Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: Again-Unique Case ID in Large Panel


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Again-Unique Case ID in Large Panel
Date   Wed, 4 Aug 2004 18:48:35 +0100

I got it, I think. You need to play
around with the -width()- option in 
-xtdes-. I surmise that the default
is not big enough for your data. 

(I was predisposed to think the blame
would lie with -xtdes-.) 

Nick 
n.j.cox@durham.ac.uk 

Stephen V. Burks
 
> Hi, Suzy.
> 
> OK, if you are correct then both version of -duplicates- 
> agree that I have no
> duplicates. But, this means they both still disagree with 
> -xtdes-, right?
> 
> My original starting point was that -xtdes- says I do not have unique 
> identifcation,
> but other approaches (now including both versions of 
> -duplicates-) say that 
> this
> is incorrect, and I should (do) have unique identification.
> 
> Is there another misinterpretation on my part buried somewhere here?
> 
> Thanks,
> Steve
> 
> P.S. just got Nick's post which seems to agree with me, once 
> I accept Suzy's
> interpretation on -duplicates-.
> 
> At 12:24 PM 8/4/2004, you wrote:
> >I believe that your output is saying that you have one copy 
> of  1322511 
> >with no surpluses (no duplicates). I just ran this yesterday 
> with my much 
> >smaller dataset and was able to verify this.
> >Suzy
> >
> >Stephen V. Burks wrote:
> >
> >>Hi, Folks.
> >>
> >>Now I wonder if I am reporting a bug.  As per Nick's suggestion
> >>(thanks, Nick) I looked up -duplicates- and ran it.
> >>
> >>Results:
> >>(1) using -duplicates report-
> >>
> >>. duplicates report  DRVNUM  CDATE
> >>
> >>Duplicates in terms of DRVNUM CDATE
> >>--------------------------------------
> >>    copies | observations       surplus
> >>----------+---------------------------
> >>         1 |      1322511             0
> >>--------------------------------------
> >>
> >>(2) using -duplicates list-
> >>
> >>. duplicates list  DRVNUM  CDATE
> >>Duplicates in terms of DRVNUM CDATE
> >>(0 observations are duplicates)
> >>
> >>
> >>If I read this correctly, one version of -duplicates- says I have
> >>a single duplicate (the last case in the file), while the other
> >>says I have none. Also, -xtdes- still says that DRVNUM and
> >>CDATE do not uniquely identify cases.
> >>
> >>I looked in the data browser, and the last case is NOT a duplicate.
> >>While DRVNUM is the same as the case before, CDATE is not.
> >>
> >>If my interpretation of the output is correct then my best guess is
> >>that -xtdes- is wrong to say I do not have unique identification,
> >>and whatever bug causes this might also be behind the apparently
> >>incorrect response from -duplicates report-.  In any event, it seems
> >>to be a problem that -duplicates list- and -xtdes- do not agree.
> >>
> >>Any better ideas?
> >>
> >>Thanks,
> >>Steve
> >>
> >>P.S. My version of Stata is 8.2 for WinXP, with current updates.
> >>

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index