Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: -mlogit- does not report all results


From   "Clive Nicholas" <Clive.Nicholas@newcastle.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: -mlogit- does not report all results
Date   Thu, 20 May 2004 18:28:38 +0100 (BST)

Adrian de la Garza wrote:

> I am running this model
>
> mlogit indic g_usip1 lswap embi_sd, basecat(0)
>
> and then using
>
> outreg using mlogit.out, replace bdec(3) bra nocon onecol
>
> to put my results in a table.
>
> My dependent variable takes values 0,1,2 with 0 as the base category of
> the mlogit. When I run the model, I see all the results, but my outreg
> command only stores those results for my 1s but not for my 2s.
>
> Why isn't -outreg- displaying the whole set of results?

For my part, all I can say is that, using the 'auto' dataset, I get the same:


. mlogit rep78 price mpg weight length foreign, basecat(1)

[...]

. outreg using junk.out, bdec(3) bra nocon onecol

	        Repair Record 1978
2:Price	        0.001
	        [0.67]
2:Mileage (mpg)	-0.054
	        [0.14]
2:Weight (lbs.)	-0.004
	        [0.87]
2:Length (in.)	0.107
	        [0.89]
2:Car type	-17.880
	        [0.00]
Observations	69
Absolute value of z statistics in brackets
* significant at 5%; ** significant at 1%

It appears to take the results from the first panel and omits the rest,
which is strange behaviour indeed!

Perhaps -est table- offers a partial way out here. Again, using 'auto':

. est table rep78, b(%9.3f) stats(r2_p ll chi2 N) star label varwidth(20)
newpanel

-------------------------------------
            Variable |    rep78
---------------------+---------------
1                    |
               Price |    -0.000
       Mileage (mpg) |     0.020
       Weight (lbs.) |     0.001
        Length (in.) |    -0.010
            Car type |   -33.048
            Constant |    -0.392
---------------------+---------------
2                    |
               Price |     0.000
       Mileage (mpg) |    -0.034
       Weight (lbs.) |    -0.003
        Length (in.) |     0.097
            Car type |   -33.928
            Constant |    -9.452
---------------------+---------------
4                    |
               Price |    -0.000
       Mileage (mpg) |     0.233
       Weight (lbs.) |    -0.001
        Length (in.) |     0.085
            Car type |     3.404*
            Constant |   -19.996
---------------------+---------------
5                    |
               Price |     0.000
       Mileage (mpg) |     0.415*
       Weight (lbs.) |    -0.004
        Length (in.) |     0.167
            Car type |     3.667*
            Constant |   -33.950*
-------------------------------------

-------------------------------------
          Statistics |    rep78
---------------------+---------------
                r2_p |     0.241
                  ll |   -71.103
                chi2 |    45.177
                   N |    69.000
-------------------------------------
legend: * p<0.05; ** p<0.01; *** p<0.001

Of course, this doesn't really answer your question about -outreg-,
especially since you probably want your regressions side-to-side, as
opposed to being stacked. Others may know of more effective workarounds
for your problem.

CLIVE NICHOLAS        |t: 0(044)191 222 5969
Politics              |e: clive.nicholas@ncl.ac.uk
Newcastle University  |http://www.ncl.ac.uk/geps
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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