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, statalist.org is already up and running.


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

Re: st: How to name equations or test coeffs across regs


From   "Michael N. Mitchell" <Michael.Norman.Mitchell@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: How to name equations or test coeffs across regs
Date   Mon, 27 Sep 2010 12:13:14 -0700

Dear Emily

  Here is an example using the -auto- dataset that I hope is helpful.

. sysuse auto
(1978 Automobile Data)

. sureg (price length weight) (mpg length weight)

Seemingly unrelated regression
----------------------------------------------------------------------
Equation          Obs  Parms        RMSE    "R-sq"       chi2        P
----------------------------------------------------------------------
price              74      2    2366.261    0.3476      39.42   0.0000
mpg                74      2     3.34377    0.6614     144.54   0.0000
----------------------------------------------------------------------

------------------------------------------------------------------------------
             |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
price        |
      length |  -97.96031    38.3723    -2.55   0.011    -173.1686   -22.75198
      weight |   4.699065   1.099354     4.27   0.000     2.544371    6.853759
       _cons |   10386.54   4219.928     2.46   0.014     2115.635    18657.45
-------------+----------------------------------------------------------------
mpg          |
      length |  -.0795935    .054224    -1.47   0.142    -.1858706    .0266836
      weight |  -.0038515   .0015535    -2.48   0.013    -.0068963   -.0008067
       _cons |   47.88487   5.963191     8.03   0.000     36.19723    59.57251
------------------------------------------------------------------------------

. test [price]length

 ( 1)  [price]length = 0

           chi2(  1) =    6.52
         Prob > chi2 =    0.0107

. test [mpg]length

 ( 1)  [mpg]length = 0

           chi2(  1) =    2.15
         Prob > chi2 =    0.1421

. test [price]length == [mpg]length

 ( 1)  [price]length - [mpg]length = 0

           chi2(  1) =    6.50
         Prob > chi2 =    0.0108

Best luck!

Michael N. Mitchell
Data Management Using Stata      - http://www.stata.com/bookstore/dmus.html
A Visual Guide to Stata Graphics - http://www.stata.com/bookstore/vgsg.html
Stata tidbit of the week         - http://www.MichaelNormanMitchell.com



On 2010-09-27 11.53 AM, Emily Rauscher wrote:

I am trying to use the test function to see whether a coefficient is equal in two different OLS regressions.  However, I cannot figure out how to name equations.

When I use the sureg command, as suggested on pp. 1914-5 of the version 11 user's manual, stata does not recognize the first word as an equation name and gives an error.

I feel I'm missing something very simple, but I have searched the manual and tried everything I can find.
Any suggestions - for either naming equations or a better way to test the equality of coefficients in different regressions - would be hugely appreciated.
Many thanks,
Emily

*
*   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   |   Site index