Re: SEs from lm

["Thomas D. Fletcher" <tom.fletcher@cox.net>]

John,

 

Use the summary function for the coefficients to get the standard errors.

 

x <- rnorm(10)
y <- .5*x + rnorm(10)
fit1 <- lm (y ~ x)
summary(fit1)

 

summary(fit1)$coefficients[,2]

 

This should work.

HTH

Tom

*** ++++++++++++ ***
Thomas D. Fletcher
Department of Psychology
Old Dominion University
Office (757) 683 - 3725
tflet002@odu.edu
*** ++++++++++++ ***
 

-----Original Message-----
From: s-news-owner@lists.biostat.wustl.edu [mailto:s-news-owner@lists.biostat.wustl.edu]On Behalf Of John Sorkin
Sent: Friday, May 13, 2005 7:19 AM
To: s-news@lists.biostat.wustl.edu
Subject: [S] SEs from lm

SPlus 6.2 running under Windows 2000

Please forgive a basic question.

 

I are using lm, e.g. fit1<-lm(y~x). I would like to obtain the coefficients AND the SEs of the coefficient. I know I can get the coefficient using fit1$coefficients[1] and fit1$coefficients[2], but this does not give the SEs. Could some one tell me how and can get the SEs? Is there anyway to use a single statement to get the coefficients and SE?

Thanks

John

 

John Sorkin M.D., Ph.D.
Chief, Biostatistics and Informatics
Baltimore VA Medical Center GRECC and
University of Maryland School of Medicine Claude Pepper OAIC

 

University of Maryland School of Medicine
Division of Gerontology
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524

 

410-605-7119
NOTE NEW EMAIL ADDRESS:
jsorkin@grecc.umaryland.edu