vcovCR: Clustered Robust Covariance Matrix Estimation

In bucky: Bucky's Archive for Data Analysis in the Social Sciences

Clustered Robust Covariance Matrix Estimation

Description

Robust estimation of the covariance matrix of the coefficient estimates in regression models with clustering.

Usage

vcovCR(x, cluster = NULL, type = c("CR", "CR0", "CR1"))

Arguments

x	A fitted model object.
cluster	A variable or expression giving the cluster for each observation.
type	A character string specifying the estimation type. For details see below.

Details

The default type of "CR" uses the same adjustment as 'Stata'. The values of "CR0" and "CR1" are analogous to "HC0" and "HC1", respectively, in vcovHC.

Value

A matrix containing the covariance matrix estimate with attribute type giving the type option used in estimating it.

See Also

See Also robust.summary and vcovHC.

Examples

clotting <- data.frame(
    cl = rep(1:2,each=9),
    u = c(5,10,15,20,30,40,60,80,100),
    lot = c(118,58,42,35,27,25,21,19,18,
            69,35,26,21,18,16,13,12,12))
clot.model <- glm(lot ~ log(u), data = clotting, family = Gamma)
vcovCR(clot.model, cluster=cl)

data(swiss)
model1 <- lm(Fertility ~ ., data = swiss)
## These should give the same answer
vcovCR(model1, cluster=1:nobs(model1), type="CR0")
sandwich::vcovHC(model1, type="HC0")

bucky documentation built on March 26, 2022, 1:12 a.m.