[R] function for linear regression with White std. errors

Thomas Lumley tlumley at u.washington.edu
Fri Apr 28 16:16:12 CEST 2006


On Thu, 27 Apr 2006, Brian Quinif wrote:

> John,
>
> Thanks for the suggestion, but tomorrow I am teaching a little seminar
> for my department trying to convince people about how wonderful R is.
> These people are all Stata users, and they really like the idea that
> they only have to type ", robust" to get het. consistent std. errors.
>

This really is a unique feature of Stata.  It's not hard to add the 
standard errors to glm(), but it is harder to make other functions such as 
predict() use them properly.

The survey package gives these standard errors by default, but that might 
also be regarded as too much work.

 	-thomas

Thomas Lumley			Assoc. Professor, Biostatistics
tlumley at u.washington.edu	University of Washington, Seattle




More information about the R-help mailing list