-ipolate- does linear interpolation, as its help
explains. What would seem to make most sense
with panel data is to interpolate with respect
to time. As -igrs- appears not to be your time variable,
your -ipolate- call might indeed produce results you
don't expect. You should probably use -year-
instead. Naturally, the explicit assumption here
is of linear segments between non-missing values.
-impute- uses a regression method, on which
see [R] impute.
Nick
n.j.cox@durham.ac.uk
soma ghosh
> I have a data set from 1977 to 1992 for every 5 yrs
> (77, 82, 87, 92) with some missing values for my
> dependent variables. For e.x. data on expenditure is
> missing for the year 1977 and there are also some
> missing values in the other years. I tried using both
> impute and ipolate command in stata to get values for
> 1977. I used
> sort id year
> by id: ipolate exp igrs, gen (iexp) epolate.
>
> But quite a few of the resulting values (about 30%)
> are negative & the ipolated values don't seem to be
> correct (way different from expenditures in other
> years). Can anybody help me to find a correct way to
> do this? Also, what is the mechanism behind ipolate or
> impute?
*
* 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/