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

Re: st: Missing values in panel data

From   Maarten buis <[email protected]>
To   [email protected]
Subject   Re: st: Missing values in panel data
Date   Tue, 12 Jan 2010 10:55:45 -0800 (PST)

--- On Tue, 12/1/10, Paul Seed <[email protected]> wrote:
> I have a puzzle.  Is it better to use -xtreg, gls- or
> -xtreg, mle- for panel data with missing values?  Little &
> Rubin have suggested that maximum likelihood estimation
> corrects for MCAR data if the model is correctly specificed.

I don't see why MCAR would be a problem at all (appart from
the smaller sample size): ignoring observations with missing
values if the missingness mechanism is MCAR just means you 
have drawn a random sample from your random sample, so no
bias will be the result of that. So that would mean that if 
you know your process is MCAR you can use whatever method 
you like.

-- Maarten

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

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