robcov_alt: Robust covariance matrix based upon the 'sandwich'-package

In Greg: Regression Helper Functions

Robust covariance matrix based upon the 'sandwich'-package

Description

This is an alternative to the 'rms'-package robust covariance matrix that uses the 'sandwich' package vcovHC() function instead of the 'rms'-built-in estimator. The advantage being that many more estimation types are available.

Usage

robcov_alt(fit, type = "HC3", ...)

Arguments

fit	The ols fit that
type	a character string specifying the estimation type. See vcovHC() for options.
...	You should specify type= followed by some of the alternative available for the vcovHC() function.

Value

model The fitted model with adjusted variance and df.residual set to NULL

Examples

# Generate some data
n <- 500
x1 <- runif(n) * 2
x2 <- runif(n)
y <- x1^3 + x2 + rnorm(n)

library(rms)
library(sandwich)
dd <- datadist(x1, x2, y)
org.op <- options(datadist = "dd")

# Main function
f <- ols(y ~ rcs(x1, 3) + x2)

# Check the bread
bread(f)
# Check the HC-matrix
vcovHC(f, type = "HC4m")
# Adjust the model so that it uses the HC4m variance
f_rob <- robcov_alt(f, type = "HC4m")
# Get the new HC4m-matrix
# - this function just returns the f_rob$var matrix
vcov(f_rob)
# Now check the confidence interval for the function
confint(f_rob)

options(org.op)

Greg documentation built on Nov. 16, 2022, 5:06 p.m.