Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: Impute an average in a stacked dataset


From   Nick Cox <n.j.cox@durham.ac.uk>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Impute an average in a stacked dataset
Date   Tue, 6 Sep 2011 15:06:05 +0100

I'd call this panel data. I think what you want is better called interpolation. 

You can do this with -ipolate-. 

I am not clear about your general rule here. Is that you want to fill in gaps of length 1 _only_? 

It sounds as if you want to cross-correlate within panels and also pool panels. You _could_ do something like this: 

. tsset case yr 
. gen x4 = L4.x 
. corr x x4 

But that's a difficult one to make inferences about given the structure. 

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

Huerta, Tim

I have a stacked dataset with missing data

Yr   case     x
2004  1                   3
2005  1                  3
2006  1       4
2007  1       6
2004  2       4
2006  2       5
2007  2       7

I want to impute the value in 2005 for case 2 as the average between the value in 2004 and 2006 if and only if data exists in those years.

On another note, it would be nice to run a cross-year correlation, but I can't figure that out either. How do the values in 2004 correlate with the values in 2008?

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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   |   Site index