Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: RE: Multiple Imputation for panel data
From
Nick Cox <[email protected]>
To
"'[email protected]'" <[email protected]>
Subject
st: RE: Multiple Imputation for panel data
Date
Wed, 23 Feb 2011 13:52:25 +0000
I think the question for you is how do you imagine you would do this? In a panel setting, it is not at all obvious how far to mix using the dependence structure in time and using cross-sectional relationships. Arguably, the right method to impute depends on the generating process, which is exactly what you are trying to identify. Still, I am observing this from a great distance, and people who work with panel data all the time may know of some conventional wisdom.
Nick
[email protected]
Sun, Yan
I have a small panel (20 years for 9 states), for each variable, for
some states, I have observations for some years, but missing some for
other years. Could I use Multiple Imputation (MI) for my regression? If
the answer is yes, could you recommend some literature? Many thanks.
*
* 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/