[R] Extracting coefficients' standard errors from linear model

David Winsemius dwinsemius at comcast.net
Fri Apr 25 16:21:54 CEST 2008


Uli Kleinwechter <ulikleinwechter at yahoo.com.mx> wrote in
news:4811E2E9.3080603 at yahoo.com.mx: 

> Dear all,
> 
> Hope this question is not too trivial...
> 
> In order to correct standard errors from an estimation of a fixed 
> effects regression model y need to extract the vector of standard
> errors of the coefficients of a simple linear model estimated using
> 
> lm(var1~var2+var3+var4)
> 
> Unfortunately I can't find out the corresponding function.

See if vcov() suits. From the lm() help page an example:

> ctl <- c(4.17,5.58,5.18,6.11,4.50,4.61,5.17,4.53,5.33,5.14)
> trt <- c(4.81,4.17,4.41,3.59,5.87,3.83,6.03,4.89,4.32,4.69)
> group <- gl(2,10,20, labels=c("Ctl","Trt"))
> weight <- c(ctl, trt)
> lm.D9 <- lm(weight ~ group)

Then look at summary(lm.D9) and these results:

> vcov(lm.D9)[2,2]
[1] 0.09699167
> vcov(lm.D9)[2,2]^(1/2)
[1] 0.3114349

diag(vcov(lm.mdl))^(1/2) may be needed to get the vector you seek.

-- 
David Winsemius



More information about the R-help mailing list