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 at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: Mlogit estimated coefficients


From   Joerg Luedicke <joerg.luedicke@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Mlogit estimated coefficients
Date   Wed, 8 May 2013 21:50:08 -0400

On Wed, May 8, 2013 at 12:56 PM, Ekim Cem Muyan <ekimcmuyan@gmail.com> wrote:
<snip>
> I couldn't figure out how STATA stores the
> estimations results from a mlogit regression.

Like other eclass commands, -mlogit- stores results in -e()-. After
fitting a model, type -ereturn list- to see what's available. For
example,

mat li e(b)

returns a vector with the estimated coefficients. You can then
use/rearrange these results to your liking. For example, the following
code creates a 2 x k matrix with coefficients, with k being the number
of predictors in the model (including constants):

*---------------------------------------
// Toy data
clear
sysuse auto
replace rep78 = rep78 - 2 if rep78 > 2

// -mlogit- fit
mlogit rep78 price mpg headroom trunk, b(1)

// Create a 2 x k matrix, where k is the
// number of predictors in the model,
// for an arbitrary number of predictors
qui levelsof `e(depvar)', loc(level)
loc base = e(baseout)
loc rowlab = regexr("`level'","`base'","")
loc np = e(k)
mat b = e(b)

mat b1 = b[1, `=`np'/2+1'..`np']
mat b2 = b[1, `=`np'+1'..`=`np'+`np'/2']
mat bmat = b1\b2
mat rownames bmat = `rowlab'

mat li bmat
*---------------------------------------

This could further be automated, for example to allow for arbitrary
base outcomes and number of outcome categories.

Joerg



On Wed, May 8, 2013 at 12:56 PM, Ekim Cem Muyan <ekimcmuyan@gmail.com> wrote:
> Hi! I am having trouble storing my estimated 'mlogit' coefficients in a matrix.
>
> Essentially, I have three categories and five explanatory variables. I
> want to store my coefficients in a 2x5 matrix so that I can transfer
> them to MATLAB automatically. (I will have to do this for many times,
> so I'd rather not copy). I couldn't figure out how STATA stores the
> estimations results from a mlogit regression.
>
> I'd appreciate any feedback. Thanks a lot!
> *
> *   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/
*
*   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/


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