update 4가지 표본추출방법

01_data/sampling_concept/index.qmd → 01_data/sampling_method/index.qmd

@@ -1,5 +1,5 @@
 ---
-title: "표본추출 개념 시각화"
+title: "대표적 표본추출 방법"
 author: "이광춘"
 date: today
 image: thumbnail.png
@@ -8,6 +8,7 @@ editor_options:
   chunk_output_type: console
 ---
 
+모집단에서 표본을 추출하는 대표적인 단순임의추출, 층화추출, 군집추출, 다단계추출 4가지 방법에 대한 개념을 시각적으로 확인해보자.
 
 # Shiny 앱
 
@@ -22,6 +23,8 @@ editor_options:
 library(shiny)
 library(openintro)
 data(COL)
+library(showtext)
+showtext_auto()
 
 # _____ Simple Random _____ #
 build_srs <- function(n, N) {
@@ -260,7 +263,40 @@ shinyApp(ui, server)
 
 
 ```{webr-r}
+library(dplyr)
 
+sampling_frame <- tibble(
+  ID = 1:1000,
+  나이 = sample(18:70, 1000, replace = TRUE),
+  소득 = sample(30000:100000, 1000, replace = TRUE),
+  지역 = sample(c("북부", "남부", "동부", "서부"), 1000, replace = TRUE),
+  군집 = sample(1:10, 1000, replace = TRUE)
+)
+
+### 1. 단순임의추출 (Simple Random Sampling)
+# 단순임의추출: 100개의 관측치 무작위 선택
+sample_n(sampling_frame, 100)
+
+### 2. 층화추출 (Stratified Sampling)
+# 층화추출: 각 지역별로 25개씩 추출 
+sampling_frame %>%
+  group_by(지역) %>%
+  sample_n(25) %>%
+  ungroup()
+
+### 3. 군집추출 (Cluster Sampling)  
+# 군집추출: 군집 3개 임의 추출 후 모든 관측치 선택
+clusters <- sample(unique(sampling_frame$군집), 3)
+sampling_frame %>%
+  filter(군집 %in% clusters)
+
+### 4. 다단계추출 (Multistage Sampling)
+# 다단계추출: 먼저 군집을 선택하고, 각 군집에서 무작위로 10개씩 추출
+sampling_frame %>%
+  filter(군집 %in% clusters) %>%
+  group_by(군집) %>%  
+  sample_n(10) %>%
+  ungroup()
 ```
 
 

docs/01_data.html

@@ -202,6 +202,10 @@
   <li class="nav-item">
     <a class="nav-link" href="./about.html"> 
 <span class="menu-text">소개</span></a>
+  </li>  
+  <li class="nav-item">
+    <a class="nav-link" href="./BitStat.html"> 
+<span class="menu-text">BitStat</span></a>
   </li>  
   <li class="nav-item compact">
     <a class="nav-link" href="https://github.com/bit2r/BitStat2"> <i class="bi bi-github" role="img">
@@ -335,7 +339,7 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="1" data-categories="확률분포,이산형 분포,베르누이 분포,이항 분포,포아송 분포" data-listing-date-sort="1715439600000" data-listing-file-modified-sort="1715482966694" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7" data-listing-word-count-sort="1323">
+<div class="g-col-1" data-index="1" data-categories="확률분포,이산형 분포,베르누이 분포,이항 분포,포아송 분포" data-listing-date-sort="1715526000000" data-listing-file-modified-sort="1715482966694" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="7" data-listing-word-count-sort="1323">
 <a href="./01_data/dist_discrete/index.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top">
@@ -370,14 +374,14 @@ <h5 class="no-anchor card-title listing-title">
 이광춘
 </div>
 <div class="listing-date">
-2024-05-12
+2024-05-13
 </div>
 </div>
 </div>
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="2" data-categories="news" data-listing-date-sort="1715439600000" data-listing-file-modified-sort="1715478734144" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="11" data-listing-word-count-sort="2189">
+<div class="g-col-1" data-index="2" data-categories="news" data-listing-date-sort="1715526000000" data-listing-file-modified-sort="1715478734144" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="11" data-listing-word-count-sort="2189">
 <a href="./01_data/dist_fitting/index.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top">
@@ -400,22 +404,22 @@ <h5 class="no-anchor card-title listing-title">
 이광춘
 </div>
 <div class="listing-date">
-2024-05-12
+2024-05-13
 </div>
 </div>
 </div>
 </div>
 </a>
 </div>
-<div class="g-col-1" data-index="3" data-categories="표본,표본추출,단순임의추출,층화추출,군집추출,다단계추출,시각화" data-listing-date-sort="1715439600000" data-listing-file-modified-sort="1715484185419" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="10" data-listing-word-count-sort="1876">
-<a href="./01_data/sampling_concept/index.html" class="quarto-grid-link">
+<div class="g-col-1" data-index="3" data-categories="표본,표본추출,단순임의추출,층화추출,군집추출,다단계추출,시각화" data-listing-date-sort="1715526000000" data-listing-file-modified-sort="1715592790127" data-listing-date-modified-sort="NaN" data-listing-reading-time-sort="11" data-listing-word-count-sort="2012">
+<a href="./01_data/sampling_method/index.html" class="quarto-grid-link">
 <div class="quarto-grid-item card h-100 card-left">
 <p class="card-img-top">
-<img src="./01_data/sampling_concept/thumbnail.png" class="thumbnail-image card-img" style="height: 150px;">
+<img src="./01_data/sampling_method/thumbnail.png" class="thumbnail-image card-img" style="height: 150px;">
 </p>
 <div class="card-body post-contents">
 <h5 class="no-anchor card-title listing-title">
-표본추출 개념 시각화
+대표적 표본추출 방법
 </h5>
 <div class="listing-categories">
 <div class="listing-category" onclick="window.quartoListingCategory('표본'); return false;">
@@ -441,22 +445,14 @@ <h5 class="no-anchor card-title listing-title">
 </div>
 </div>
 <div class="card-text listing-description">
-
-
-  // Configure the Monaco Editor's loader
-  require.config({
-    paths: {
-      'vs': 'https://cdn.jsdelivr.net/npm/monaco-editor@0.47.0/min/vs'
-    }
-  });
-
+모집단에서 표본을 추출하는 대표적인 단순임의추출, 층화추출, 군집추출, 다단계추출 4가지 방법에 대한 개념을 시각적으로 확인해보자.
 </div>
 <div class="card-attribution card-text-small justify">
 <div class="listing-author">
 이광춘
 </div>
 <div class="listing-date">
-2024-05-12
+2024-05-13
 </div>
 </div>
 </div>