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, is already up and running.

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

AW: st: problems with probit after multiple imputation with ice

From   "Berger, Martin" <>
To   "" <>
Subject   AW: st: problems with probit after multiple imputation with ice
Date   Mon, 20 Jun 2011 13:18:51 +0200

thanks Marten,

you are right for the example, of course. 

However, my real mim: probit includes variables with several missing values -, could there be any other cause you can think of?!

-----Ursprüngliche Nachricht-----
Von: [] Im Auftrag von Maarten Buis
Gesendet: Montag, 20. Juni 2011 12:26
Betreff: Re: st: problems with probit after multiple imputation with ice

On Mon, Jun 20, 2011 at 12:11 PM, Berger, Martin wrote:
> I am using STATA 10 and have problems with running probit estimates after the multiple imputation with ice.
> For illustration  the following -stupid- example, which shows what happens when using my real data:
> sysuse auto, clear
> ice price rep78 mpg foreign, m(5) saving(d:\temp\icetest.dta)
> use d:\temp\icetest.dta, clear
> mim: probit foreign price
> micombine probit foreign price
> The probit works fine using micombine but not using mim: - why?!
> Any idea, what might cause the problem?! (maybe I don't see the obvious...)

There are no missing values in any of the variables you used in your
-probit- model. So there is no between imputation variance in the
coefficients and -mim- seems to choke on that.

Hope this helps,

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

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index