Re: st: The sample reduces when running logistic regressions

[Richard Williams <richardwilliams.ndu@gmail.com>]

I don't know if it applies here, but the Mi Impute manual does have a 
section on "The issue of perfect prediction during imputation of 
categorical data."

Also, there is nothing that says you can't still have missing data 
after using Mi.  For example, if a variable has hard missings (.a, 
.b, etc) it stays missing after imputation. If you don't impute Y it 
can still have missing. If a case is missing on a bunch of variables 
you may not be able to impute values for it.

At 02:43 PM 12/17/2013, Maarten Buis wrote:
> Sounds to me like a problem of perfect prediction. You can read more
> about that here:
> http://www.stata.com/support/faqs/statistics/completely-determined-in-logistic-regression/
>
> Hope this helps,
> Maarten
>
>
> On Tue, Dec 17, 2013 at 6:25 PM, liliana <lilly-90@hotmail.it> wrote:
> > Hello,
> >
> > I am running a logistic regression on different samples using multiple
> > imputations:
> >
> > mi estimate, or post: logit Y X1 X2, vce(cluster PSU)
> >
> > I have run the regression for the first samples and Stata gave me back
> > results where all the observations are included, except for one sample for
> > which I have got 1332 observations but 1292 observations were 
> taken by Stata
> > for the regression. In addition, the categorical variable education
> > (i.education which takes values 0, 1, 2, and 3) presents a problem:
> > 0.education is the baseline, for 1.education and 2.education Stata gives me
> > back the relative coefficient, whereas 3.education is omitted 
> although there
> > are 168 observations.
> >
> > Which could be the causes of these two problems?
> >
> > Thanks in advance.
> > Lil
> >
> >
> >
> > --
> > View this message in context: 
> http://statalist.1588530.n2.nabble.com/The-sample-reduces-when-running-logistic-regressions-tp7580467.html
> > Sent from the Statalist mailing list archive at Nabble.com.
> > *
> > *   For searches and help try:
> > *   http://www.stata.com/help.cgi?search
> > *   http://www.stata.com/support/faqs/resources/statalist-faq/
> > *   http://www.ats.ucla.edu/stat/stata/
>
>
>
> --
> ---------------------------------
> Maarten L. Buis
> WZB
> Reichpietschufer 50
> 10785 Berlin
> Germany
>
> http://www.maartenbuis.nl
> ---------------------------------
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/faqs/resources/statalist-faq/
> *   http://www.ats.ucla.edu/stat/stata/

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW:    http://www.nd.edu/~rwilliam

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/