R Graphical Manual

Browse All

Last data update: 2014.03.03

R: Pairs Cluster Bootstrapped p-Values For GLM

cluster.bs.glm

R Documentation

Pairs Cluster Bootstrapped p-Values For GLM

Description

This software estimates p-values using pairs cluster bootstrapped t-statistics for GLM models (Cameron, Gelbach, and Miller 2008). The data set is repeatedly re-sampled by cluster, a model is estimated, and inference is based on the sampling distribution of the pivotal (t) statistic.

Usage

cluster.bs.glm(mod, dat, cluster, ci.level = 0.95, boot.reps = 1000,
  stratify = FALSE, cluster.se = TRUE, report = TRUE, prog.bar = TRUE)

Arguments

`mod`	A model estimated using `glm`.
`dat`	The data set used to estimate `mod`.
`cluster`	A formula of the clustering variable.
`ci.level`	What confidence level should CIs reflect?
`boot.reps`	The number of bootstrap samples to draw.
`stratify`	Sample clusters only (= FALSE) or clusters and observations by cluster (= TRUE).
`cluster.se`	Use clustered standard errors (= TRUE) or ordinary SEs (= FALSE) for bootstrap replicates.
`report`	Should a table of results be printed to the console?
`prog.bar`	Show a progress bar of the bootstrap (= TRUE) or not (= FALSE).

Value

A list with the elements

`p.values`	A matrix of the estimated p-values.
`ci`	A matrix of confidence intervals.

Note

Code to estimate GLM clustered standard errors by Mahmood Arai: http://thetarzan.wordpress.com/2011/06/11/clustered-standard-errors-in-r/. Cluster SE degrees of freedom correction = (M/(M-1)) with M = the number of clusters.

Author(s)

Justin Esarey

References

Cameron, A. Colin, Jonah B. Gelbach, and Douglas L. Miller. 2008. "Bootstrap-Based Improvements for Inference with Clustered Errors." The Review of Economics and Statistics 90(3): 414-427. <DOI:10.1162/rest.90.3.414>.

Examples

## Not run: 

# example one: predict whether respondent has a university degree
require(effects)
data(WVS)
logit.model <- glm(degree ~ religion + gender + age, data=WVS, family=binomial(link="logit"))
summary(logit.model)

# compute pairs cluster bootstrapped p-values
clust.bs.p <- cluster.bs.glm(logit.model, WVS, ~ country, report = T)



# example two: predict chicken weight
rm(list=ls())
data(ChickWeight)

dum <- model.matrix(~ ChickWeight$Diet)
ChickWeight$Diet2 <- as.numeric(dum[,2])
ChickWeight$Diet3 <- as.numeric(dum[,3])
ChickWeight$Diet4 <- as.numeric(dum[,4])

weight.mod2 <- glm(formula = weight~Diet2+Diet3+Diet4+log(Time+1),data=ChickWeight)

# compute pairs cluster bootstrapped p-values
clust.bs.w <- cluster.bs.glm(weight.mod2, ChickWeight, ~ Chick, report = T)


## End(Not run)