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]

Re: st: running simple regression on mixed data of cross-section and panel


From   Melaku Fekadu <melaku.fekadu@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: running simple regression on mixed data of cross-section and panel
Date   Wed, 8 Dec 2010 17:04:16 +0200

thanks Clyde. you helped me to know that i have a problem. I will try
xtreg and xlogit.
i will try to learn about these procedures more. thanks again.

On Sat, Dec 4, 2010 at 6:49 PM, Clyde Schechter
<clyde.schechter@einstein.yu.edu> wrote:
> "I want to do a regression of employment (logistic) and wage
> (loglinear) on some demographic variables. I do the regressions on a
> cross-section data of labor force survey. However, small proportion of
> individuals in the data recur more than once."
>
> Strictly speaking you no longer have independent observations, so your
> estimates of standard errors, p-values, likelihood ratio tests, etc., will
> be incorrect if you rely on ordinary logistic regression.
>
> From a practical perspective, the best solution depends on how small the
> number of recurrent individuals is and how they came to recur.  If they
> are really few and your overall data set is large enough that you would
> not lose substantial power, you might simply delete all but one occurrence
> for any such person.  Depending on the substance of your problem, you
> might retain only the first observation per person, or only the last, or
> one observation per person selected at random.  This approach also assumes
> that the fact of occurring more than once in the data set happens
> independently of the variables you are studying and the relationships
> among them.
>
> Or you may want to retain all of your data.  In that case you should look
> into -xtlogit-.  You will then have to give some thought to whether fixed
> or random effects are most appropriate for your problem.
>
> Clyde Schechter, MA MD
> Associate Professor of Family & Social Medicine
> Albert Einstein College of Medicine, Bronx, NY, USA
>
> Please note new e-mail address: clyde.schechter@einstein.yu.edu
>
> *
> *   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index