Statalist


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

Re: st: Re: Multiple Imputation


From   JIBONAYAN RAYCHAUDHURI <jibonayanrc@yahoo.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Re: Multiple Imputation
Date   Tue, 16 Dec 2008 09:31:14 -0800 (PST)

Hi,
I also had another concern. I have a panel data set of firms that are classified by industry (nic in the code below). I am predicting the value of the residual from levpet and that is the measure of TFP. Can I use both _mj== #  and nic2== ## where # and ## are two numbers in the same code? How do I get the predicted value of e`num' from each of the imputations? Finally, where in your  code are we using  mim as you mentioned in the first mail? Thank you for your help.

CODE

#delimit;
set seed 000000001; /*levpet GIVES DIFFERENT RESULTS EACH TIME WE RUN SO SET seed*/

#delimit;
foreach num of numlist 15 16 17 18 19 20 21  23 24 25 26 27 28 29 30 
31 32 33 34 35 {;
dis "nic2=`num'";
levpet lognetvalueadded if nic2==`num', 
free(lognoofemployees)
proxy(lograwmaterialexpenses) 
capital(lognetfixedassets);
predict e`num', omega;
replace tfplevpet=e`num' if nic2==`num';
};

Jibonayan
--- On Mon, 12/15/08, Maarten buis <maartenbuis@yahoo.co.uk> wrote:

> From: Maarten buis <maartenbuis@yahoo.co.uk>
> Subject: Re: st: Re: Multiple Imputation
> To: statalist@hsphsun2.harvard.edu
> Date: Monday, December 15, 2008, 11:45 PM
> --- JIBONAYAN RAYCHAUDHURI <jibonayanrc@yahoo.com>
> wrote:
> > Thank you for the code. When I run it it gives me the
> following
> > error:
> > 
> >  ice wage grade age union, clear m(5)
> > saving() required
> > r(100);
> 
> you are probably not using the latest version of -ice-.
> Type 
> -ssc install ice, replace-. Notice that the version on SSC
> is usually
> more recent than the version from the Stata Journal.
> 
> -- Maarten
> 
> -----------------------------------------
> Maarten L. Buis
> Department of Social Research Methodology
> Vrije Universiteit Amsterdam
> Boelelaan 1081
> 1081 HV Amsterdam
> The Netherlands
> 
> visiting address:
> Buitenveldertselaan 3 (Metropolitan), room N515
> 
> +31 20 5986715
> 
> http://home.fsw.vu.nl/m.buis/
> -----------------------------------------
> 
> 
>       
> *
> *   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   |   What's new   |   Site index