The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

GEE cluster standard errors and predictions for glm objects

Klaus Holst & Thomas Scheike

2024-02-16

Utility functions for GLM objects

Getting the OR with confidence intervals using the GEE (sandwhich) standard errors

set.seed(100)

library(mets)
data(bmt); 
bmt$id <- sample(1:100,408,replace=TRUE)

glm1 <- glm(tcell~platelet+age,bmt,family=binomial)
summaryGLM(glm1)
#> $coef
#>             Estimate Std.Err    2.5%   97.5%   P-value
#> (Intercept)  -2.4371  0.2225 -2.8732 -2.0009 6.481e-28
#> platelet      1.1368  0.3076  0.5340  1.7397 2.189e-04
#> age           0.5927  0.1551  0.2888  0.8966 1.319e-04
#> 
#> $or
#>               Estimate       2.5%     97.5%
#> (Intercept) 0.08741654 0.05651794 0.1352076
#> platelet    3.11688928 1.70573194 5.6955015
#> age         1.80895115 1.33489115 2.4513641
#> 
#> $fout
#> NULL

## GEE robust standard errors
summaryGLM(glm1,id=bmt$id)
#> $coef
#>             Estimate Std.Err    2.5%   97.5%   P-value
#> (Intercept)  -2.4371  0.2157 -2.8599 -2.0142 1.361e-29
#> platelet      1.1368  0.2830  0.5822  1.6914 5.877e-05
#> age           0.5927  0.1434  0.3117  0.8738 3.568e-05
#> 
#> $or
#>               Estimate       2.5%     97.5%
#> (Intercept) 0.08741654 0.05727471 0.1334211
#> platelet    3.11688928 1.79006045 5.4271903
#> age         1.80895115 1.36575550 2.3959664
#> 
#> $fout
#> NULL

Predictions also simple

age <- seq(-2,2,by=0.1)
nd <- data.frame(platelet=0,age=seq(-2,2,by=0.1))
pnd <- predictGLM(glm1,nd)
head(pnd$pred)
#>      Estimate       2.5%      97.5%
#> p1 0.02601899 0.01115243 0.05951051
#> p2 0.02756409 0.01214068 0.06136414
#> p3 0.02919819 0.01321187 0.06328733
#> p4 0.03092608 0.01437206 0.06528441
#> p5 0.03275278 0.01562757 0.06736019
#> p6 0.03468351 0.01698493 0.06952008
plot(age,pnd$pred[,1],type="l",ylab="predictions",xlab="age",ylim=c(0,0.3))
matlines(age,pnd$pred[,-1],col=2)

SessionInfo

sessionInfo()
#> R version 4.3.2 (2023-10-31)
#> Platform: aarch64-apple-darwin22.6.0 (64-bit)
#> Running under: macOS Sonoma 14.3.1
#> 
#> Matrix products: default
#> BLAS:   /Users/kkzh/.asdf/installs/R/4.3.2/lib/R/lib/libRblas.dylib 
#> LAPACK: /Users/kkzh/.asdf/installs/R/4.3.2/lib/R/lib/libRlapack.dylib;  LAPACK version 3.11.0
#> 
#> locale:
#> [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#> 
#> time zone: Europe/Copenhagen
#> tzcode source: internal
#> 
#> attached base packages:
#> [1] stats     graphics  grDevices utils     datasets  methods   base     
#> 
#> other attached packages:
#> [1] mets_1.3.4     timereg_2.0.5  survival_3.5-7
#> 
#> loaded via a namespace (and not attached):
#>  [1] cli_3.6.2           knitr_1.45          rlang_1.1.3        
#>  [4] xfun_0.41           highr_0.10          jsonlite_1.8.8     
#>  [7] listenv_0.9.1       future.apply_1.11.1 lava_1.7.4         
#> [10] htmltools_0.5.6.1   sass_0.4.7          rmarkdown_2.25     
#> [13] grid_4.3.2          evaluate_0.23       jquerylib_0.1.4    
#> [16] fastmap_1.1.1       mvtnorm_1.2-4       yaml_2.3.7         
#> [19] numDeriv_2016.8-1.1 compiler_4.3.2      codetools_0.2-19   
#> [22] ucminf_1.2.0        Rcpp_1.0.12         future_1.33.1      
#> [25] lattice_0.22-5      digest_0.6.34       R6_2.5.1           
#> [28] parallelly_1.37.0   parallel_4.3.2      splines_4.3.2      
#> [31] bslib_0.5.1         Matrix_1.6-5        tools_4.3.2        
#> [34] globals_0.16.2      cachem_1.0.8

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.