R Under development (unstable) (2024-03-07 r86063 ucrt) -- "Unsuffered Consequences" Copyright (C) 2024 The R Foundation for Statistical Computing Platform: x86_64-w64-mingw32/x64 R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type 'license()' or 'licence()' for distribution details. R is a collaborative project with many contributors. Type 'contributors()' for more information and 'citation()' on how to cite R or R packages in publications. Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R. > > ## lonely PSUs by design > library(survey) Loading required package: grid Loading required package: Matrix Loading required package: survival Attaching package: 'survey' The following object is masked from 'package:graphics': dotchart > data(api) > ## not certainty PSUs by fpc > ds<-svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = apiclus1) > summary(ds) Stratified Independent Sampling design (with replacement) svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = apiclus1) Probabilities: Min. 1st Qu. Median Mean 3rd Qu. Max. 0.02954 0.02954 0.02954 0.02954 0.02954 0.02954 Stratum Sizes: 61 135 178 197 255 406 413 437 448 510 568 637 716 778 815 obs 13 34 4 13 16 2 1 4 12 21 9 11 37 2 4 design.PSU 13 34 4 13 16 2 1 4 12 21 9 11 37 2 4 actual.PSU 13 34 4 13 16 2 1 4 12 21 9 11 37 2 4 Data variables: [1] "cds" "stype" "name" "sname" "snum" "dname" [7] "dnum" "cname" "cnum" "flag" "pcttest" "api00" [13] "api99" "target" "growth" "sch.wide" "comp.imp" "both" [19] "awards" "meals" "ell" "yr.rnd" "mobility" "acs.k3" [25] "acs.46" "acs.core" "pct.resp" "not.hsg" "hsg" "some.col" [31] "col.grad" "grad.sch" "avg.ed" "full" "emer" "enroll" [37] "api.stu" "fpc" "pw" > > options(survey.lonely.psu="fail") > try(svymean(~api00,ds)) Error in onestrat(`attr<-`(x[index, , drop = FALSE], "recentering", recentering), : Stratum (413) has only one PSU at stage 1 > try(svymean(~api00, as.svrepdesign(ds))) Error in jknweights(design$strata[, 1], design$cluster[, 1], fpc = fpc, : Stratum413has only one PSU > options(survey.lonely.psu="remove") > svymean(~api00,ds) mean SE api00 644.17 5.8058 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.8058 > options(survey.lonely.psu="certainty") > svymean(~api00,ds) mean SE api00 644.17 5.8058 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.8058 > options(survey.lonely.psu="adjust") > svymean(~api00,ds) mean SE api00 644.17 5.8281 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.8267 > options(survey.lonely.psu="average") > svymean(~api00,ds) mean SE api00 644.17 6.0096 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.8217 > > ## fpc specified > fpc<-ifelse(apiclus1$dnum==413, 1,1000) > ds<-svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = apiclus1,fpc=fpc) > summary(ds) Stratified Independent Sampling design svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = apiclus1, fpc = fpc) Probabilities: Min. 1st Qu. Median Mean 3rd Qu. Max. 0.02954 0.02954 0.02954 0.02954 0.02954 0.02954 Stratum Sizes: 61 135 178 197 255 406 413 437 448 510 568 637 716 778 815 obs 13 34 4 13 16 2 1 4 12 21 9 11 37 2 4 design.PSU 13 34 4 13 16 2 1 4 12 21 9 11 37 2 4 actual.PSU 13 34 4 13 16 2 1 4 12 21 9 11 37 2 4 Population stratum sizes (PSUs): 135 178 197 255 406 413 437 448 510 568 61 637 716 778 815 1000 1000 1000 1000 1000 1 1000 1000 1000 1000 1000 1000 1000 1000 1000 Data variables: [1] "cds" "stype" "name" "sname" "snum" "dname" [7] "dnum" "cname" "cnum" "flag" "pcttest" "api00" [13] "api99" "target" "growth" "sch.wide" "comp.imp" "both" [19] "awards" "meals" "ell" "yr.rnd" "mobility" "acs.k3" [25] "acs.46" "acs.core" "pct.resp" "not.hsg" "hsg" "some.col" [31] "col.grad" "grad.sch" "avg.ed" "full" "emer" "enroll" [37] "api.stu" "fpc" "pw" > > options(survey.lonely.psu="fail") > try(svymean(~api00,ds)) mean SE api00 644.17 5.7344 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.7344 > options(survey.lonely.psu="remove") > svymean(~api00,ds) mean SE api00 644.17 5.7344 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.7344 > options(survey.lonely.psu="certainty") > svymean(~api00,ds) mean SE api00 644.17 5.7344 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.7344 > options(survey.lonely.psu="adjust") > svymean(~api00,ds) mean SE api00 644.17 5.7344 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.7344 > options(survey.lonely.psu="average") > svymean(~api00,ds) mean SE api00 644.17 5.7344 > svymean(~api00, as.svrepdesign(ds)) mean SE api00 644.17 5.7501 > > rs<-as.svrepdesign(ds) > svytotal(~api00,rs) total SE api00 3989986 35616 > SE(svytotal(~api00,subset(rs, dnum==413)))==0 [1] TRUE > > ## lonely PSUs after subsetting > ds<-svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = subset(apiclus1,dnum !=413)) > ds1<-ds[-31,] > summary(ds1) Stratified Independent Sampling design (with replacement) svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = subset(apiclus1, dnum != 413)) Probabilities: Min. 1st Qu. Median Mean 3rd Qu. Max. 0.02954 0.02954 0.02954 0.02954 0.02954 0.02954 Stratum Sizes: 61 135 178 197 255 406 437 448 510 568 637 716 778 815 obs 13 34 4 13 16 1 4 12 21 9 11 37 2 4 design.PSU 13 34 4 13 16 2 4 12 21 9 11 37 2 4 actual.PSU 13 34 4 13 16 1 4 12 21 9 11 37 2 4 Data variables: [1] "cds" "stype" "name" "sname" "snum" "dname" [7] "dnum" "cname" "cnum" "flag" "pcttest" "api00" [13] "api99" "target" "growth" "sch.wide" "comp.imp" "both" [19] "awards" "meals" "ell" "yr.rnd" "mobility" "acs.k3" [25] "acs.46" "acs.core" "pct.resp" "not.hsg" "hsg" "some.col" [31] "col.grad" "grad.sch" "avg.ed" "full" "emer" "enroll" [37] "api.stu" "fpc" "pw" > > options(survey.lonely.psu="fail") > svymean(~api00,ds1) mean SE api00 645.14 5.8909 > options(survey.lonely.psu="remove") > svymean(~api00,ds1) mean SE api00 645.14 5.8909 > options(survey.lonely.psu="certainty") > svymean(~api00,ds1) mean SE api00 645.14 5.8909 > options(survey.lonely.psu="adjust") > svymean(~api00,ds1) mean SE api00 645.14 5.8909 > options(survey.lonely.psu="average") > svymean(~api00,ds1) mean SE api00 645.14 5.8909 > > ## with adjustment > options(survey.adjust.domain.lonely=TRUE) > ds<-svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = subset(apiclus1,dnum !=413)) > ds1<-ds[-31,] > summary(ds1) Stratified Independent Sampling design (with replacement) svydesign(id = ~1, weights = ~pw, strata = ~dnum, data = subset(apiclus1, dnum != 413)) Probabilities: Min. 1st Qu. Median Mean 3rd Qu. Max. 0.02954 0.02954 0.02954 0.02954 0.02954 0.02954 Stratum Sizes: 61 135 178 197 255 406 437 448 510 568 637 716 778 815 obs 13 34 4 13 16 1 4 12 21 9 11 37 2 4 design.PSU 13 34 4 13 16 2 4 12 21 9 11 37 2 4 actual.PSU 13 34 4 13 16 1 4 12 21 9 11 37 2 4 Data variables: [1] "cds" "stype" "name" "sname" "snum" "dname" [7] "dnum" "cname" "cnum" "flag" "pcttest" "api00" [13] "api99" "target" "growth" "sch.wide" "comp.imp" "both" [19] "awards" "meals" "ell" "yr.rnd" "mobility" "acs.k3" [25] "acs.46" "acs.core" "pct.resp" "not.hsg" "hsg" "some.col" [31] "col.grad" "grad.sch" "avg.ed" "full" "emer" "enroll" [37] "api.stu" "fpc" "pw" > > options(survey.lonely.psu="fail") > try(svymean(~api00,ds1)) mean SE api00 645.14 5.8909 Warning message: In onestrat(`attr<-`(x[index, , drop = FALSE], "recentering", recentering), : Stratum (406) has only one PSU at stage 1 > options(survey.lonely.psu="remove") > svymean(~api00,ds1) mean SE api00 645.14 5.8909 Warning message: In onestrat(`attr<-`(x[index, , drop = FALSE], "recentering", recentering), : Stratum (406) has only one PSU at stage 1 > options(survey.lonely.psu="certainty") > svymean(~api00,ds1) mean SE api00 645.14 5.8909 Warning message: In onestrat(`attr<-`(x[index, , drop = FALSE], "recentering", recentering), : Stratum (406) has only one PSU at stage 1 > options(survey.lonely.psu="adjust") > svymean(~api00,ds1) mean SE api00 645.14 5.9119 Warning message: In onestrat(`attr<-`(x[index, , drop = FALSE], "recentering", recentering), : Stratum (406) has only one PSU at stage 1 > options(survey.lonely.psu="average") > svymean(~api00,ds1) mean SE api00 645.14 6.0914 Warning message: In onestrat(`attr<-`(x[index, , drop = FALSE], "recentering", recentering), : Stratum (406) has only one PSU at stage 1 > > ## checks for `svytotal()` > > df_w_singleton <- data.frame( + Stratum = c(1, 1, 2, 2, 3), + PSU = c(1, 2, 3, 4, 5), + Design_Weight = c(10.5, 10.5, 20, 20, 15), + Sex = c("M", "F", "F", "M", "M"), + Age = c(30.5, 40.5, 35, 52, 44), + Height = c(6.2, 5.0, 5.3, 5.7, 5.5) + ) > > design_w_singleton <- survey::svydesign( + data = df_w_singleton, + ids = ~ PSU, strata = ~ Stratum, + weights = ~ Design_Weight + ) > > options("survey.lonely.psu" = "remove") > > stopifnot(all.equal( + target = 126625, + current = as.numeric( + vcov(svytotal(x = ~ Age, design = design_w_singleton)) + ) + )) > > options("survey.lonely.psu" = "certainty") > > stopifnot(all.equal( + target = 126625, + current = as.numeric( + vcov(svytotal(x = ~ Age, design = design_w_singleton)) + ) + )) > > options("survey.lonely.psu" = "adjust") > > stopifnot(all.equal( + target = 127579.8, + current = as.numeric( + vcov(svytotal(x = ~ Age, design = design_w_singleton)) + ), + scale = 127579.8, tolerance = 0.000001 + )) > > proc.time() user system elapsed 1.25 0.15 1.40