Alfred
your problem is somewhat different from the provided resources, but I
think the user written command -tsspell- could also be of some help
for you. For my solution you will need it. So you should install it
from ssc by typing -ssc install tsspell- in your Stata command window.
This is my solution (assuming you panel var is named "id" and you time
var is named "year" and the three variables of interest are named
var1, var2, var3):
tsset id year
tsspell , cond(!(missing(var1) | missing(var2) | missing(var3)) ///
& (D.year==1 | _n==1))
bys id: egen maxrun = max(_seq)
// Next: returning number of panels fulfilling the condition to have five
// consecutive observations with no missing data in any of
// the three variables (var1, var2, var3)
quiet tab id if maxrun==5
ret list
I hope this works for you.
Sebastian
2007/10/20, Alfred Blair <[email protected]>:
> Dear Marteen, thank you for your suggestion, but it seems it doesn't help me. The link provides useful tricks, but my problem is quite different. I mean: starting from a large but incomplete database (three variables, from 1980 to 1998), I simply need to restrict my analysis to individuals (my units) that have
> no missing data (on my three variables) for at least five
> consecutive years. Until now I haven't found how to get this selection in Stata, and I still hope that you or someone else will help me (an example with a basic dataset would be a big hand).
> Thanks.
>
> Alfred
>
>
>
>
> ----- Original Message ----
>
> From: Maarten buis <[email protected]>
>
> To: [email protected]
>
> Sent: Saturday, 20 October, 2007 8:52:37 PM
>
> Subject: Re: st: consecutive observation - incomplete panel data (help)
>
>
>
> --- Alfred Blair <[email protected]> wrote:
>
> > I have an incomplete (/unbalanced) panel of 2078 units (individuals)
>
> > and three variables, from 1980 to 1998. In order to retrieve
>
> > asymptotically efficient tests for a GMM, my research requires to
>
> > keep only individuals that have a minimum of 5 consecutive annual
>
> > observations for all variables together. What's the Stata code
>
> > necessary to identify and select units according to this criterion?
>
>
>
> You can find a lot of useful tricks in:
>
> http://www.stata.com/statalist/archive/2007-07/msg00602.html
>
>
>
> and in the Stata Journal article it refers to.
>
>
>
> Hope this helps,
>
> Maarten
>
>
>
> -----------------------------------------
>
> Maarten L. Buis
>
> Department of Social Research Methodology
>
> Vrije Universiteit Amsterdam
>
> Boelelaan 1081
>
> 1081 HV Amsterdam
>
> The Netherlands
>
>
>
> visiting address:
>
> Buitenveldertselaan 3 (Metropolitan), room Z434
>
>
>
> +31 20 5986715
>
>
>
> http://home.fsw.vu.nl/m.buis/
>
> -----------------------------------------
>
>
>
>
>
>
>
> ___________________________________________________________
> Yahoo! Answers - Got a question? Someone out there knows the answer. Try it
> now.
> http://uk.answers.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/
