nalimilan · Jan 3, 2026 · Dec 29, 2025
diff --git a/data/survey/apiclus1.rda b/data/survey/apiclus1.rda
diff --git a/data/survey/apiclus2.rda b/data/survey/apiclus2.rda
diff --git a/data/survey/apipop.rda b/data/survey/apipop.rda
diff --git a/data/survey/apisrs.rda b/data/survey/apisrs.rda
diff --git a/data/survey/apistrat.rda b/data/survey/apistrat.rda
diff --git a/data/survey/crowd.rda b/data/survey/crowd.rda
diff --git a/data/survey/election.rda b/data/survey/election.rda
diff --git a/data/survey/fpc.rda b/data/survey/fpc.rda
diff --git a/data/survey/hospital.rda b/data/survey/hospital.rda
diff --git a/data/survey/mu284.rda b/data/survey/mu284.rda
diff --git a/data/survey/myco.rda b/data/survey/myco.rda
diff --git a/data/survey/nhanes.rda b/data/survey/nhanes.rda
diff --git a/data/survey/salamander.rda b/data/survey/salamander.rda
diff --git a/data/survey/scd.rda b/data/survey/scd.rda
diff --git a/data/survey/yrbs.rda b/data/survey/yrbs.rda
diff --git a/doc/datasets.csv b/doc/datasets.csv
@@ -684,6 +684,21 @@
 "sem","Klein","Klein's Data on the U. S. Economy",22,10
 "sem","Kmenta","Partly Artificial Data on the U. S. Economy",20,5
 "sem","Tests","Six Mental Tests",32,6
+"survey","apiclus1","Student performance in California schools, Cluster Sample of School Districts",183,39
+"survey","apiclus2","Student performance in California schools, Two-Stage Cluster Sample of Schools",126,40
+"survey","apipop","Student performance in California schools, Entire Population",6194,37
+"survey","apisrs","Student performance in California schools, Simple Random Sample",200,39
+"survey","apistrat","Student performance in California schools, Stratified Sample",200,39
+"survey","crowd","Household crowding",6,5
+"survey","election","US 2004 presidential election data at state or county level",4600,8
+"survey","fpc","Small survey example",8,6
+"survey","hospital","Sample of obstetric hospitals",15,6
+"survey","mu284","Two-stage sample from MU284",15,5
+"survey","myco","Association between leprosy and BCG vaccination",516,6
+"survey","nhanes","Cholesterol data from a US survey",8591,7
+"survey","salamander","Salamander mating data set from McCullagh and Nelder (1989)",360,4
+"survey","scd","Survival in cardiac arrest",6,4
+"survey","yrbs","One variable from the Youth Risk Behaviors Survey, 2015.",15624,4
 "survival","bladder","Bladder Cancer Recurrences",340,7
 "survival","cancer","NCCTG Lung Cancer Data",228,10
 "survival","cgd","Chronic Granulotomous Disease data",203,16

diff --git a/doc/packages.csv b/doc/packages.csv
@@ -31,5 +31,6 @@
 "rpart","Recursive Partitioning and Regression Trees"
 "sandwich","Robust Covariance Matrix Estimators"
 "sem","Structural Equation Models"
+"survey","Analysis of Complex Survey Samples"
 "survival","Survival Analysis"
 "vcd","Visualizing Categorical Data"
diff --git a/doc/survey/crowd.html b/doc/survey/crowd.html
@@ -0,0 +1,81 @@
+<!DOCTYPE html><html><head><title>R: Household crowding</title>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" />
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.15.3/dist/katex.min.css">
+<script type="text/javascript">
+const macros = { "\\R": "\\textsf{R}", "\\code": "\\texttt"};
+function processMathHTML() {
+    var l = document.getElementsByClassName('reqn');
+    for (let e of l) { katex.render(e.textContent, e, { throwOnError: false, macros }); }
+    return;
+}</script>
+<script defer src="https://cdn.jsdelivr.net/npm/katex@0.15.3/dist/katex.min.js"
+    onload="processMathHTML();"></script>
+<link rel="stylesheet" type="text/css" href="R.css" />
+</head><body><div class="container"><main>
+
+<table style="width: 100%;"><tr><td>crowd</td><td style="text-align: right;">R Documentation</td></tr></table>
+
+<h2>Household crowding</h2>
+
+<h3>Description</h3>
+
+<p>A tiny dataset from the VPLX manual.
+</p>
+
+
+<h3>Usage</h3>
+
+<pre><code class='language-R'>data(crowd)</code></pre>
+
+
+<h3>Format</h3>
+
+<p>A data frame with 6 observations on the following 5 variables.
+</p>
+
+<dl>
+<dt>rooms</dt><dd><p>Number of rooms in the house</p>
+</dd>
+<dt>person</dt><dd><p>Number of people in the household</p>
+</dd>
+<dt>weight</dt><dd><p>Sampling weight</p>
+</dd>
+<dt>cluster</dt><dd><p>Cluster number</p>
+</dd>
+<dt>stratum</dt><dd><p>Stratum number</p>
+</dd>
+</dl>
+
+
+
+<h3>Source</h3>
+
+<p>Manual for VPLX, Census Bureau.
+</p>
+
+
+<h3>Examples</h3>
+
+<pre><code class='language-R'>data(crowd)
+
+## Example 1-1
+i1.1&lt;-as.svrepdesign(svydesign(id=~cluster, weight=~weight,data=crowd))
+i1.1&lt;-update(i1.1, room.ratio=rooms/person,
+overcrowded=factor(person&gt;rooms))
+svymean(~rooms+person+room.ratio,i1.1)
+svytotal(~rooms+person+room.ratio,i1.1)
+svymean(~rooms+person+room.ratio,subset(i1.1,overcrowded==TRUE))
+svytotal(~rooms+person+room.ratio,subset(i1.1,overcrowded==TRUE))
+
+## Example 1-2
+i1.2&lt;-as.svrepdesign(svydesign(id=~cluster,weight=~weight,strata=~stratum, data=crowd))
+svymean(~rooms+person,i1.2)
+svytotal(~rooms+person,i1.2)
+
+</code></pre>
+
+</main>
+
+</div>
+</body></html>
diff --git a/doc/survey/election.html b/doc/survey/election.html
@@ -0,0 +1,110 @@
+<!DOCTYPE html><html><head><title>R: US 2004 presidential election data at state or county level</title>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" />
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.15.3/dist/katex.min.css">
+<script type="text/javascript">
+const macros = { "\\R": "\\textsf{R}", "\\code": "\\texttt"};
+function processMathHTML() {
+    var l = document.getElementsByClassName('reqn');
+    for (let e of l) { katex.render(e.textContent, e, { throwOnError: false, macros }); }
+    return;
+}</script>
+<script defer src="https://cdn.jsdelivr.net/npm/katex@0.15.3/dist/katex.min.js"
+    onload="processMathHTML();"></script>
+<link rel="stylesheet" type="text/css" href="R.css" />
+</head><body><div class="container"><main>
+
+<table style="width: 100%;"><tr><td>election</td><td style="text-align: right;">R Documentation</td></tr></table>
+
+<h2>US 2004 presidential election data at state or county level</h2>
+
+<h3>Description</h3>
+
+<p>A sample of voting data from US states or counties (depending on data
+availability), sampled with probability proportional to number of votes. The sample was drawn using Tille's splitting method, implemented in the &quot;sampling&quot; package.
+</p>
+
+
+<h3>Usage</h3>
+
+<pre><code class='language-R'>data(election)</code></pre>
+
+
+<h3>Format</h3>
+
+<p><code>election</code> is a data frame with 4600 observations on the following 8 variables.
+</p>
+
+<dl>
+<dt><code>County</code></dt><dd><p>A factor specifying the state or country</p>
+</dd>
+<dt><code>TotPrecincts</code></dt><dd><p>Number of precincts in the state or county</p>
+</dd>
+<dt><code>PrecinctsReporting</code></dt><dd><p>Number of precincts supplying data</p>
+</dd>
+<dt><code>Bush</code></dt><dd><p>Votes for George W. Bush</p>
+</dd>
+<dt><code>Kerry</code></dt><dd><p>Votes for John Kerry</p>
+</dd>
+<dt><code>Nader</code></dt><dd><p>Votes for Ralph Nader</p>
+</dd>
+<dt><code>votes</code></dt><dd><p>Total votes for those three candidates</p>
+</dd>
+<dt><code>p</code></dt><dd><p>Sampling probability, proportional to <code>votes</code></p>
+</dd>
+</dl>
+
+<p><code>election_pps</code> is a sample of 40 counties or states taken with
+probability proportional to the number of votes. It includes the
+additional column <code>wt</code> with the sampling weights. 
+</p>
+<p><code>election_insample</code> indicates which rows of <code>election</code> were sampled.
+</p>
+<p><code>election_jointprob</code> are the pairwise sampling probabilities and
+<code>election_jointHR</code> are approximate pairwise sampling probabilities using
+the Hartley-Rao approximation.
+</p>
+
+
+<h3>Source</h3>
+
+<p>.
+</p>
+
+
+<h3>Examples</h3>
+
+<pre><code class='language-R'>data(election)
+## high positive correlation between totals
+plot(Bush~Kerry,data=election,log="xy")
+## high negative correlation between proportions
+plot(I(Bush/votes)~I(Kerry/votes), data=election)
+
+## Variances without replacement
+## Horvitz-Thompson type
+dpps_br&lt;- svydesign(id=~1,  fpc=~p, data=election_pps, pps="brewer")
+dpps_ov&lt;- svydesign(id=~1,  fpc=~p, data=election_pps, pps="overton")
+dpps_hr&lt;- svydesign(id=~1,  fpc=~p, data=election_pps, pps=HR(sum(election$p^2)/40))
+dpps_hr1&lt;- svydesign(id=~1, fpc=~p, data=election_pps, pps=HR())
+dpps_ht&lt;- svydesign(id=~1,  fpc=~p, data=election_pps, pps=ppsmat(election_jointprob))
+## Yates-Grundy type
+dpps_yg&lt;- svydesign(id=~1,  fpc=~p, data=election_pps, pps=ppsmat(election_jointprob),variance="YG")
+dpps_hryg&lt;- svydesign(id=~1,  fpc=~p, data=election_pps, pps=HR(sum(election$p^2)/40),variance="YG")
+
+## The with-replacement approximation
+dppswr &lt;-svydesign(id=~1, probs=~p, data=election_pps)
+
+svytotal(~Bush+Kerry+Nader, dpps_ht)
+svytotal(~Bush+Kerry+Nader, dpps_yg)
+svytotal(~Bush+Kerry+Nader, dpps_hr)
+svytotal(~Bush+Kerry+Nader, dpps_hryg)
+svytotal(~Bush+Kerry+Nader, dpps_hr1)
+svytotal(~Bush+Kerry+Nader, dpps_br)
+svytotal(~Bush+Kerry+Nader, dpps_ov)
+svytotal(~Bush+Kerry+Nader, dppswr)
+</code></pre>
+
+</main>
+
+</div>
+</body></html>
diff --git a/doc/survey/fpc.html b/doc/survey/fpc.html
@@ -0,0 +1,112 @@
+<!DOCTYPE html><html><head><title>R: Small survey example</title>
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" />
+<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.15.3/dist/katex.min.css">
+<script type="text/javascript">
+const macros = { "\\R": "\\textsf{R}", "\\code": "\\texttt"};
+function processMathHTML() {
+    var l = document.getElementsByClassName('reqn');
+    for (let e of l) { katex.render(e.textContent, e, { throwOnError: false, macros }); }
+    return;
+}</script>
+<script defer src="https://cdn.jsdelivr.net/npm/katex@0.15.3/dist/katex.min.js"
+    onload="processMathHTML();"></script>
+<link rel="stylesheet" type="text/css" href="R.css" />
+</head><body><div class="container"><main>
+
+<table style="width: 100%;"><tr><td>fpc</td><td style="text-align: right;">R Documentation</td></tr></table>
+
+<h2>Small survey example</h2>
+
+<h3>Description</h3>
+
+<p>The <code>fpc</code> data frame has 8 rows and 6 columns. It is artificial
+data to illustrate survey sampling estimators.
+</p>
+
+
+<h3>Usage</h3>
+
+<pre><code class='language-R'>data(fpc)</code></pre>
+
+
+<h3>Format</h3>
+
+<p>This data frame contains the following columns:
+</p>
+
+<dl>
+<dt>stratid</dt><dd><p>Stratum ids</p>
+</dd>
+<dt>psuid</dt><dd><p>Sampling unit ids</p>
+</dd>
+<dt>weight</dt><dd><p>Sampling weights</p>
+</dd>
+<dt>nh</dt><dd><p>number sampled per stratum</p>
+</dd>
+<dt>Nh</dt><dd><p>population size per stratum</p>
+</dd>
+<dt>x</dt><dd><p>data</p>
+</dd>
+</dl>
+
+
+
+<h3>Source</h3>
+
+<p><code style="white-space: pre;">&#8288;https://www.stata-press.com/data/r7/fpc.dta&#8288;</code>
+</p>
+
+
+<h3>Examples</h3>
+
+<pre><code class='language-R'>data(fpc)
+fpc
+
+
+withoutfpc&lt;-svydesign(weights=~weight, ids=~psuid, strata=~stratid, variables=~x, 
+   data=fpc, nest=TRUE)
+
+withoutfpc
+svymean(~x, withoutfpc)
+
+withfpc&lt;-svydesign(weights=~weight, ids=~psuid, strata=~stratid,
+fpc=~Nh, variables=~x, data=fpc, nest=TRUE)
+
+withfpc
+svymean(~x, withfpc)
+
+## Other equivalent forms 
+withfpc&lt;-svydesign(prob=~I(1/weight), ids=~psuid, strata=~stratid,
+fpc=~Nh, variables=~x, data=fpc, nest=TRUE)
+
+svymean(~x, withfpc)
+
+withfpc&lt;-svydesign(weights=~weight, ids=~psuid, strata=~stratid,
+fpc=~I(nh/Nh), variables=~x, data=fpc, nest=TRUE)
+
+svymean(~x, withfpc)
+
+withfpc&lt;-svydesign(weights=~weight, ids=~interaction(stratid,psuid),
+strata=~stratid, fpc=~I(nh/Nh), variables=~x, data=fpc)
+
+svymean(~x, withfpc)
+
+withfpc&lt;-svydesign(ids=~psuid, strata=~stratid, fpc=~Nh,
+ variables=~x,data=fpc,nest=TRUE)
+
+svymean(~x, withfpc)
+
+withfpc&lt;-svydesign(ids=~psuid, strata=~stratid,
+fpc=~I(nh/Nh), variables=~x, data=fpc, nest=TRUE)
+
+svymean(~x, withfpc)
+
+
+
+</code></pre>
+
+</main>
+
+</div>
+</body></html>