[R] coeftest() R squared

[Achim Zeileis]

On Wed, 15 Feb 2017, T.Riedle wrote:

>
> Dear all,
> I want to run a regression using lm() with Newey West corrected standard errors.
>
> This is the code
>
> Reg<-lm(g~sent + liquidity + Cape, data=dataUsa)
> CoefNW<-coeftest(Reg, vcov.=NeweyWest)
> CoefNW
>
> In contrast to summary(Reg) the output of CoefNW neither returns the 
> adjusted R squared nor the F-statistic. How can I obtain the R squared 
> for coeftest? Alternatively, how do I get robust standard errors and the 
> R squared of the regression?

The adjusted analogue to the F statistic can be obtained by
waldtest(Reg, vcov = NeweyWest)

For the R-squared there is no appropriate quantity with analogous
properties. Hence nothing is provided in the package.

> Thanks for your help.
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>