Zelig does not appear to be doing anything when provided information on clusters. Am I doing something wrong? I really appreciate the ease with which this package generates predicted values for changes in a single variable--very useful for getting a sense of the substantive effect of one of my variables.
Here is a MWE:
library(Zelig)
data(bivariate)
summary(m_cluster <- zelig(formula=y1 ~ x1, data=bivariate, cluster="x4", "logit"))
summary(m_noCluster <- zelig(formula=y1 ~ x1, data=bivariate, "logit"))
It does not seem to matter if I make the cluster variable a factor, either:
summary(zelig(formula=y1 ~ x1, data=bivariate, cluster=as.factor(bivariate$x4), "logit"))
Thanks for any suggestions.
