----- Original Message -----
From: Scott Cunningham <[email protected]>
Date: Tuesday, July 25, 2006 3:46 pm
Subject: Re: st: linear interpolation
To: [email protected]
> On Jul 25, 2006, at 4:26 PM, [email protected] wrote:
>
> > Perhaps -tsfill- would help?
>
> Scott,
>
> I think -tsfill- must be right. The problem I'm having is that
> the
> panel I'm creating has, as an indicator variable, four variables:
>
> state name, age cohort indicator, race and sex. So, for instance,
>
> when I reshape the data, I use a nested reshape like this:
>
> . reshape wide ir, i(fip age race sex) j(year)
>
> But when I attempt to -tsset- the data, I can't seem to use the
> same
> kind of nesting. When I simply use -tsset-, I use this:
>
> . tsset fip year
> repeated time values within panel
> r(451);
>
> Do you have any thoughts on this?
>
If your panelvar is actually made up of four variables then you will
need to create a single variable for the groups formed by fips, age,
race, and sex.
For example:
egen id = groups(fip age race sex)
tsset id year
tsfill (or tsfill, full)
Scott
*
* 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/
