st: AW: Multiple Imputation on Panel Data: all variables have missing data, and the panels are expanding

["Martin Weiss" <martin.weiss1@gmx.de>]

<> 


" I am trying to use STATA 12's"


You must be the first person to get a copy of it outside StataCorp... What
is it like?



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Jennie Day
Gesendet: Dienstag, 24. August 2010 11:35
An: statalist@hsphsun2.harvard.edu
Betreff: st: Multiple Imputation on Panel Data: all variables have missing
data, and the panels are expanding

Hi out there.  Thanks for having a look at my questions.  I have two:

1)  I am trying to use STATA 12's mi commands to do multiple imputations on
a panel dataset where all variables have some missing values (save the
unique ID numbers and the time variable).  I am getting confused on whether
to register a variable as passive or imputed.  Can anybody tell me what is
the standard of care here? 

2) I have a panel dataset where the number of observations has expanded over
time.  There are 292 observations in 1993, and 434 observations in 2007.  Is
there a way to avoid imputing values for IDs 293-434 in 1993, etc?

Here are some details about my dataset:   

A) I have a panel dataset beginning in 1993 and going to 2007, annually.  

B) I have some variables that have a 1% missing rate and some that have a 10
percent missing rate.  Should I use imputed for the ones with lower
non-response rates and passive for the ones with higher non-response rates?

C) All of my variables are continuous.

Thanks in advance,
jennie
*
*   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/


*
*   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/