[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: RE: RE: RE: RE: could not predict rstudent
Really appreciate your response to my question. You are absolute right at
suggesting me reading Statlist FAQ before posting messages. I also change
Microsoft settings and hope the winmail.dat problem is fixed.
I checked again following your suggestion.I found out that I was using
'regress Y x1, cluster(ID)'. The option of cluster gives me the trouble.
Thanks again for your help. This is my first time using "set trace on"; and
it is quite useful.
[mailto:email@example.com]On Behalf Of Nick Cox
Sent: Sunday, May 22, 2005 4:58 PM
Subject: st: RE: RE: RE: could not predict rstudent
The rule about winmail.dat files is explained
in the Statalist FAQ, which all, novices or
not, should read carefully before posting to
Statalist. A Google on winmail.dat will
It is possible, although unlikely, that
your predict.ado file is corrupt.
You need to do something like this:
. use auto
. set trace on
. regress mpg weight
. predict rs, rstudent
and see where the error message you get
Alice (Libo) Sun
> Thanks for the quick response. I am a novice here.
> Yes, I am using -regress- command. Could that be something
> wrong with predict ado file in my computer?
> " Incidentally, please don't send your winmail.dat
> file to Statalist. "
> What do you mean? Should not I send email to the Statlist?
> I can't reproduce this. With Stata 7 and the auto
> data I can go
> regress mpg weight
> predict rs, rstudent
> Are you using -regress-?
> Incidentally, please don't send your winmail.dat
> file to Statalist.
> Alice(Libo) Sun
> > I am using stata 7.0. Stata returns error message
> "rstudent invalid" when I type "predict rstud, rstudent"
> after regression.
> > Any hint on how to fix it?
> > I checked my ado files update status. All updated to 05 Dec 2002.
* For searches and help try: