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: margins vs. lincom


From   "Michael N. Mitchell" <Michael.Norman.Mitchell@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: margins vs. lincom
Date   Wed, 15 Dec 2010 22:54:13 -0800

Dear Paul

The difference appears to be that -lincom- is using a t-distribution and -margins- is using a z distribution. See the output below my signature based on your example. In looking at the "Methods and Formulas" section of the -margins- documentation, it refers to the use of maximum likelihood estimation. My hunch is that is the reason that the z distribution is used, but someone might have something better than a hunch.

I hope that helps,

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

-----------------------
Output
-----------------------

. clear

. webuse margex
. set seed 1
. sample 1     // draw a 1% sample of the data
. regress y i.sex
(output omitted)
. margins sex

Adjusted predictions                              Number of obs   =         30
Model VCE    : OLS

Expression   : Linear prediction, predict()

------------------------------------------------------------------------------
             |            Delta-method
             |     Margin   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         sex |
          0  |   62.77647   4.230417    14.84   0.000     54.48501    71.06794
          1  |   72.60769   4.837667    15.01   0.000     63.12604    82.08935
------------------------------------------------------------------------------

. lincom 1.sex+_cons
 ( 1)  1.sex + _cons = 0

------------------------------------------------------------------------------
           y |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         (1) |   72.60769   4.837667    15.01   0.000     62.69818     82.5172
------------------------------------------------------------------------------








On 2010-12-15 1.38 PM, Visintainer, Paul wrote:
clear
webuse margex
sample 1     // draw a 1% sample of the data
regress y i.sex
margins sex
lincom 1.sex+_cons
*
*   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