Statalist


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

st: Re: missing values


From   Kit Baum <baum@bc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Re: missing values
Date   Wed, 18 Nov 2009 10:12:35 -0500

<>
I'm not sure -nmissing- is the answer here, as this involves listwise deletion: any observation with a value missing in any variable in the regression will be dropped. Something like this will test for that:

sysuse auto,clear
replace turn = . if foreign & mod(_n,2)
replace weight = . if !foreign & !mod(_n,2)
nmissing price rep78 turn weight

g ts1 = rep78+turn
g ts2 = rep78+weight
g ts3 = turn+weight
g ts4 = rep78+turn+weight
g ts5 = length+displacement+gear_ratio
su ts*

The N reported by summarize is the number of cases that would enter the regression, given these regressors.

On Nov 18, 2009, at 2:33 AM, statalist-digest wrote:

> I'm using windows XP and stata 9.2. I'm running some econometric
> models and when I got the output I can see the number of observations
> that were used in the estimation.
> Since my database has several missing values for almost all variables
> I would like to know if there is some command-function that allow me
> to see which combination of variables will produce the regression with
> the highest avaialble number of non-missing observations.


Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   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   |   What's new   |   Site index