selecting age focused sample

[andkov]

Here's the solution Ardo prepared for selecting those individuals who have a valid observation of gait between ages 68 and 72 (inclusive)

dta <- ds_valid %>% dplyr::select(-firstobs)
subjects <- unique(ds_valid$id) 

library(dplyr)
library(elect)
# dta <- ELECTData
# subjects <- unique(dta$id)
for(i in 1:length(subjects)){
  dta.i <- dta[dta$id==subjects[i],]
  if(nrow(dta.i)<=2){print(subjects[i])}
}

dta %>% glimpse()
# Subselect:
bound <- c(68,72)
count <- 0
for(i in 1:length(subjects)){
  select <- 0
  dta.i <- dta[dta$id==subjects[i],]
  if(dta.i$age[1]< bound[2]){
    ddta.i <- dta.i[dta.i$age>bound[1],]
    if(nrow(ddta.i)>1){
      select <- 1; print(i)
      select <- 1 ; print (i)
      firstobs <- rep(0, nrow(ddta.i))
      firstobs[1] <- 1
      ddta.i <- cbind(ddta.i, firstobs = firstobs)
    }
  }
  if(select==1 & count==0){
    ddta <- ddta.i
    count <- count +1
  }
  if(select==1 & count>0){
    ddta <- rbind(ddta,ddta.i)
    count <- count+1
  }
}

hist(ddta$age[ddta$firstobs == 1])

[andkov]

Here's reformulation of the same logic using dplyr phraseology

> ds <- ds_valid %>% 
+   dplyr::select(id, age, wave, firstobs, gait) %>% 
+   dplyr::filter( id %in% c("617643","709354","228190"))
> 
> ds %>% glimpse()
Observations: 22
Variables: 5
$ id       <int> 228190, 228190, 617643, 617643, 617643, 617643, 617643, 617643...
$ age      <dbl> 74, 74, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 78, 69, 70...
$ wave     <int> 0, 1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 13, 0, 1, 2, 3, 4, 5, ...
$ firstobs <dbl> 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
$ gait     <dbl> 0.57, NA, 0.87, 0.76, 0.94, 0.83, 0.80, 0.70, 0.92, 0.75, NA, ...
> ids_gait_70 <- ds %>% 
+   dplyr::filter( age > 67 & age <  73) %>%
+   dplyr::group_by(id) %>% 
+   dplyr::arrange(age) %>% 
+   dplyr::mutate(gait70 = dplyr::first(gait)) %>% 
+   dplyr::distinct(id, gait70)
> ids_gait_70 %>% glimpse()
Observations: 2
Variables: 2
$ id     <int> 617643, 709354
$ gait70 <dbl> 0.94, 1.08
> 
> d2 <- ds %>% 
+   dplyr::left_join(ids_gait_70, by = "id") %>% 
+   # keep only people who have a non-missing gait70
+   dplyr::filter(!is.na(gait70)) %>% 
+   dplyr::filter(age > 68 )
> 
> d2 %>% head(40)
       id age wave firstobs gait gait70
1  617643  68    3        0 0.83   0.94
2  617643  69    4        0 0.80   0.94
3  617643  70    5        0 0.70   0.94
4  617643  71    6        0 0.92   0.94
5  617643  72    7        0 0.75   0.94
6  617643  73    8        0   NA   0.94
7  617643  74    9        0 0.81   0.94
8  617643  75   10        0 0.70   0.94
9  617643  78   13        0   NA   0.94
10 709354  69    0        1 1.08   1.08
11 709354  70    1        0 0.96   1.08
12 709354  71    2        0 0.61   1.08
13 709354  72    3        0 0.44   1.08
14 709354  73    4        0 0.54   1.08
15 709354  75    5        0 0.69   1.08
16 709354  75    6        0 0.59   1.08
17 709354  76    7        0   NA   1.08
>