Yes, I found the -dfbeta- command, which as far as I can tell works only
after -regress-. I also dug up -ldfbeta- which works after logit, but
none suited for surivial time data. However, following links in the
helpfiles you suggested I found that dfbetas can also be calculated
through -predict-, although only one variable at a time.
I'm puzzled as to why it doesn't say so in the helpfile for -predict- or
in the chapter concering predict after streg. I'm still using stata8
documentation though, it might be updated in the more recent manuals.
Thanks for your help.
-Steinar
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Ricardo
Ovaldia
Sent: 7. oktober 2005 14:44
To: [email protected]
Subject: Re: st: dfbeta for survival time data
--- Steinar Fossedal <[email protected]> wrote:
> Hello,
> I'm fitting a parametric survival time model and I'm
> trying to figure
> out if any of my observations have a unreasonable
> large effect on the
> estimates. I've been looking into the dfbeta
> commands, but cannot seem
> to find one for use with survival time data.
In Stata 9, according to the manual, the command
-dfbeta- should work. Type -help dfbeta- to see the
syntax.
Ricardo.
Ricardo Ovaldia, MS
Statistician
Oklahoma City, OK
__________________________________
Yahoo! Mail - PC Magazine Editors' Choice 2005
http://mail.yahoo.com
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
