[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: estimating an unbalanced panel

From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: RE: estimating an unbalanced panel
Date   Mon, 21 Jan 2008 16:41:06 +0000 (GMT)

> --- Jessica [iso-8859-1] �lschl�ger asked: 
> I've got an unbalanced panel dataset covering 30 OECD-countries (i)
> over a period of 15 years (t).
> Running for example a fixed effects regression, I lose a lot of
> observations due to the missings in some of the variables In some
> cases I only have about 50 observations left.
> Is there a way to some kind of "save on observations" i.e. tell stata
> to use all of the observations available irrespective of the fact
> that some of the observations for a country i (panel) at time t are
> missing?

--- Nick Cox <[email protected]> answered:
> It's not clear what you want Stata to do here given missings: try
> harder? 
> If there are missings, the only way to get more out is to put more
> in, e.g. impute values where missings would be otherwise. And then
> you need to discount your results accordingly. 

One way to do what Nick suggests is to do multiple imputation, which in
Stata is implemented as -ice-, (within Stata type -ssc install ice-,
-ssc install mim-, -help ice-, and -help mim-). You might want to do
some reading before you get into that. 

Royston, P. 2004. Multiple imputation of missing values. Stata Journal
4(3): 227�241.

Royston, P. 2005. Multiple imputation of missing values: update. Stata
Journal 5(2): 188�201.

Royston, P. 2005. Multiple imputation of missing values: Update of ice.
Stata Journal 5(4): 527-536. 

Hope this helps,

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

Sent from Yahoo! Mail - a smarter inbox

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index