnt eat because you/your household didnt have enough food?"<- food_g2c1$q20h 
food_g2c1$"...did you not eat for a whole day because you/your household didnt have enough money for food?"<- food_g2c1$q20i 
# Select only the new variable names
food_g2c <- dplyr::select(food_g2c1, cycle1,
 "...did you worry that food at home would run out before you/your household got money to buy more?" 
,"...did the food that you/your household bought run out, and you didnt have money to get more?" 
,"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"
,"...were you not able to eat a balanced meal because you/your household didnt have enough money?"
,"...did you have to eat less because you/your household didnt have enough money to buy food?" 
,"...has the size of your meals been cut because you/your household didnt have enough money for food?"
,"...did you have to skip a meal because you/your household didnt have enough money for food?"
,"...were you hungry but didnt eat because you/your household didnt have enough food?"
,"...did you not eat for a whole day because you/your household didnt have enough money for food?")
# Assign an order to the variables
food_g2c$"...did you worry that food at home would run out before you/your household got money to buy more?"  = factor(food_g2c$"...did you worry that food at home would run out before you/your household got money to buy more?" , levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...did the food that you/your household bought run out, and you didnt have money to get more?" = factor(food_g2c$"...did the food that you/your household bought run out, and you didnt have money to get more?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?" = factor(food_g2c$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...were you not able to eat a balanced meal because you/your household didnt have enough money?" = factor(food_g2c$"...were you not able to eat a balanced meal because you/your household didnt have enough money?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...did you have to eat less because you/your household didnt have enough money to buy food?" = factor(food_g2c$"...did you have to eat less because you/your household didnt have enough money to buy food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...has the size of your meals been cut because you/your household didnt have enough money for food?" = factor(food_g2c$"...has the size of your meals been cut because you/your household didnt have enough money for food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...did you have to skip a meal because you/your household didnt have enough money for food?" = factor(food_g2c$"...did you have to skip a meal because you/your household didnt have enough money for food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...were you hungry but didnt eat because you/your household didnt have enough food?" = factor(food_g2c$"...were you hungry but didnt eat because you/your household didnt have enough food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
food_g2c$"...did you not eat for a whole day because you/your household didnt have enough money for food?" = factor(food_g2c$"...did you not eat for a whole day because you/your household didnt have enough money for food?", levels = c("Never", "Sometimes", "A lot"), ordered = TRUE)
```
### G2C graphs
<p><strong>G2C Survey – Food Insecurity Questions
<br><stong>"The next set of questions will ask you about food in your household.
<br><strong> How often..."</p>
```{r echo=FALSE}
# G2C Food Insecurity plot all variables
food_g2c_likert1 <- likert(food_g2c[,2:5])
plot(food_g2c_likert1, wrap=50)
food_g2c_likert2 <- likert(food_g2c[,6:10])
plot(food_g2c_likert2, wrap=50)
```
<p><strong>G2C Survey – Food Insecurity Questions, <u>by Youth Arm variable</u>
<br>"The next set of questions will ask you about food in your household.
<br><strong> How often..."</p>

```{r echo=FALSE}
# G2C food questions, BY CATEGORY
food_g2c_cat1 <- likert(food_g2c[,2:4], grouping=food_g2c$arm)
plot(food_g2c_cat1, wrap=50, col= c("darkseagreen", "azure2", "dodgerblue4"))
food_g2c_cat1 <- likert(food_g2c[,5:7], grouping=food_g2c$arm)
plot(food_g2c_cat1, wrap=50, col= c("darkseagreen", "azure2", "dodgerblue4"))
food_g2c_cat1 <- likert(food_g2c[,8:10], grouping=food_g2c$arm)
plot(food_g2c_cat1, wrap=50, col= c("darkseagreen", "azure2", "dodgerblue4"))
```

### G2C Tables
```{r echo=FALSE}
# Table of g2cguard food variables
foodg2c_table1 <- food_g2c1 %>% tabyl(cycle1, q20a) %>% adorn_totals(c("row", "col"))
foodg2c_table1 <- dplyr::select(foodg2c_table1, cycle1,"Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table2 <- food_g2c1 %>% tabyl(cycle1, q20b) %>% adorn_totals(c("row", "col"))
foodg2c_table2 <- dplyr::select(foodg2c_table2, cycle1,"Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table3 <- food_g2c1 %>% tabyl(cycle1, q20c) %>% adorn_totals(c("row", "col"))
foodg2c_table3 <- dplyr::select(foodg2c_table3, cycle1, "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table4 <- food_g2c1 %>% tabyl(cycle1, q20d) %>% adorn_totals(c("row", "col"))
foodg2c_table4 <- dplyr::select(foodg2c_table4, cycle1, "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table5 <- food_g2c1 %>% tabyl(cycle1, q20e) %>% adorn_totals(c("row", "col"))
foodg2c_table5 <- dplyr::select(foodg2c_table5, cycle1, "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table6 <- food_g2c1 %>% tabyl(cycle1, q20f) %>% adorn_totals(c("row", "col"))
foodg2c_table6 <- dplyr::select(foodg2c_table6, cycle1,"Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table7 <- food_g2c1 %>% tabyl(cycle1, q20g) %>% adorn_totals(c("row", "col"))
foodg2c_table7 <- dplyr::select(foodg2c_table7, cycle1, "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table8 <- food_g2c1 %>% tabyl(cycle1, q20h) %>% adorn_totals(c("row", "col"))
foodg2c_table8 <- dplyr::select(foodg2c_table8, cycle1, "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
foodg2c_table9 <- food_g2c1 %>% tabyl(cycle1, q20i) %>% adorn_totals(c("row", "col"))
foodg2c_table9 <- dplyr::select(foodg2c_table9, cycle1, "Prefer not to answer", "Never", "Sometimes", "A lot", Total)
```
<br>"The next set of questions will ask you about food in your household.
<br><strong> How often..."</p></strong>
<br>
<strong>"...did you worry that food at home would run out before you/your household got money to buy more?" </strong>
```{r echo=FALSE}
formattable(foodg2c_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did the food that you/your household bought run out, and you didnt have money to get more?" </strong>
```{r echo=FALSE}
formattable(foodg2c_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"</strong>
```{r echo=FALSE}
formattable(foodg2c_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...were you not able to eat a balanced meal because you/your household didnt have enough money?"</strong>
```{r echo=FALSE}
formattable(foodg2c_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did you have to eat less because you/your household didnt have enough money to buy food?"  </strong>
```{r echo=FALSE}
formattable(foodg2c_table5 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...has the size of your meals been cut because you/your household didnt have enough money for food?"</strong>
```{r echo=FALSE}
formattable(foodg2c_table6 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did you have to skip a meal because you/your household didnt have enough money for food?"</strong>
```{r echo=FALSE}
formattable(foodg2c_table7 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...were you hungry but didnt eat because you/your household didnt have enough food?"</strong>
```{r echo=FALSE}
formattable(foodg2c_table8 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"...did you not eat for a whole day because you/your household didnt have enough money for food?"</strong>
```{r echo=FALSE}
formattable(foodg2c_table9 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```

### Vanguard vs. G2C
<br>"The next set of questions will ask you about food in your household.
<br><strong> How often..."</p>
```{r echo=FALSE}
# Merge the vanguard and g2c data for comparison
food_g2c_merge <- dplyr::select(food_g2c, -cycle1)
food_g2c_merge$study <- "Grads2Careers"
food_van_merge <- dplyr::select(food_van, -arm)
food_van_merge$study <- "Vanguard"
food_merged <- rbind(food_g2c_merge,food_van_merge)
food_merged1 <- dplyr::select(food_merged,  "...did you worry that food at home would run out before you/your household got money to buy more?" 
,"...did the food that you/your household bought run out, and you didnt have money to get more?" 
,"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"
,"...were you not able to eat a balanced meal because you/your household didnt have enough money?"
,"...did you have to eat less because you/your household didnt have enough money to buy food?" 
,"...has the size of your meals been cut because you/your household didnt have enough money for food?"
,"...did you have to skip a meal because you/your household didnt have enough money for food?"
,"...were you hungry but didnt eat because you/your household didnt have enough food?"
,"...did you not eat for a whole day because you/your household didnt have enough money for food?")
# MERGED food Plot by Study
food_merged_cat1 <- likert(food_merged1[,1:3], grouping=food_merged$study)
plot(food_merged_cat1)
food_merged_cat2 <- likert(food_merged1[,4:6], grouping=food_merged$study)
plot(food_merged_cat2)
food_merged_cat3 <- likert(food_merged1[,7:9], grouping=food_merged$study)
plot(food_merged_cat3)

```

```{r echo=FALSE, message=FALSE, warning=FALSE}
####################### Vanguard ####################
# Select Vanguard food variables and create new variables for total score and dichotomous variable
food_van_total <- dplyr::select(redcap_van_survey, arm, q13a_foodsec,	q13b_foodsec,	q13c_foodsec,	q13d_foodsec, q13e_foodsec, q13f_foodsec, q13g_foodsec, q13h_foodsec, q13i_foodsec)
# Create food Score w/ and w/o "Prefer not to answer"
food_van_total$food_total <- food_van_total$q13a_foodsec + food_van_total$q13b_foodsec + food_van_total$q13c_foodsec + food_van_total$q13d_foodsec + food_van_total$q13e_foodsec + food_van_total$q13f_foodsec + food_van_total$q13g_foodsec + food_van_total$q13h_foodsec + food_van_total$q13i_foodsec 
food_van_total$food_total_no_refused <- ifelse(food_van_total$food_total>18, NA, food_van_total$food_total)
# Flagged if score 2 or greater
food_van_total$food_flagged <- if_else(food_van_total$food_total>=2, 1,0)
# Rename Vanguard variables
food_van_total$"...did you worry that food at home would run out before you/your household got money to buy more?" <-food_van_total$q13a_foodsec 
food_van_total$"...did the food that you/your household bought run out, and you didnt have money to get more?" <- food_van_total$q13b_foodsec 
food_van_total$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"<- food_van_total$q13c_foodsec 
food_van_total$"...were you not able to eat a balanced meal because you/your household didnt have enough money?"<- food_van_total$q13d_foodsec 
food_van_total$"...did you have to eat less because you/your household didnt have enough money to buy food?" <- food_van_total$q13e_foodsec 
food_van_total$"...has the size of your meals been cut because you/your household didnt have enough money for food?"<- food_van_total$q13f_foodsec 
food_van_total$"...did you have to skip a meal because you/your household didnt have enough money for food?"<- food_van_total$q13g_foodsec 
food_van_total$"...were you hungry but didnt eat because you/your household didnt have enough food?"<- food_van_total$q13h_foodsec 
food_van_total$"...did you not eat for a whole day because you/your household didnt have enough money for food?"<- food_van_total$q13i_foodsec 
#Select only the new variable names
food_van_totals <- dplyr::select(food_van_total, food_total, food_total_no_refused, food_flagged,
 "...did you worry that food at home would run out before you/your household got money to buy more?" 
,"...did the food that you/your household bought run out, and you didnt have money to get more?" 
,"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"
,"...were you not able to eat a balanced meal because you/your household didnt have enough money?"
,"...did you have to eat less because you/your household didnt have enough money to buy food?" 
,"...has the size of your meals been cut because you/your household didnt have enough money for food?"
,"...did you have to skip a meal because you/your household didnt have enough money for food?"
,"...were you hungry but didnt eat because you/your household didnt have enough food?"
,"...did you not eat for a whole day because you/your household didnt have enough money for food?")

######################## G2C #######################
# Add variable names, total and select new variables for G2C data
food_g2c_total <- dplyr::select(redcap_g2c_raw, cycle.y, q20a,	q20b,	q20c,	q20d, q20e, q20f, q20g, q20h, q20i)
# Create a food score w/ and w/o "Prefer not to answer"
food_g2c_total$food_total <- food_g2c_total$q20a + food_g2c_total$q20b + food_g2c_total$q20c + food_g2c_total$q20d + food_g2c_total$q20e + food_g2c_total$q20f + food_g2c_total$q20g + food_g2c_total$q20h + food_g2c_total$q20i
food_g2c_total$food_total_no_refused <- ifelse(food_g2c_total$food_total>18, NA, food_g2c_total$food_total)
# Flagged if score 2 or greater
food_g2c_total$food_flagged <- if_else(food_g2c_total$food_total>=2, 1,0)
# Rename G2C variable
food_g2c_total$"...did you worry that food at home would run out before you/your household got money to buy more?" <-food_g2c_total$q20a
food_g2c_total$"...did the food that you/your household bought run out, and you didnt have money to get more?" <- food_g2c_total$q20b
food_g2c_total$"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"<- food_g2c_total$q20c
food_g2c_total$"...were you not able to eat a balanced meal because you/your household didnt have enough money?"<- food_g2c_total$q20d
food_g2c_total$"...did you have to eat less because you/your household didnt have enough money to buy food?" <- food_g2c_total$q20e 
food_g2c_total$"...has the size of your meals been cut because you/your household didnt have enough money for food?"<- food_g2c_total$q20f
food_g2c_total$"...did you have to skip a meal because you/your household didnt have enough money for food?"<- food_g2c_total$q20g 
food_g2c_total$"...were you hungry but didnt eat because you/your household didnt have enough food?"<- food_g2c_total$q20h
food_g2c_total$"...did you not eat for a whole day because you/your household didnt have enough money for food?"<- food_g2c_total$q20i
#Select only the new variable names
food_g2c_totals <- dplyr::select(food_g2c_total, food_total, food_total_no_refused, food_flagged, "...did you worry that food at home would run out before you/your household got money to buy more?" 
,"...did the food that you/your household bought run out, and you didnt have money to get more?" 
,"...did your meals only include a few kinds of cheap foods because you/your household was running out of money to buy food?"
,"...were you not able to eat a balanced meal because you/your household didnt have enough money?"
,"...did you have to eat less because you/your household didnt have enough money to buy food?" 
,"...has the size of your meals been cut because you/your household didnt have enough money for food?"
,"...did you have to skip a meal because you/your household didnt have enough money for food?"
,"...were you hungry but didnt eat because you/your household didnt have enough food?"
,"...did you not eat for a whole day because you/your household didnt have enough money for food?") 
```

```{r echo=FALSE}
# Combine the studies
food1 <- as.data.frame(ftable(food_van_totals$food_total_no_refused))
food1$Vanguard <- food1$Freq
food_van_totals$study <-"Vanguard"

food2 <- as.data.frame(ftable(food_g2c_totals$food_total_no_refused))
food2$G2C <- food2$Freq
food_g2c_totals$study <- "G2C"

food_total_merged <- rbind(food_g2c_totals, food_van_totals)
```
<strong>Histogram of Food Security Scores (total of 9 variables, range:0-18): Vanguard vs. G2C </strong>
```{r echo=FALSE}
# Create a grouped bar chart
food1$subgroup <- "Vanguard"
food1$group <- food1$Var1
food1$values <- food1$Freq
food1a <- dplyr::select(food1, subgroup, group, values)
food2$subgroup <- "G2c"
food2$group <- food2$Var1
food2$values <- food2$Freq
food2a <- dplyr::select(food2, subgroup, group, values)
food3 <- rbind(food1a, food2a)

ggplot(food3, 
       aes(x=group, 
           y=values, 
           fill=subgroup)) + 
    geom_bar(position="dodge", 
             stat="identity")
        
```

```{r echo=FALSE}
food_total_merged1 <- dplyr::filter(food_total_merged, !is.na(food_total) & food_total <=30)
histogram(~ food_total | study,
          main = "Food Security Score, Percent Comparison of Vanguard and G2C",
          xlab = "Score",
          data=food_total_merged1,
          type="percent",
          layout=c(1,2))      #  columns and rows of individual plots
```

```{r echo=FALSE}
wilcox.test(food_total_merged$food_total_no_refused ~ food_total_merged$study)

t.test(food_total_merged$food_total_no_refused ~ food_total_merged$study)
```
Food Security Score comparison
```{r echo=FALSE}
boxplot(food_total_merged$food_total_no_refused ~ food_total_merged$study, col="#69b3a2" , ylab="Total food Score", xlab = "Study")
```


## 2. Anxiety
```{r message=FALSE, warning=FALSE, include=FALSE}
# ETO data - Cycle 2
eto2_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Demographics")
eto2_demo$subjectid <- eto2_demo$`Subject.Unique.Identifier`
eto2_demo$cycle <- eto2_demo$`Cycle:`
eto2_demo$name_first <- eto2_demo$`First.Name`
eto2_demo$name_last <- eto2_demo$`Last.Name`
eto2_demo$gender <- eto2_demo$`Gender_3753`
eto2_demo$ethnic <- eto2_demo$`Ethnicity-Custom`
eto2_demo$race <- eto2_demo$`Race-Custom`
eto2_demo$dob <- eto2_demo$DOB
eto2_demo$source <- "eto2"
eto2_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Enrolled Current Program")
eto2_prog$subjectid <- eto2_prog$ID
eto2_prog$program <- eto2_prog$`Current.Program`
# ETO data - Cycle 3
eto3_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Demographics")
eto3_demo$subjectid <- eto3_demo$`Subject.Id`
eto3_demo$cycle <- eto3_demo$`Cycle:`
eto3_demo$name_first <- eto3_demo$`First.Name`
eto3_demo$name_last <- eto3_demo$`Last.Name`
eto3_demo$gender <- eto3_demo$`Gender_3753`
eto3_demo$ethnic <- eto3_demo$`Ethnicity-Custom`
eto3_demo$race <- eto3_demo$`Race-Custom`
eto3_demo$dob <- eto3_demo$DOB
eto3_demo$source <- "eto3"
eto3_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Training")
eto3_prog$subjectid <- eto3_prog$SubjectID
eto3_prog$program <- eto3_prog$`Program.Name`
# Salesforce data
salesforce1 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210208 - unlocked.xlsx')
salesforce2 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210209 - unlocked.xlsx')
salesforce2$name_first <- salesforce2$`Contact:.First.Name`
salesforce2$name_last <- salesforce2$`Contact:.Last.Name`
salesforce2$gender_sales <- salesforce2$`Gender`
salesforce2$ethnic_sales <- salesforce2$`Ethnicity`
salesforce2$race_sales <- salesforce2$`Race`
salesforce2$source_sales <- "salesforce"
# Select variables from Salesforce data
salesforce3 <- dplyr::select(salesforce2, name_first, name_last, gender_sales, ethnic_sales, race_sales, source_sales)
# Select variables from ETO data
eto2_demo_select <- dplyr::select(eto2_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto2_prog_select <- dplyr::select(eto2_prog, subjectid, `program`)
eto2 <- left_join(eto2_demo_select, eto2_prog_select, by="subjectid")
eto3_demo_select <- dplyr::select(eto3_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto3_prog_select <- dplyr::select(eto3_prog, subjectid, `program`)
eto3 <- left_join(eto3_demo_select, eto3_prog_select, by="subjectid")
# All ETO data
eto_data <- rbind(eto2, eto3)
# Merge REDCap data with ETO and Salesforce data
redcap_g2c_raw3 <- left_join(redcap_g2c_raw2, eto_data, by=c("name_first", "name_last"))
redcap_g2c_raw4 <- left_join(redcap_g2c_raw3, salesforce3, by=c("name_first", "name_last"))
redcap_g2c_raw <- unique(redcap_g2c_raw4)
redcap_g2c_raw$gender_merge <- if_else((is.na(redcap_g2c_raw$gender)), redcap_g2c_raw$gender_sales, redcap_g2c_raw$gender)
# Manually replace missing gender and cycle data
redcap_g2c_raw[redcap_g2c_raw$name_last=="Porter" & redcap_g2c_raw$name_first=="Jared","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Johnson" & redcap_g2c_raw$name_first=="Jamyra","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Baker" & redcap_g2c_raw$name_first=="Amori","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","cycle.y"] <- "Cycle 2"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","program"] <- "Civic Works"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Gladney" & redcap_g2c_raw$name_first=="Kayla","gender_merge"] <- "Female"
# Handle cycle 
redcap_g2c_raw$cycle1<- ifelse(is.na(redcap_g2c_raw$cycle.y), "Undetermined", redcap_g2c_raw$cycle.y)
```

```{r include=FALSE}
# Import Vanguard data from REDCap project
redcap_van_survey <- filter(redcap_raw_van, redcap_event_name=="youth_arm_1" | redcap_event_name=="youth_arm_2" | redcap_event_name=="youth_arm_3" | redcap_event_name=="youth_arm_4")

redcap_van_survey$arm1 <- if_else(redcap_van_survey$redcap_event_name=="youth_arm_1", "Youth Arm 1", if_else(redcap_van_survey$redcap_event_name=="youth_arm_2", "Youth Arm 2", if_else(redcap_van_survey$redcap_event_name=="youth_arm_3", "Youth Arm 3", if_else(redcap_van_survey$redcap_event_name=="youth_arm_4", "Youth Arm 4", "NA"))))

redcap_van_survey$arm<- ifelse(is.na(redcap_van_survey$arm1), "NA", redcap_van_survey$arm1)
```

```{r include=FALSE}
# Anxiety for Vanguard Study only
anxiety_van1 <- dplyr::select(redcap_van_survey, arm, q22a_anxiety, q22b_anxiety, q22c_anxiety, q22d_anxiety) 
# Assign labels to choices             
anxiety_van1$q22a_anxiety <- if_else(anxiety_van1$q22a_anxiety==4, "Almost always", if_else(anxiety_van1$q22a_anxiety==3,"Often", if_else(anxiety_van1$q22a_anxiety==2,"Sometimes",      
if_else(anxiety_van1$q22a_anxiety==1,"Almost never", if_else(anxiety_van1$q22a_anxiety==0,"Never", "Prefer not to answer")))))
anxiety_van1$q22b_anxiety <- if_else(anxiety_van1$q22b_anxiety==4, "Almost always", if_else(anxiety_van1$q22b_anxiety==3,"Often", if_else(anxiety_van1$q22b_anxiety==2,"Sometimes",      
if_else(anxiety_van1$q22b_anxiety==1,"Almost never", if_else(anxiety_van1$q22b_anxiety==0,"Never", "Prefer not to answer")))))
anxiety_van1$q22c_anxiety <- if_else(anxiety_van1$q22c_anxiety==4, "Almost always", if_else(anxiety_van1$q22c_anxiety==3,"Often", if_else(anxiety_van1$q22c_anxiety==2,"Sometimes",      
if_else(anxiety_van1$q22c_anxiety==1,"Almost never", if_else(anxiety_van1$q22c_anxiety==0,"Never", "Prefer not to answer")))))
anxiety_van1$q22d_anxiety <- if_else(anxiety_van1$q22d_anxiety==4, "Almost always", if_else(anxiety_van1$q22d_anxiety==3,"Often", if_else(anxiety_van1$q22d_anxiety==2,"Sometimes",      
if_else(anxiety_van1$q22d_anxiety==1,"Almost never", if_else(anxiety_van1$q22d_anxiety==0,"Never", "Prefer not to answer")))))
#Assign variable names                   
anxiety_van1$"I felt like something awful might happen"<- anxiety_van1$q22a_anxiety 
anxiety_van1$"I felt nervous"<- anxiety_van1$q22b_anxiety 
anxiety_van1$"I felt worried"<- anxiety_van1$q22c_anxiety 
anxiety_van1$"I worried when I was at home" <- anxiety_van1$q22d_anxiety
#Select only the new variable names
anxiety_van <- dplyr::select(anxiety_van1, arm,"I felt like something awful might happen","I felt nervous","I felt worried","I worried when I was at home") 
#Assign an order to the variables
anxiety_van$"I felt like something awful might happen" = factor(anxiety_van$"I felt like something awful might happen", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
anxiety_van$"I felt nervous" = factor(anxiety_van$"I felt nervous", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
anxiety_van$"I felt worried" = factor(anxiety_van$"I felt worried", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
anxiety_van$"I worried when I was at home" = factor(anxiety_van$"I worried when I was at home", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
```
## {.tabset}
### Vanguard graphs
<p><strong>Vanguard Survey – Anxiety Questions
<br>"Please answer the following questions based on how you felt in the past 7 days."</p>
```{r echo=FALSE}
# Vanguard anxiety Plot all variables
anxiety_van_likert <- likert(anxiety_van[,2:5])
plot(anxiety_van_likert, wrap=25)
```
<p><strong>Vanguard Survey – Anxiety Questions, by Youth Arm variable
<br>"Please answer the following questions based on how you felt in the past 7 days."</p>
```{r echo=FALSE}
# Vanguard anxiety questions, BY CATEGORY
anxiety_van_cat1 <- likert(anxiety_van[,2:5], grouping=anxiety_van$arm)
plot(anxiety_van_cat1, wrap=50)
```

### Vanguard Tables
```{r echo=FALSE}
# Table of Vanguard anxiety variables
anxietyvan_table1 <- anxiety_van1 %>% tabyl(arm, q22a_anxiety) %>% adorn_totals(c("row", "col"))
anxietyvan_table1 <- dplyr::select(anxietyvan_table1, arm,"NA_", "Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
anxietyvan_table2 <- anxiety_van1 %>% tabyl(arm, q22b_anxiety) %>% adorn_totals(c("row", "col"))
anxietyvan_table2 <- dplyr::select(anxietyvan_table2, arm,"NA_", "Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
anxietyvan_table3 <- anxiety_van1 %>% tabyl(arm, q22c_anxiety) %>% adorn_totals(c("row", "col"))
anxietyvan_table3 <- dplyr::select(anxietyvan_table3, arm, "NA_","Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
anxietyvan_table4 <- anxiety_van1 %>% tabyl(arm, q22d_anxiety) %>% adorn_totals(c("row", "col"))
anxietyvan_table4 <- dplyr::select(anxietyvan_table4, arm, "NA_","Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
```
<strong>"I felt like something awful might happen" </strong>
```{r echo=FALSE}
formattable(anxietyvan_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"I felt nervous"</strong>
```{r echo=FALSE}
formattable(anxietyvan_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"I felt worried"</strong>
```{r echo=FALSE}
formattable(anxietyvan_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"I worried when I was at home"</strong>
```{r echo=FALSE}
formattable(anxietyvan_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```

```{r echo=FALSE}
# Anxiety for G2C Study only
anxiety_g2c1 <- dplyr::select(redcap_g2c_raw, cycle1, q34a,	q34b,	q34c,	q34d)
# Assign labels to choices
anxiety_g2c1$q34a <- if_else(anxiety_g2c1$q34a==4, "Almost always", if_else(anxiety_g2c1$q34a==3,"Often", if_else(anxiety_g2c1$q34a==2,"Sometimes",      
if_else(anxiety_g2c1$q34a==1,"Almost never", if_else(anxiety_g2c1$q34a==0,"Never", "Prefer not to answer")))))
anxiety_g2c1$q34b<- if_else(anxiety_g2c1$q34b==4, "Almost always", if_else(anxiety_g2c1$q34b==3,"Often", if_else(anxiety_g2c1$q34b==2,"Sometimes",      
if_else(anxiety_g2c1$q34b==1,"Almost never", if_else(anxiety_g2c1$q34b==0,"Never", "Prefer not to answer")))))
anxiety_g2c1$q34c <- if_else(anxiety_g2c1$q34c==4, "Almost always", if_else(anxiety_g2c1$q34c==3,"Often", if_else(anxiety_g2c1$q34c==2,"Sometimes",      
if_else(anxiety_g2c1$q34c==1,"Almost never", if_else(anxiety_g2c1$q34c==0,"Never", "Prefer not to answer")))))
anxiety_g2c1$q34d <- if_else(anxiety_g2c1$q34d==4, "Almost always", if_else(anxiety_g2c1$q34d==3,"Often", if_else(anxiety_g2c1$q34d==2,"Sometimes",      
if_else(anxiety_g2c1$q34d==1,"Almost never", if_else(anxiety_g2c1$q34d==0,"Never", "Prefer not to answer")))))
# Assign variable names
anxiety_g2c1$"I felt like something awful might happen"<- anxiety_g2c1$q34a 
anxiety_g2c1$"I felt nervous"<- anxiety_g2c1$q34b 
anxiety_g2c1$"I felt worried"<- anxiety_g2c1$q34c 
anxiety_g2c1$"I worried when I was at home"<- anxiety_g2c1$q34d 
# Select only the new variable names
anxiety_g2c <- dplyr::select(anxiety_g2c1, cycle1,
"I felt like something awful might happen"
,"I felt nervous"
,"I felt worried"
,"I worried when I was at home")

anxiety_g2c$"I felt like something awful might happen"= factor(anxiety_g2c$"I felt like something awful might happen", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
anxiety_g2c$"I felt nervous"= factor(anxiety_g2c$"I felt nervous", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
anxiety_g2c$"I felt worried"= factor(anxiety_g2c$"I felt worried", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
anxiety_g2c$"I worried when I was at home"= factor(anxiety_g2c$"I worried when I was at home", levels = c("Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always"), ordered = TRUE)
```
### G2C graphs
<strong>"Please answer the following questions based on how you felt in the past 7 days."/strong>
```{r echo=FALSE}
# G2c anxiety Plot all variables
anxiety_g2c_likert <- likert(anxiety_g2c[,2:5])
plot(anxiety_g2c_likert, wrap=30, order=F)
```
<p><strong>G2C Survey – Anxiety Questions, by Youth Arm variable
<br>"Please answer the following questions based on how you felt in the past 7 days."</strong></p>
```{r echo=FALSE}
# G2C anxiety questions, BY CATEGORY
anxiety_g2c_cat1 <- likert(anxiety_g2c[,2:5], grouping=anxiety_g2c$cycle1)
plot(anxiety_g2c_cat1, wrap=30)

```

### G2C Tables
```{r echo=FALSE}
# Table of g2cguard anxiety variables
anxietyg2c_table1 <- anxiety_g2c1 %>% tabyl(cycle1, q34a) %>% adorn_totals(c("row", "col"))
anxietyg2c_table1 <- dplyr::select(anxietyg2c_table1, cycle1, "Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
anxietyg2c_table2 <- anxiety_g2c1 %>% tabyl(cycle1, q34b) %>% adorn_totals(c("row", "col"))
anxietyg2c_table2 <- dplyr::select(anxietyg2c_table2, cycle1, "Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
anxietyg2c_table3 <- anxiety_g2c1 %>% tabyl(cycle1, q34c) %>% adorn_totals(c("row", "col"))
anxietyg2c_table3 <- dplyr::select(anxietyg2c_table3, cycle1, "Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
anxietyg2c_table4 <- anxiety_g2c1 %>% tabyl(cycle1, q34d) %>% adorn_totals(c("row", "col"))
anxietyg2c_table4 <- dplyr::select(anxietyg2c_table4, cycle1, "Prefer not to answer", "Never", "Almost never", "Sometimes", "Often", "Almost always", Total)
```
<strong>"I felt like something awful might happen"</strong>
```{r echo=FALSE}
formattable(anxietyg2c_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"I felt nervous" </strong>
```{r echo=FALSE}
formattable(anxietyg2c_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"I felt worried"</strong>
```{r echo=FALSE}
formattable(anxietyg2c_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"I worried when I was at home" </strong>
```{r echo=FALSE}
formattable(anxietyg2c_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```

### Vanguard vs. G2C
<strong>Please answer the following questions based on how you felt in the past 7 days.</strong>
```{r echo=FALSE}
# Merge the vanguard and g2c data for comparison
anxiety_g2c_merge <- dplyr::select(anxiety_g2c, -cycle1)
anxiety_g2c_merge$study <- "Grads2Careers"
anxiety_van_merge <- dplyr::select(anxiety_van, -arm)
anxiety_van_merge$study <- "Vanguard"
anxiety_merged <- rbind(anxiety_g2c_merge,anxiety_van_merge)
anxiety_merged1 <- dplyr::select(anxiety_merged, "I felt like something awful might happen","I felt nervous","I felt worried","I worried when I was at home")
# MERGED anxiety Plot by Study
anxiety_merged_cat1 <- likert(anxiety_merged1, grouping=anxiety_merged$study)
plot(anxiety_merged_cat1)
```

```{r echo=FALSE, message=FALSE, warning=FALSE}
####################### Vanguard ####################
# Select Vanguard anxiety variables and create new variables for total score and dichotomous variable
anxiety_van_total <- dplyr::select(redcap_van_survey, arm, q22a_anxiety, q22b_anxiety, q22c_anxiety, q22d_anxiety)
# Create Anxiety Score w/ and w/o "Prefer not to answer"
anxiety_van_total$anxiety_total <- anxiety_van_total$q22a_anxiety + anxiety_van_total$q22b_anxiety + anxiety_van_total$q22c_anxiety + anxiety_van_total$q22d_anxiety
anxiety_van_total$anxiety_total_no_refused <- ifelse(anxiety_van_total$anxiety_total>16, NA, anxiety_van_total$anxiety_total)
# Flagged if score 8 or greater
anxiety_van_total$anxiety_flagged <- if_else(anxiety_van_total$anxiety_total>=8, 1,0)
# Rename Vanguard variables
anxiety_van_total$"I felt like something awful might happen" <- anxiety_van_total$q22a_anxiety
anxiety_van_total$"I felt nervous" <- anxiety_van_total$q22b_anxiety
anxiety_van_total$"I felt worried" <- anxiety_van_total$q22c_anxiety
anxiety_van_total$"I worried when I was at home" <- anxiety_van_total$q22d_anxiety 
#Select only the new variable names
anxiety_van_totals <- dplyr::select(anxiety_van_total, anxiety_total, anxiety_total_no_refused, anxiety_flagged,
"I felt like something awful might happen","I felt nervous","I felt worried"
,"I worried when I was at home")

######################## G2C #######################
# Add variable names, total and select new variables for G2C data
anxiety_g2c_total <- dplyr::select(redcap_g2c_raw, cycle.y, q34a, q34b, q34c, q34d)
# Create a anxiety score w/ and w/o "Prefer not to answer"
anxiety_g2c_total$anxiety_total <- anxiety_g2c_total$q34a + anxiety_g2c_total$q34b + anxiety_g2c_total$q34c + anxiety_g2c_total$q34d
anxiety_g2c_total$anxiety_total_no_refused <- ifelse(anxiety_g2c_total$anxiety_total>16, NA, anxiety_g2c_total$anxiety_total)
# Flagged if score 8 or greater
anxiety_g2c_total$anxiety_flagged <- if_else(anxiety_g2c_total$anxiety_total>=8, 1,0)
# Rename G2C variable
anxiety_g2c_total$"I felt like something awful might happen" <- anxiety_g2c_total$q34a
anxiety_g2c_total$"I felt nervous" <- anxiety_g2c_total$q34b
anxiety_g2c_total$"I felt worried"<- anxiety_g2c_total$q34c
anxiety_g2c_total$"I worried when I was at home"<- anxiety_g2c_total$q34d
#Select only the new variable names
anxiety_g2c_totals <- dplyr::select(anxiety_g2c_total, anxiety_total, anxiety_total_no_refused, anxiety_flagged,"I felt like something awful might happen", "I felt nervous","I felt worried","I worried when I was at home") 
```

```{r echo=FALSE}
# Combine the studies
anxiety1 <- as.data.frame(ftable(anxiety_van_totals$anxiety_total_no_refused))
anxiety1$Vanguard <- anxiety1$Freq
anxiety_van_totals$study <-"Vanguard"

anxiety2 <- as.data.frame(ftable(anxiety_g2c_totals$anxiety_total_no_refused))
anxiety2$G2C <- anxiety2$Freq
anxiety_g2c_totals$study <- "G2C"

anxiety_total_merged <- rbind(anxiety_g2c_totals, anxiety_van_totals)
```
<strong>Histogram of anxiety Scores (total of 4 variables, range:0-16): Vanguard vs. G2C </strong>
```{r echo=FALSE}
# Create a grouped bar chart
anxiety1$subgroup <- "Vanguard"
anxiety1$group <- anxiety1$Var1
anxiety1$values <- anxiety1$Freq
anxiety1a <- dplyr::select(anxiety1, subgroup, group, values)
anxiety2$subgroup <- "G2c"
anxiety2$group <- anxiety2$Var1
anxiety2$values <- anxiety2$Freq
anxiety2a <- dplyr::select(anxiety2, subgroup, group, values)
anxiety3 <- rbind(anxiety1a, anxiety2a)

ggplot(anxiety3, 
       aes(x=group, 
           y=values, 
           fill=subgroup)) + 
    geom_bar(position="dodge", 
             stat="identity")
        
```

```{r echo=FALSE}
anxiety_total_merged1 <- dplyr::filter(anxiety_total_merged, !is.na(anxiety_total) & anxiety_total <=30)
histogram(~ anxiety_total | study,
          main = "Anxiety Score, Percent Comparison of Vanguard and G2C",
          xlab = "Score",
          data=anxiety_total_merged1,
          type="percent",
          layout=c(1,2))      #  columns and rows of individual plots
```

```{r echo=FALSE}
wilcox.test(anxiety_total_merged$anxiety_total_no_refused ~ anxiety_total_merged$study)

t.test(anxiety_total_merged$anxiety_total_no_refused ~ anxiety_total_merged$study)
```
Anxiety Score comparison
```{r echo=FALSE}
boxplot(anxiety_total_merged$anxiety_total_no_refused ~ anxiety_total_merged$study, col="#69b3a2" , ylab="Total anxiety Score", xlab = "Study")
```

## 3. PTSD / Trauma
```{r message=FALSE, warning=FALSE, include=FALSE}
# Import G2C REDCap data for comparison to Vanguard
redcap_g2c_raw2 = filter(redcap_g2c_raw1, heybmore_survey_complete==2)
redcap_g2c_raw2$name_first <- redcap_g2c_raw2$info_fn
redcap_g2c_raw2$name_last <- redcap_g2c_raw2$info_ln
redcap_g2c_raw2$dob <- redcap_g2c_raw2$dob
# ETO data - Cycle 2
eto2_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Demographics")
eto2_demo$subjectid <- eto2_demo$`Subject.Unique.Identifier`
eto2_demo$cycle <- eto2_demo$`Cycle:`
eto2_demo$name_first <- eto2_demo$`First.Name`
eto2_demo$name_last <- eto2_demo$`Last.Name`
eto2_demo$gender <- eto2_demo$`Gender_3753`
eto2_demo$ethnic <- eto2_demo$`Ethnicity-Custom`
eto2_demo$race <- eto2_demo$`Race-Custom`
eto2_demo$dob <- eto2_demo$DOB
eto2_demo$source <- "eto2"
eto2_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Enrolled Current Program")
eto2_prog$subjectid <- eto2_prog$ID
eto2_prog$program <- eto2_prog$`Current.Program`
# ETO data - Cycle 3
eto3_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Demographics")
eto3_demo$subjectid <- eto3_demo$`Subject.Id`
eto3_demo$cycle <- eto3_demo$`Cycle:`
eto3_demo$name_first <- eto3_demo$`First.Name`
eto3_demo$name_last <- eto3_demo$`Last.Name`
eto3_demo$gender <- eto3_demo$`Gender_3753`
eto3_demo$ethnic <- eto3_demo$`Ethnicity-Custom`
eto3_demo$race <- eto3_demo$`Race-Custom`
eto3_demo$dob <- eto3_demo$DOB
eto3_demo$source <- "eto3"
eto3_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Training")
eto3_prog$subjectid <- eto3_prog$SubjectID
eto3_prog$program <- eto3_prog$`Program.Name`
# Salesforce data
salesforce1 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210208 - unlocked.xlsx')
salesforce2 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210209 - unlocked.xlsx')
salesforce2$name_first <- salesforce2$`Contact:.First.Name`
salesforce2$name_last <- salesforce2$`Contact:.Last.Name`
salesforce2$gender_sales <- salesforce2$`Gender`
salesforce2$ethnic_sales <- salesforce2$`Ethnicity`
salesforce2$race_sales <- salesforce2$`Race`
salesforce2$source_sales <- "salesforce"
# Select variables from Salesforce data
salesforce3 <- dplyr::select(salesforce2, name_first, name_last, gender_sales, ethnic_sales, race_sales, source_sales)
# Select variables from ETO data
eto2_demo_select <- dplyr::select(eto2_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto2_prog_select <- dplyr::select(eto2_prog, subjectid, `program`)
eto2 <- left_join(eto2_demo_select, eto2_prog_select, by="subjectid")
eto3_demo_select <- dplyr::select(eto3_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto3_prog_select <- dplyr::select(eto3_prog, subjectid, `program`)
eto3 <- left_join(eto3_demo_select, eto3_prog_select, by="subjectid")
# All ETO data
eto_data <- rbind(eto2, eto3)
# Merge REDCap data with ETO and Salesforce data
redcap_g2c_raw3 <- left_join(redcap_g2c_raw2, eto_data, by=c("name_first", "name_last"))
redcap_g2c_raw4 <- left_join(redcap_g2c_raw3, salesforce3, by=c("name_first", "name_last"))
redcap_g2c_raw <- unique(redcap_g2c_raw4)
redcap_g2c_raw$gender_merge <- if_else((is.na(redcap_g2c_raw$gender)), redcap_g2c_raw$gender_sales, redcap_g2c_raw$gender)
# Manually replace missing gender and cycle data
redcap_g2c_raw[redcap_g2c_raw$name_last=="Porter" & redcap_g2c_raw$name_first=="Jared","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Johnson" & redcap_g2c_raw$name_first=="Jamyra","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Baker" & redcap_g2c_raw$name_first=="Amori","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","cycle.y"] <- "Cycle 2"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","program"] <- "Civic Works"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Gladney" & redcap_g2c_raw$name_first=="Kayla","gender_merge"] <- "Female"
# Handle cycle 
redcap_g2c_raw$cycle1<- ifelse(is.na(redcap_g2c_raw$cycle.y), "Undetermined", redcap_g2c_raw$cycle.y)
```

```{r include=FALSE}
# Import Vanguard data from REDCap project
redcap_van_survey <- filter(redcap_raw_van, redcap_event_name=="youth_arm_1" | redcap_event_name=="youth_arm_2" | redcap_event_name=="youth_arm_3" | redcap_event_name=="youth_arm_4")

redcap_van_survey$arm <- if_else(redcap_van_survey$redcap_event_name=="youth_arm_1", "Youth Arm 1", if_else(redcap_van_survey$redcap_event_name=="youth_arm_2", "Youth Arm 2", if_else(redcap_van_survey$redcap_event_name=="youth_arm_3", "Youth Arm 3", if_else(redcap_van_survey$redcap_event_name=="youth_arm_4", "Youth Arm 4", "NA"))))
```

```{r include=FALSE}
# ptsd for Vanguard Study only
ptsd_van1 <- dplyr::select(redcap_van_survey, arm, q23a_trauma, q23b_trauma, q23c_trauma, q23d_trauma) 
# Assign labels to choices             
ptsd_van1$q23a_trauma <- if_else(ptsd_van1$q23a_trauma==4, "Etremely", if_else(ptsd_van1$q23a_trauma==3,"Quite a bit", if_else(ptsd_van1$q23a_trauma==2,"Moderately",      
if_else(ptsd_van1$q23a_trauma==1,"A little bit", if_else(ptsd_van1$q23a_trauma==0,"Not at all", "Prefer not to answer")))))
ptsd_van1$q23b_trauma <- if_else(ptsd_van1$q23b_trauma==4, "Etremely", if_else(ptsd_van1$q23b_trauma==3,"Quite a bit", if_else(ptsd_van1$q23b_trauma==2,"Moderately",      
if_else(ptsd_van1$q23b_trauma==1,"A little bit", if_else(ptsd_van1$q23b_trauma==0,"Not at all", "Prefer not to answer")))))
ptsd_van1$q23c_trauma <- if_else(ptsd_van1$q23c_trauma==4, "Etremely", if_else(ptsd_van1$q23c_trauma==3,"Quite a bit", if_else(ptsd_van1$q23c_trauma==2,"Moderately",      
if_else(ptsd_van1$q23c_trauma==1,"A little bit", if_else(ptsd_van1$q23c_trauma==0,"Not at all", "Prefer not to answer")))))
ptsd_van1$q23d_trauma <- if_else(ptsd_van1$q23d_trauma==4, "Etremely", if_else(ptsd_van1$q23d_trauma==3,"Quite a bit", if_else(ptsd_van1$q23d_trauma==2,"Moderately",      
if_else(ptsd_van1$q23d_trauma==1,"A little bit", if_else(ptsd_van1$q23d_trauma==0,"Not at all", "Prefer not to answer")))))
#Assign variable names                   
ptsd_van1$"Suddenly feeling or acting as if the stressful experience were actually happening again"<- ptsd_van1$q23a_trauma 
ptsd_van1$"Avoiding external reminders of the stressful experience"<- ptsd_van1$q23b_trauma
ptsd_van1$"Feeling distant or cut off from other people"<- ptsd_van1$q23c_trauma
ptsd_van1$"Irritable behavior, angry outbursts, or acting aggressively" <- ptsd_van1$q23d_trauma
#Select only the new variable names
ptsd_van <- dplyr::select(ptsd_van1, arm, "Suddenly feeling or acting as if the stressful experience were actually happening again"
,"Avoiding external reminders of the stressful experience"
,"Feeling distant or cut off from other people"
,"Irritable behavior, angry outbursts, or acting aggressively") 
#Assign an order to the variables
ptsd_van$"Suddenly feeling or acting as if the stressful experience were actually happening again" = factor(ptsd_van$"Suddenly feeling or acting as if the stressful experience were actually happening again", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely"), ordered = TRUE)
ptsd_van$"Avoiding external reminders of the stressful experience" = factor(ptsd_van$"Avoiding external reminders of the stressful experience", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely"), ordered = TRUE)
ptsd_van$"Feeling distant or cut off from other people" = factor(ptsd_van$"Feeling distant or cut off from other people", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely"), ordered = TRUE)
ptsd_van$"Irritable behavior, angry outbursts, or acting aggressively" = factor(ptsd_van$"Irritable behavior, angry outbursts, or acting aggressively", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely"), ordered = TRUE)
```
## {.tabset}
### Vanguard graphs
<p><strong>Vanguard Survey – PTSD Questions
<br>"Below is a list of problems that people sometimes have in response to a very stressful experience. Please read each problem carefully and then circle one of the numbers to the right to indicate how much you have been bothered by that problem in the <u>past 30 days</u>.
In the <u>past 30 days</u>, how much were you bothered by:"</p>
```{r echo=FALSE}
# Vanguard PTSD Plot all variables
ptsd_van_likert <- likert(ptsd_van[,2:5])
plot(ptsd_van_likert, wrap=25)
```
<p><strong>Vanguard Survey – PTSD Questions, by Youth Arm variable
<br>"Below is a list of problems that people sometimes have in response to a very stressful experience. Please read each problem carefully and then circle one of the numbers to the right to indicate how much you have been bothered by that problem in the <u>past 30 days</u>.
In the <u>past 30 days</u>, how much were you bothered by:"</p>
```{r echo=FALSE}
# Vanguard ptsd questions, BY CATEGORY
ptsd_van_cat1 <- likert(ptsd_van[,2:5], grouping=ptsd_van$arm)
plot(ptsd_van_cat1, wrap=50)
```

### Vanguard Tables
```{r echo=FALSE}
# Table of Vanguard ptsd variables
ptsdvan_table1 <- ptsd_van1 %>% tabyl(arm, q23a_trauma) %>% adorn_totals(c("row", "col"))
ptsdvan_table1 <- dplyr::select(ptsdvan_table1, arm, NA_, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely", Total)
ptsdvan_table2 <- ptsd_van1 %>% tabyl(arm, q23b_trauma) %>% adorn_totals(c("row", "col"))
ptsdvan_table2 <- dplyr::select(ptsdvan_table2, arm,NA_, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely", Total)
ptsdvan_table3 <- ptsd_van1 %>% tabyl(arm, q23c_trauma) %>% adorn_totals(c("row", "col"))
ptsdvan_table3 <- dplyr::select(ptsdvan_table3, arm, NA_, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely", Total)
ptsdvan_table4 <- ptsd_van1 %>% tabyl(arm, q23d_trauma) %>% adorn_totals(c("row", "col"))
ptsdvan_table4 <- dplyr::select(ptsdvan_table4, arm, NA_, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Etremely", Total)
```
<strong>"Suddenly feeling or acting as if the stressful experience were actually happening again" </strong>
```{r echo=FALSE}
formattable(ptsdvan_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"Avoiding external reminders of the stressful experience"</strong>
```{r echo=FALSE}
formattable(ptsdvan_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"Feeling distant or cut off from other people"</strong>
```{r echo=FALSE}
formattable(ptsdvan_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"Irritable behavior, angry outbursts, or acting aggressively"</strong>
```{r echo=FALSE}
formattable(ptsdvan_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```

```{r echo=FALSE}
# ptsd for G2C Study only
ptsd_g2c1 <- dplyr::select(redcap_g2c_raw, cycle1, q35a,	q35b,	q35c,	q35d)
# Assign labels to choices
ptsd_g2c1$q35a <- if_else(ptsd_g2c1$q35a==4, "Extremely", if_else(ptsd_g2c1$q35a==3,"Quite a bit", if_else(ptsd_g2c1$q35a==2,"Moderately",      
if_else(ptsd_g2c1$q35a==1,"A little bit", if_else(ptsd_g2c1$q35a==0,"Not at all", "Prefer not to answer")))))
ptsd_g2c1$q35b<- if_else(ptsd_g2c1$q35b==4, "Extremely", if_else(ptsd_g2c1$q35b==3,"Quite a bit", if_else(ptsd_g2c1$q35b==2,"Moderately",      
if_else(ptsd_g2c1$q35b==1,"A little bit", if_else(ptsd_g2c1$q35b==0,"Not at all", "Prefer not to answer")))))
ptsd_g2c1$q35c <- if_else(ptsd_g2c1$q35c==4, "Extremely", if_else(ptsd_g2c1$q35c==3,"Quite a bit", if_else(ptsd_g2c1$q35c==2,"Moderately",      
if_else(ptsd_g2c1$q35c==1,"A little bit", if_else(ptsd_g2c1$q35c==0,"Not at all", "Prefer not to answer")))))
ptsd_g2c1$q35d <- if_else(ptsd_g2c1$q35d==4, "Extremely", if_else(ptsd_g2c1$q35d==3,"Quite a bit", if_else(ptsd_g2c1$q35d==2,"Moderately",      
if_else(ptsd_g2c1$q35d==1,"A little bit", if_else(ptsd_g2c1$q35d==0,"Not at all", "Prefer not to answer")))))
# Assign variable names
ptsd_g2c1$"Suddenly feeling or acting as if the stressful experience were actually happening again"<- ptsd_g2c1$q35a 
ptsd_g2c1$"Avoiding external reminders of the stressful experience"<- ptsd_g2c1$q35b 
ptsd_g2c1$"Feeling distant or cut off from other people"<- ptsd_g2c1$q35c 
ptsd_g2c1$"Irritable behavior, angry outbursts, or acting aggressively"<- ptsd_g2c1$q35d 
# Select only the new variable names
ptsd_g2c <- dplyr::select(ptsd_g2c1, cycle1,
"Suddenly feeling or acting as if the stressful experience were actually happening again"
,"Avoiding external reminders of the stressful experience"
,"Feeling distant or cut off from other people"
,"Irritable behavior, angry outbursts, or acting aggressively")

ptsd_g2c$"Suddenly feeling or acting as if the stressful experience were actually happening again"= factor(ptsd_g2c$"Suddenly feeling or acting as if the stressful experience were actually happening again", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely"), ordered = TRUE)
ptsd_g2c$"Avoiding external reminders of the stressful experience"= factor(ptsd_g2c$"Avoiding external reminders of the stressful experience", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely"), ordered = TRUE)
ptsd_g2c$"Feeling distant or cut off from other people"= factor(ptsd_g2c$"Feeling distant or cut off from other people", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely"), ordered = TRUE)
ptsd_g2c$"Irritable behavior, angry outbursts, or acting aggressively"= factor(ptsd_g2c$"Irritable behavior, angry outbursts, or acting aggressively", levels = c("Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely"), ordered = TRUE)
```
### G2C graphs
<strong>"Below is a list of problems that people sometimes have in response to a very stressful experience. Please read each problem carefully and then circle one of the numbers to the right to indicate how much you have been bothered by that problem in the <u>past 30 days</u>.
In the <u>past 30 days</u>, how much were you bothered by:"/strong>
```{r echo=FALSE}
# G2c ptsd Plot all variables
ptsd_g2c_likert <- likert(ptsd_g2c[,2:5])
plot(ptsd_g2c_likert, wrap=30, order=F)
```
<p><strong>G2C Survey – ptsd Questions, by Youth Arm variable
<br>"Below is a list of problems that people sometimes have in response to a very stressful experience. Please read each problem carefully and then circle one of the numbers to the right to indicate how much you have been bothered by that problem in the <u>past 30 days</u>.
In the <u>past 30 days</u>, how much were you bothered by:"</strong></p>
```{r echo=FALSE}
# G2C ptsd questions, BY CATEGORY
ptsd_g2c_cat1 <- likert(ptsd_g2c[,2:5], grouping=ptsd_g2c$cycle1)
plot(ptsd_g2c_cat1, wrap=30)

```

### G2C Tables
```{r echo=FALSE}
# Table of g2cguard ptsd variables
ptsdg2c_table1 <- ptsd_g2c1 %>% tabyl(cycle1, q35a) %>% adorn_totals(c("row", "col"))
ptsdg2c_table1 <- dplyr::select(ptsdg2c_table1, cycle1, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely", Total)
ptsdg2c_table2 <- ptsd_g2c1 %>% tabyl(cycle1, q35b) %>% adorn_totals(c("row", "col"))
ptsdg2c_table2 <- dplyr::select(ptsdg2c_table2, cycle1, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely", Total)
ptsdg2c_table3 <- ptsd_g2c1 %>% tabyl(cycle1, q35c) %>% adorn_totals(c("row", "col"))
ptsdg2c_table3 <- dplyr::select(ptsdg2c_table3, cycle1, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely", Total)
ptsdg2c_table4 <- ptsd_g2c1 %>% tabyl(cycle1, q35d) %>% adorn_totals(c("row", "col"))
ptsdg2c_table4 <- dplyr::select(ptsdg2c_table4, cycle1, "Prefer not to answer", "Not at all", "A little bit", "Moderately", "Quite a bit", "Extremely", Total)
```
<strong>"Suddenly feeling or acting as if the stressful experience were actually happening again"</strong>
```{r echo=FALSE}
formattable(ptsdg2c_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"Avoiding external reminders of the stressful experience" </strong>
```{r echo=FALSE}
formattable(ptsdg2c_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"Feeling distant or cut off from other people"</strong>
```{r echo=FALSE}
formattable(ptsdg2c_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>"Irritable behavior, angry outbursts, or acting aggressively" </strong>
```{r echo=FALSE}
formattable(ptsdg2c_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```

### Vanguard vs. G2C
<strong>"Below is a list of problems that people sometimes have in response to a very stressful experience. Please read each problem carefully and then circle one of the numbers to the right to indicate how much you have been bothered by that problem in the <u>past 30 days</u>.
In the <u>past 30 days</u>, how much were you bothered by:"</strong>
```{r echo=FALSE}
# Merge the vanguard and g2c data for comparison
ptsd_g2c_merge <- dplyr::select(ptsd_g2c, -cycle1)
ptsd_g2c_merge$study <- "Grads2Careers"
ptsd_van_merge <- dplyr::select(ptsd_van, -arm)
ptsd_van_merge$study <- "Vanguard"
ptsd_merged <- rbind(ptsd_g2c_merge,ptsd_van_merge)
ptsd_merged1 <- dplyr::select(ptsd_merged, study, "Suddenly feeling or acting as if the stressful experience were actually happening again", "Avoiding external reminders of the stressful experience", "Feeling distant or cut off from other people", "Irritable behavior, angry outbursts, or acting aggressively")
# MERGED ptsd Plot by Study
ptsd_merged_cat <- likert(ptsd_merged[,1:4], grouping=ptsd_merged$study)
plot(ptsd_merged_cat)
```

```{r echo=FALSE, message=FALSE, warning=FALSE}
####################### Vanguard ####################
# Select Vanguard Food variables and create new variables for total score and dichotomous variable
ptsd_van_total <- dplyr::select(redcap_van_survey, arm, q23a_trauma, q23b_trauma, q23c_trauma, q23d_trauma) 
# Create a Food Insecurity score w/ and w/o "Prefer not to answer"
ptsd_van_total$ptsd_total <- ptsd_van_total$q23a_trauma + ptsd_van_total$q23b_trauma + ptsd_van_total$q23c_trauma + ptsd_van_total$q23d_trauma
ptsd_van_total$ptsd_total_no_refused <- ifelse(ptsd_van_total$ptsd_total>16, NA, ptsd_van_total$ptsd_total)
# Flagged if score 7 or greater
ptsd_van_total$ptsd_flagged <- if_else(ptsd_van_total$ptsd_total>=7, 1,0)
# Rename Vanguard variable
ptsd_van_total$"Suddenly feeling or acting as if the stressful experience were actually happening again" <- ptsd_van_total$q23a_trauma
ptsd_van_total$"Avoiding external reminders of the stressful experience" <- ptsd_van_total$q23b_trauma
ptsd_van_total$"Feeling distant or cut off from other people" <- ptsd_van_total$q23c_trauma
ptsd_van_total$"Irritable behavior, angry outbursts, or acting aggressively" <- ptsd_van_total$q23d_trauma  
#Select only the new variable names
ptsd_van_totals <- dplyr::select(ptsd_van_total, ptsd_total, ptsd_total_no_refused, ptsd_flagged,
"Suddenly feeling or acting as if the stressful experience were actually happening again","Avoiding external reminders of the stressful experience","Feeling distant or cut off from other people"
,"Irritable behavior, angry outbursts, or acting aggressively")
######################## G2C #######################
# Add variable names, total and select new variables for G2C data
ptsd_g2c_total <- dplyr::select(redcap_g2c_raw, q35a, q35b, q35c, q35d)
ptsd_g2c_total$ptsd_total <- ptsd_g2c_total$q35a + ptsd_g2c_total$q35b + ptsd_g2c_total$q35c + ptsd_g2c_total$q35d
ptsd_g2c_total$ptsd_total_no_refused <- ifelse(ptsd_g2c_total$ptsd_total>16, NA, ptsd_g2c_total$ptsd_total)
ptsd_g2c_total$ptsd_flagged <- if_else(ptsd_g2c_total$ptsd_total>=7, 1,0)
# Rename G2C variable
ptsd_g2c_total$"Suddenly feeling or acting as if the stressful experience were actually happening again" <- ptsd_g2c_total$q35a
ptsd_g2c_total$"Avoiding external reminders of the stressful experience" <- ptsd_g2c_total$q35b
ptsd_g2c_total$"Feeling distant or cut off from other people"<- ptsd_g2c_total$q35c
ptsd_g2c_total$"Irritable behavior, angry outbursts, or acting aggressively"<- ptsd_g2c_total$q35d
#Select only the new variable names
ptsd_g2c_totals <- dplyr::select(ptsd_g2c_total, ptsd_total, ptsd_total_no_refused, ptsd_flagged,"Suddenly feeling or acting as if the stressful experience were actually happening again", "Avoiding external reminders of the stressful experience","Feeling distant or cut off from other people","Irritable behavior, angry outbursts, or acting aggressively") 
```

```{r echo=FALSE}
# Combine the studies
ptsd1 <- as.data.frame(ftable(ptsd_van_totals$ptsd_total_no_refused))
ptsd1$Vanguard <- ptsd1$Freq
ptsd_van_totals$study <-"Vanguard"

ptsd2 <- as.data.frame(ftable(ptsd_g2c_totals$ptsd_total_no_refused))
ptsd2$G2C <- ptsd2$Freq
ptsd_g2c_totals$study <- "G2C"

ptsd_total_merged <- rbind(ptsd_g2c_totals, ptsd_van_totals)
```
<strong>Histogram of ptsd Scores (total of 4 variables, range:0-16): Vanguard vs. G2C </strong>
```{r echo=FALSE}
# Create a grouped bar chart
ptsd1$subgroup <- "Vanguard"
ptsd1$group <- ptsd1$Var1
ptsd1$values <- ptsd1$Freq
ptsd1a <- dplyr::select(ptsd1, subgroup, group, values)
ptsd2$subgroup <- "G2c"
ptsd2$group <- ptsd2$Var1
ptsd2$values <- ptsd2$Freq
ptsd2a <- dplyr::select(ptsd2, subgroup, group, values)
ptsd3 <- rbind(ptsd1a, ptsd2a)

ggplot(ptsd3, 
       aes(x=group, 
           y=values, 
           fill=subgroup)) + 
    geom_bar(position="dodge", 
             stat="identity")
        
```

```{r echo=FALSE}
ptsd_total_merged1 <- dplyr::filter(ptsd_total_merged, !is.na(ptsd_total) & ptsd_total <=30)
histogram(~ ptsd_total | study,
          main = "PTSD/Trauma Score, Percent Comparison of Vanguard and G2C",
          xlab = "Score",
          data=ptsd_total_merged1,
          type="percent",
          layout=c(1,2))      #  columns and rows of individual plots
```

```{r echo=FALSE}
wilcox.test(ptsd_total_merged$ptsd_total_no_refused ~ ptsd_total_merged$study)

t.test(ptsd_total_merged$ptsd_total_no_refused ~ ptsd_total_merged$study)
```
ptsd Score comparison
```{r echo=FALSE}
boxplot(ptsd_total_merged$ptsd_total_no_refused ~ ptsd_total_merged$study, col="#69b3a2" , ylab="Total PTSD/Trauma Score", xlab = "Study")
```

## 4.  Depression

```{r message=FALSE, warning=FALSE, include=FALSE}
#Load library
library(Hmisc)
library(summarytools)
library(tidyverse)
library(readxl)
library(dplyr)
library(likert)
library(kableExtra)
library(formattable)
library(janitor)
```

```{r message=FALSE, warning=FALSE, include=FALSE}
# Import G2C REDCap data for comparison to Vanguard
redcap_g2c_raw2 = filter(redcap_g2c_raw1, heybmore_survey_complete==2)
redcap_g2c_raw2$name_first <- redcap_g2c_raw2$info_fn
redcap_g2c_raw2$name_last <- redcap_g2c_raw2$info_ln
redcap_g2c_raw2$dob <- redcap_g2c_raw2$dob
# ETO data - Cycle 2
eto2_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Demographics")
eto2_demo$subjectid <- eto2_demo$`Subject.Unique.Identifier`
eto2_demo$cycle <- eto2_demo$`Cycle:`
eto2_demo$name_first <- eto2_demo$`First.Name`
eto2_demo$name_last <- eto2_demo$`Last.Name`
eto2_demo$gender <- eto2_demo$`Gender_3753`
eto2_demo$ethnic <- eto2_demo$`Ethnicity-Custom`
eto2_demo$race <- eto2_demo$`Race-Custom`
eto2_demo$dob <- eto2_demo$DOB
eto2_demo$source <- "eto2"
eto2_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHU_Request022021_Demographics(cycle 2).xlsx', sheet="Enrolled Current Program")
eto2_prog$subjectid <- eto2_prog$ID
eto2_prog$program <- eto2_prog$`Current.Program`
# ETO data - Cycle 3
eto3_demo = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Demographics")
eto3_demo$subjectid <- eto3_demo$`Subject.Id`
eto3_demo$cycle <- eto3_demo$`Cycle:`
eto3_demo$name_first <- eto3_demo$`First.Name`
eto3_demo$name_last <- eto3_demo$`Last.Name`
eto3_demo$gender <- eto3_demo$`Gender_3753`
eto3_demo$ethnic <- eto3_demo$`Ethnicity-Custom`
eto3_demo$race <- eto3_demo$`Race-Custom`
eto3_demo$dob <- eto3_demo$DOB
eto3_demo$source <- "eto3"
eto3_prog = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/ETO Data/JHURequest022021_Cycle3.xlsx', sheet="Training")
eto3_prog$subjectid <- eto3_prog$SubjectID
eto3_prog$program <- eto3_prog$`Program.Name`
# Salesforce data
salesforce1 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210208 - unlocked.xlsx')
salesforce2 = read.xlsx('/Users/jon/Desktop/PFRH/Grads2Careers - HEYBMORE/Data/Salesforce data/Salesforce Data for JHU 210209 - unlocked.xlsx')
salesforce2$name_first <- salesforce2$`Contact:.First.Name`
salesforce2$name_last <- salesforce2$`Contact:.Last.Name`
salesforce2$gender_sales <- salesforce2$`Gender`
salesforce2$ethnic_sales <- salesforce2$`Ethnicity`
salesforce2$race_sales <- salesforce2$`Race`
salesforce2$source_sales <- "salesforce"
# Select variables from Salesforce data
salesforce3 <- dplyr::select(salesforce2, name_first, name_last, gender_sales, ethnic_sales, race_sales, source_sales)
# Select variables from ETO data
eto2_demo_select <- dplyr::select(eto2_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto2_prog_select <- dplyr::select(eto2_prog, subjectid, `program`)
eto2 <- left_join(eto2_demo_select, eto2_prog_select, by="subjectid")
eto3_demo_select <- dplyr::select(eto3_demo, subjectid, cycle, name_first, name_last, gender, ethnic, race, dob, source)
eto3_prog_select <- dplyr::select(eto3_prog, subjectid, `program`)
eto3 <- left_join(eto3_demo_select, eto3_prog_select, by="subjectid")
# All ETO data
eto_data <- rbind(eto2, eto3)
# Merge REDCap data with ETO and Salesforce data
redcap_g2c_raw3 <- left_join(redcap_g2c_raw2, eto_data, by=c("name_first", "name_last"))
redcap_g2c_raw4 <- left_join(redcap_g2c_raw3, salesforce3, by=c("name_first", "name_last"))
redcap_g2c_raw <- unique(redcap_g2c_raw4)
redcap_g2c_raw$gender_merge <- if_else((is.na(redcap_g2c_raw$gender)), redcap_g2c_raw$gender_sales, redcap_g2c_raw$gender)
# Manually replace missing gender and cycle data
redcap_g2c_raw[redcap_g2c_raw$name_last=="Porter" & redcap_g2c_raw$name_first=="Jared","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Christian" & redcap_g2c_raw$name_first=="Ja'Daia","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Johnson" & redcap_g2c_raw$name_first=="Jamyra","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Baker" & redcap_g2c_raw$name_first=="Amori","gender_merge"] <- "Female"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","cycle.y"] <- "Cycle 2"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Collins" & redcap_g2c_raw$name_first=="Jatay","program"] <- "Civic Works"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","gender_merge"] <- "Male"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Evans" & redcap_g2c_raw$name_first=="Dasean","cycle.y"] <- "Cycle 3"
redcap_g2c_raw[redcap_g2c_raw$name_last=="Gladney" & redcap_g2c_raw$name_first=="Kayla","gender_merge"] <- "Female"
# Handle cycle 
redcap_g2c_raw$cycle1<- ifelse(is.na(redcap_g2c_raw$cycle.y), "Undetermined", redcap_g2c_raw$cycle.y)
```

```{r include=FALSE}
# Import Vanguard data from REDCap project
redcap_van_survey <- filter(redcap_raw_van, redcap_event_name=="youth_arm_1" | redcap_event_name=="youth_arm_2" | redcap_event_name=="youth_arm_3" | redcap_event_name=="youth_arm_4")

redcap_van_survey$arm <- if_else(redcap_van_survey$redcap_event_name=="youth_arm_1", "Youth Arm 1", if_else(redcap_van_survey$redcap_event_name=="youth_arm_2", "Youth Arm 2", if_else(redcap_van_survey$redcap_event_name=="youth_arm_3", "Youth Arm 3", if_else(redcap_van_survey$redcap_event_name=="youth_arm_4", "Youth Arm 4", "NA"))))
```

```{r include=FALSE}
# Depression for Vanguard Study only
depression_van1 <- dplyr::select(redcap_van_survey, arm, q21a_depression, q21b_depression, q21c_depression, q21d_depression, q21e_depression, q21f_depression, q21g_depression, q21h_depression, q21i_depression, q21j_depression) 
# Assign labels to choices             
depression_van1$q21a_depression <-  if_else(depression_van1$q21a_depression==3,"5-7 days", if_else(depression_van1$q21a_depression==2,"3-4 days", if_else(depression_van1$q21a_depression==1,"1-2 days", if_else(depression_van1$q21a_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21b_depression <-  if_else(depression_van1$q21b_depression==3,"5-7 days", if_else(depression_van1$q21b_depression==2,"3-4 days", if_else(depression_van1$q21b_depression==1,"1-2 days", if_else(depression_van1$q21b_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21c_depression <-  if_else(depression_van1$q21c_depression==3,"5-7 days", if_else(depression_van1$q21c_depression==2,"3-4 days", if_else(depression_van1$q21c_depression==1,"1-2 days", if_else(depression_van1$q21c_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21d_depression <-  if_else(depression_van1$q21d_depression==3,"5-7 days", if_else(depression_van1$q21d_depression==2,"3-4 days", if_else(depression_van1$q21d_depression==1,"1-2 days", if_else(depression_van1$q21d_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21e_depression <-  if_else(depression_van1$q21e_depression==3,"5-7 days", if_else(depression_van1$q21e_depression==2,"3-4 days", if_else(depression_van1$q21e_depression==1,"1-2 days", if_else(depression_van1$q21e_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21f_depression <-  if_else(depression_van1$q21f_depression==3,"5-7 days", if_else(depression_van1$q21f_depression==2,"3-4 days", if_else(depression_van1$q21f_depression==1,"1-2 days", if_else(depression_van1$q21f_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21g_depression <-  if_else(depression_van1$q21g_depression==3,"5-7 days", if_else(depression_van1$q21g_depression==2,"3-4 days", if_else(depression_van1$q21g_depression==1,"1-2 days", if_else(depression_van1$q21g_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21h_depression <-  if_else(depression_van1$q21h_depression==3,"5-7 days", if_else(depression_van1$q21h_depression==2,"3-4 days", if_else(depression_van1$q21h_depression==1,"1-2 days", if_else(depression_van1$q21h_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21i_depression <-  if_else(depression_van1$q21i_depression==3,"5-7 days", if_else(depression_van1$q21i_depression==2,"3-4 days", if_else(depression_van1$q21i_depression==1,"1-2 days", if_else(depression_van1$q21i_depression==0,"less than 1 day", "Prefer not to answer"))))
depression_van1$q21j_depression <-  if_else(depression_van1$q21j_depression==3,"5-7 days", if_else(depression_van1$q21j_depression==2,"3-4 days", if_else(depression_van1$q21j_depression==1,"1-2 days", if_else(depression_van1$q21j_depression==0,"less than 1 day", "Prefer not to answer"))))
# Assign variable names                   
depression_van1$"I was bothered by things that usually don't bother me"<- depression_van1$q21a_depression 
depression_van1$"I had trouble keeping my mind on what I was doing"<- depression_van1$q21b_depression 
depression_van1$"I felt lonely"<- depression_van1$q21c_depression 
depression_van1$"I felt depressed" <- depression_van1$q21d_depression
depression_van1$"I felt that everything was an effort"<- depression_van1$q21e_depression 
depression_van1$"I felt hopeful about the future"<- depression_van1$q21f_depression 
depression_van1$"I felt fearful"<- depression_van1$q21g_depression 
depression_van1$"My sleep was restless" <- depression_van1$q21h_depression
depression_van1$"I was happy"<- depression_van1$q21i_depression 
depression_van1$"I could not get going" <- depression_van1$q21j_depression
# Select only the new variable names
depression_van <- dplyr::select(depression_van1, arm,"I was bothered by things that usually don't bother me","I had trouble keeping my mind on what I was doing","I felt lonely","I felt depressed" ,"I felt that everything was an effort","I felt hopeful about the future" ,"I felt fearful","My sleep was restless" ,"I was happy","I could not get going") 
# Assign an order to the variables
depression_van$"I was bothered by things that usually don't bother me" = factor(depression_van$"I was bothered by things that usually don't bother me", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I had trouble keeping my mind on what I was doing" = factor(depression_van$"I had trouble keeping my mind on what I was doing", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I felt lonely" = factor(depression_van$"I felt lonely", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I felt depressed" = factor(depression_van$"I felt depressed", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I felt that everything was an effort" = factor(depression_van$"I felt that everything was an effort", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I felt hopeful about the future" = factor(depression_van$"I felt hopeful about the future", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I felt fearful" = factor(depression_van$"I felt fearful", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"My sleep was restless" = factor(depression_van$"My sleep was restless", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I was happy" = factor(depression_van$"I was happy", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_van$"I could not get going" = factor(depression_van$"I could not get going", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
```
## {.tabset}
### Vanguard graphs
<p><strong>Vanguard Survey – Depression Questions
<br>Below is a list of the ways you might have felt or behaved. Please tell me how often you have felt this way <u>during the past 7 days.</strong></u></p>
```{r echo=FALSE}
# Vanguard Depression Plot all variables
depression_van_likert <- likert(depression_van[,2:10])
plot(depression_van_likert, wrap=30)
```
<p><strong>Vanguard Survey – Depression Questions, by Youth Arm variable
<br>Below is a list of the ways you might have felt or behaved. Please tell me how often you have felt this way <u>during the past 7 days.</strong></u></p>
```{r echo=FALSE}
# Vanguard Depression questions, BY CATEGORY
depression_van_cat1 <- likert(depression_van[,2:6], grouping=depression_van$arm)
plot(depression_van_cat1, wrap=50)

depression_van_cat2 <- likert(depression_van[,6:11], grouping=depression_van$arm)
plot(depression_van_cat2, wrap=50)
```

### Vanguard Tables
```{r echo=FALSE}
# Table of Vanguard depression variables
depressionvan_table1 <- depression_van1 %>% tabyl(arm, q21a_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table2 <- depression_van1 %>% tabyl(arm, q21b_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table3 <- depression_van1 %>% tabyl(arm, q21c_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table4 <- depression_van1 %>% tabyl(arm, q21d_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table5 <- depression_van1 %>% tabyl(arm, q21e_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table6 <- depression_van1 %>% tabyl(arm, q21f_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table7 <- depression_van1 %>% tabyl(arm, q21g_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table8 <- depression_van1 %>% tabyl(arm, q21h_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table9 <- depression_van1 %>% tabyl(arm, q21i_depression) %>% adorn_totals(c("row", "col"))
depressionvan_table10 <- depression_van1 %>% tabyl(arm, q21j_depression) %>% adorn_totals(c("row", "col"))
```
<strong>I was bothered by things that usually don't bother me </strong>
```{r echo=FALSE}
formattable(depressionvan_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I had trouble keeping my mind on what I was doing </strong>
```{r echo=FALSE}
formattable(depressionvan_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt lonely </strong>
```{r echo=FALSE}
formattable(depressionvan_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt depressed </strong>
```{r echo=FALSE}
formattable(depressionvan_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt that everything was an effort  </strong>
```{r echo=FALSE}
formattable(depressionvan_table5 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt hopeful about the future </strong> 
```{r echo=FALSE}
formattable(depressionvan_table6 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt fearful </strong>
```{r echo=FALSE}
formattable(depressionvan_table7 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>My sleep was restless </strong>
```{r echo=FALSE}
formattable(depressionvan_table8 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I was happy </strong>
```{r echo=FALSE}
formattable(depressionvan_table9 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I could not get going </strong>
```{r echo=FALSE}
formattable(depressionvan_table10 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```

```{r echo=FALSE}
# Subset Depression questions for G2C Study only
depression_g2c1 <- dplyr::select(redcap_g2c_raw, cycle1, q33a,	q33b,	q33c,	q33d, q33e,	q33f,	q33g,	q33h, q33i,	q33j)
# Assign labels to choices
depression_g2c1$q33a <-  if_else( depression_g2c1$q33a==3,"5-7 days", if_else(depression_g2c1$q33a==2,"3-4 days", if_else(depression_g2c1$q33a==1,"1-2 days", if_else(depression_g2c1$q33a==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33b <-  if_else(depression_g2c1$q33b==3,"5-7 days", if_else(depression_g2c1$q33b==2,"3-4 days", if_else(depression_g2c1$q33b==1,"1-2 days", if_else(depression_g2c1$q33b==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33c <-  if_else(depression_g2c1$q33c==3,"5-7 days", if_else(depression_g2c1$q33c==2,"3-4 days", if_else(depression_g2c1$q33c==1,"1-2 days", if_else(depression_g2c1$q33c==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33d <-  if_else(depression_g2c1$q33d==3,"5-7 days", if_else(depression_g2c1$q33d==2,"3-4 days", if_else(depression_g2c1$q33d==1,"1-2 days", if_else(depression_g2c1$q33d==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33e <-  if_else(depression_g2c1$q33e==3,"5-7 days", if_else(depression_g2c1$q33e==2,"3-4 days", if_else(depression_g2c1$q33e==1,"1-2 days", if_else(depression_g2c1$q33e==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33f <-  if_else(depression_g2c1$q33f==3,"5-7 days", if_else(depression_g2c1$q33f==2,"3-4 days", if_else(depression_g2c1$q33f==1,"1-2 days", if_else(depression_g2c1$q33f==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33g <-  if_else(depression_g2c1$q33g==3,"5-7 days", if_else(depression_g2c1$q33g==2,"3-4 days",  if_else(depression_g2c1$q33g==1,"1-2 days", if_else(depression_g2c1$q33g==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33h <-  if_else(depression_g2c1$q33h==3,"5-7 days", if_else(depression_g2c1$q33h==2,"3-4 days",  if_else(depression_g2c1$q33h==1,"1-2 days", if_else(depression_g2c1$q33h==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33i <-  if_else(depression_g2c1$q33i==3,"5-7 days", if_else(depression_g2c1$q33i==2,"3-4 days",  if_else(depression_g2c1$q33i==1,"1-2 days", if_else(depression_g2c1$q33i==0,"less than 1 day", "Prefer not to answer"))))
depression_g2c1$q33j <-  if_else(depression_g2c1$q33j==3,"5-7 days", if_else(depression_g2c1$q33j==2,"3-4 days", if_else(depression_g2c1$q33j==1,"1-2 days", if_else(depression_g2c1$q33j==0,"less than 1 day", "Prefer not to answer"))))
#Assign variable names                   
depression_g2c1$"I was bothered by things that usually don't bother me"<- depression_g2c1$q33a
depression_g2c1$"I had trouble keeping my mind on what I was doing"<- depression_g2c1$q33b 
depression_g2c1$"I felt lonely"<- depression_g2c1$q33i
depression_g2c1$"I felt depressed" <- depression_g2c1$q33c
depression_g2c1$"I felt that everything was an effort"<- depression_g2c1$q33d
depression_g2c1$"I felt hopeful about the future"<- depression_g2c1$q33e
depression_g2c1$"I felt fearful"<- depression_g2c1$q33f
depression_g2c1$"My sleep was restless" <- depression_g2c1$q33g
depression_g2c1$"I was happy"<- depression_g2c1$q33h
depression_g2c1$"I could not get going" <- depression_g2c1$q33j
#Select only the new variable names
depression_g2c <- dplyr::select(depression_g2c1, cycle1, "I was bothered by things that usually don't bother me" ,"I had trouble keeping my mind on what I was doing", "I felt lonely", "I felt depressed", "I felt that everything was an effort","I felt hopeful about the future" ,"I felt fearful","My sleep was restless" 
,"I was happy","I could not get going") 
#Assign an order to the variables
depression_g2c$"I was bothered by things that usually don't bother me" = factor(depression_g2c$"I was bothered by things that usually don't bother me", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I had trouble keeping my mind on what I was doing" = factor(depression_g2c$"I had trouble keeping my mind on what I was doing", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I felt lonely" = factor(depression_g2c$"I felt lonely", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I felt depressed" = factor(depression_g2c$"I felt depressed", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I felt that everything was an effort" = factor(depression_g2c$"I felt that everything was an effort", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I felt hopeful about the future" = factor(depression_g2c$"I felt hopeful about the future", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I felt fearful" = factor(depression_g2c$"I felt fearful", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"My sleep was restless" = factor(depression_g2c$"My sleep was restless", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I was happy" = factor(depression_g2c$"I was happy", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
depression_g2c$"I could not get going" = factor(depression_g2c$"I could not get going", levels = c("Prefer not to answer", "less than 1 day", "1-2 days", "3-4 days", "5-7 days"), ordered = TRUE)
```
### G2C graphs
<strong>Below is a list of the ways you might have felt or behaved. Please tell me how often you have felt this way <u>during the past 7 days.</u></strong>
```{r echo=FALSE}
# G2c Depression Plot all variables
depression_g2c_likert <- likert(depression_g2c[,2:10])
plot(depression_g2c_likert, wrap=40, order=F)
```
<p><strong>G2C Survey – Depression Questions, by Youth Arm variable
<br>Below is a list of the ways you might have felt or behaved. Please tell me how often you have felt this way <u>during the past 7 days.</strong></u></p>
```{r echo=FALSE}
# G2C Depression questions, BY CATEGORY
depression_g2c_cat1 <- likert(depression_g2c[,2:6], grouping=depression_g2c$cycle1)
plot(depression_g2c_cat1, wrap=30)

depression_g2c_cat2 <- likert(depression_g2c[,7:11], grouping=depression_g2c$cycle1)
plot(depression_g2c_cat2, wrap=30)
```

### G2C Tables
```{r echo=FALSE}
# Table of g2cguard depression variables
depressiong2c_table1 <- depression_g2c1 %>% tabyl(cycle1, q33a) %>% adorn_totals(c("row", "col"))
depressiong2c_table2 <- depression_g2c1 %>% tabyl(cycle1, q33b) %>% adorn_totals(c("row", "col"))
depressiong2c_table3 <- depression_g2c1 %>% tabyl(cycle1, q33i) %>% adorn_totals(c("row", "col"))
depressiong2c_table4 <- depression_g2c1 %>% tabyl(cycle1, q33c) %>% adorn_totals(c("row", "col"))
depressiong2c_table5 <- depression_g2c1 %>% tabyl(cycle1, q33d) %>% adorn_totals(c("row", "col"))
depressiong2c_table6 <- depression_g2c1 %>% tabyl(cycle1, q33e) %>% adorn_totals(c("row", "col"))
depressiong2c_table7 <- depression_g2c1 %>% tabyl(cycle1, q33f) %>% adorn_totals(c("row", "col"))
depressiong2c_table8 <- depression_g2c1 %>% tabyl(cycle1, q33g) %>% adorn_totals(c("row", "col"))
depressiong2c_table9 <- depression_g2c1 %>% tabyl(cycle1, q33h) %>% adorn_totals(c("row", "col"))
depressiong2c_table10 <- depression_g2c1 %>% tabyl(cycle1, q33j) %>% adorn_totals(c("row", "col"))
```
<strong>I was bothered by things that usually don't bother me </strong>
```{r echo=FALSE}
formattable(depressiong2c_table1 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I had trouble keeping my mind on what I was doing </strong>
```{r echo=FALSE}
formattable(depressiong2c_table2 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt lonely </strong>
```{r echo=FALSE}
formattable(depressiong2c_table3 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt depressed </strong>
```{r echo=FALSE}
formattable(depressiong2c_table4 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt that everything was an effort  </strong>
```{r echo=FALSE}
formattable(depressiong2c_table5 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt hopeful about the future </strong> 
```{r echo=FALSE}
formattable(depressiong2c_table6 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I felt fearful </strong>
```{r echo=FALSE}
formattable(depressiong2c_table7 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>My sleep was restless </strong>
```{r echo=FALSE}
formattable(depressiong2c_table8 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I was happy </strong>
```{r echo=FALSE}
formattable(depressiong2c_table9 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```
<strong>I could not get going </strong>
```{r echo=FALSE}
formattable(depressiong2c_table10 %>% adorn_percentages("row") %>% adorn_pct_formatting(digits = 1))
```


### Vanguard vs. G2C
<strong>Please answer the following questions based on how you felt in the past 7 days.</strong>
```{r echo=FALSE}
# Merge the vanguard and g2c data for comparison
depression_g2c_merge <- dplyr::select(depression_g2c, -cycle1)
depression_g2c_merge$study <- "Grads2Careers"
depression_van_merge <- dplyr::select(depression_van, -arm)
depression_van_merge$study <- "Vanguard"
depression_merged <- rbind(depression_g2c_merge,depression_van_merge)
depression_merged1 <- dplyr::select(depression_merged, "I was bothered by things that usually don't bother me" ,"I had trouble keeping my mind on what I was doing", "I felt lonely", "I felt depressed", "I felt that everything was an effort")
depression_merged2 <- dplyr::select(depression_merged, "I felt hopeful about the future" ,"I felt fearful","My sleep was restless" 
,"I was happy","I could not get going")

# MERGED Depression Plot by Study
depression_merged_cat1 <- likert(depression_merged1, grouping=depression_merged$study)
plot(depression_merged_cat1)
depression_merged_cat2 <- likert(depression_merged2, grouping=depression_merged$study)
plot(depression_merged_cat2)
```

```{r echo=FALSE, message=FALSE, warning=FALSE}
####################### Vanguard ####################
# Select Vanguard Depression variables and create new variables for total score and dichotomous variable
depression_van_total <- dplyr::select(redcap_van_survey, arm, q21a_depression, q21b_depression, q21c_depression, q21d_depression, q21e_depression, q21f_depression, q21g_depression, q21h_depression, q21i_depression, q21j_depression) 
# Reverse Code 2 Variables
depression_van_total$q21i_reversed <- ifelse(depression_van_total$q21i_depression==0,3,ifelse(depression_van_total$q21i_depression==1,2,ifelse(depression_van_total$q21i_depression==2,1,0)))
depression_van_total$q21f_reversed <- ifelse(depression_van_total$q21f_depression==0,3,ifelse(depression_van_total$q21f_depression==1,2,ifelse(depression_van_total$q21f_depression==2,1,0)))

# Create a Depression score w/ and w/o "Prefer not to answer"
depression_van_total$depression_total <- depression_van_total$q21a_depression + depression_van_total$q21b_depression + depression_van_total$q21c_depression + depression_van_total$q21d_depression + depression_van_total$q21e_depression + depression_van_total$q21f_reversed + depression_van_total$q21g_depression + depression_van_total$q21h_depression + depression_van_total$q21i_reversed + depression_van_total$q21j_depression
depression_van_total$depression_total_no_refused <- ifelse(depression_van_total$depression_total>30, NA, depression_van_total$depression_total)
# Flagged if score 9 or greater
depression_van_total$depression_flagged <- if_else(depression_van_total$depression_total>=9, 1,0)
# Rename Vanguard variables
depression_van_total$"I was bothered by things that usually don't bother me"<- depression_van_total$q21a_depression 
depression_van_total$"I had trouble keeping my mind on what I was doing"<- depression_van_total$q21b_depression 
depression_van_total$"I felt lonely"<- depression_van_total$q21c_depression 
depression_van_total$"I felt depressed" <- depression_van_total$q21d_depression
depression_van_total$"I felt that everything was an effort"<- depression_van_total$q21e_depression 
depression_van_total$"I felt hopeful about the future"<- depression_van_total$q21f_reversed 
depression_van_total$"I felt fearful"<- depression_van_total$q21g_depression 
depression_van_total$"My sleep was restless" <- depression_van_total$q21h_depression
depression_van_total$"I was happy"<- depression_van_total$q21i_reversed 
depression_van_total$"I could not get going" <- depression_van_total$q21j_depression
#Select only the new variable names
depression_van_totals <- dplyr::select(depression_van_total, depression_total, depression_total_no_refused, depression_flagged, "I was bothered by things that usually don't bother me" ,"I had trouble keeping my mind on what I was doing", "I felt lonely", "I felt depressed", "I felt that everything was an effort","I felt hopeful about the future" ,"I felt fearful","My sleep was restless" 
,"I was happy","I could not get going")

######################## G2C #######################
# Add variable names, total and select new variables for G2C data
depression_g2c_total <- dplyr::select(redcap_g2c_raw, cycle.y, q33a, q33b, q33c,	q33d, q33e,	q33f,	q33g,	q33h, q33i,	q33j)
# Reverse Code 2 Variables
depression_g2c_total$q33e_reversed <- ifelse(depression_g2c_total$q33e==0,3,ifelse(depression_g2c_total$q33e==1,2,ifelse(depression_g2c_total$q33e==2,1,0)))
depression_g2c_total$q33h_reversed <- ifelse(depression_g2c_total$q33h==0,3,ifelse(depression_g2c_total$q33h==1,2,ifelse(depression_g2c_total$q33h==2,1,0)))
# Create a Depression score w/ and w/o "Prefer not to answer"
depression_g2c_total$depression_total <- depression_g2c_total$q33a + depression_g2c_total$q33b + depression_g2c_total$q33c + depression_g2c_total$q33d + depression_g2c_total$q33e_reversed + depression_g2c_total$q33f + depression_g2c_total$q33g + depression_g2c_total$q33h_reversed + depression_g2c_total$q33i + depression_g2c_total$q33j
depression_g2c_total$depression_total_no_refused <- ifelse(depression_g2c_total$depression_total>30, NA, depression_g2c_total$depression_total)
# Flagged if score 9 or greater
depression_g2c_total$depression_flagged <- if_else(depression_g2c_total$depression_total>=9, 1,0)
# Rename G2C variable
depression_g2c_total$"I was bothered by things that usually don't bother me"<- depression_g2c_total$q33a
depression_g2c_total$"I had trouble keeping my mind on what I was doing"<- depression_g2c_total$q33b 
depression_g2c_total$"I felt lonely"<- depression_g2c_total$q33i
depression_g2c_total$"I felt depressed" <- depression_g2c_total$q33c
depression_g2c_total$"I felt that everything was an effort"<- depression_g2c_total$q33d
depression_g2c_total$"I felt hopeful about the future"<- depression_g2c_total$q33e_reversed
depression_g2c_total$"I felt fearful"<- depression_g2c_total$q33f
depression_g2c_total$"My sleep was restless" <- depression_g2c_total$q33g
depression_g2c_total$"I was happy"<- depression_g2c_total$q33h_reversed
depression_g2c_total$"I could not get going" <- depression_g2c_total$q33j
#Select only the new variable names
depression_g2c_totals <- dplyr::select(depression_g2c_total, depression_total, depression_total_no_refused, depression_flagged,"I was bothered by things that usually don't bother me" ,"I had trouble keeping my mind on what I was doing", "I felt lonely", "I felt depressed", "I felt that everything was an effort","I felt hopeful about the future" ,"I felt fearful","My sleep was restless" 
,"I was happy","I could not get going") 
```

```{r echo=FALSE}
# Combine the studies
depression1 <- as.data.frame(ftable(depression_van_totals$depression_total_no_refused))
depression1$Vanguard <- depression1$Freq
depression_van_totals$study <-"Vanguard"


depression2 <- as.data.frame(ftable(depression_g2c_totals$depression_total_no_refused))
depression2$G2C <- depression2$Freq
depression_g2c_totals$study <- "G2C"

depression_total_merged <- rbind(depression_g2c_totals, depression_van_totals)
```
<strong>Histogram of Depression Scores (total of 10 variables, range:0-30): Vanguard vs. G2C </strong>
```{r echo=FALSE}
# Create a grouped bar chart
depression1$subgroup <- "Vanguard"
depression1$group <- depression1$Var1
depression1$values <- depression1$Freq
depression1a <- dplyr::select(depression1, subgroup, group, values)
depression2$subgroup <- "G2c"
depression2$group <- depression2$Var1
depression2$values <- depression2$Freq
depression2a <- dplyr::select(depression2, subgroup, group, values)
depression3 <- rbind(depression1a, depression2a)

ggplot(depression3, 
       aes(x=group, 
           y=values, 
           fill=subgroup)) + 
    geom_bar(position="dodge", 
             stat="identity")
        
```

```{r echo=FALSE}
depression_total_merged1 <- dplyr::filter(depression_total_merged, !is.na(depression_total) & depression_total <=30)
histogram(~ depression_total | study,
          main = "Depression Score, Percent Comparison of Vanguard and G2C",
          xlab = "Score",
          data=depression_total_merged1,
          type="percent",
          layout=c(1,2))      #  columns and rows of individual plots
```

```{r echo=FALSE}
wilcox.test(depression_total_merged$depression_total_no_refused ~ depression_total_merged$study)

t.test(depression_total_merged$depression_total_no_refused ~ depression_total_merged$study)
```
Depression score comparison
```{r echo=FALSE}
boxplot(depression_total_merged$depression_total_no_refused ~ depression_total_merged$study, col="#69b3a2" , ylab="Total Depression Score", xlab = "Study")
```
### 5. Housing[docs](housing.html)