Statalist


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

Re: AW: st: re: beta coefficients for interaction terms


From   lschoele@rumms.uni-mannheim.de
To   statalist@hsphsun2.harvard.edu
Subject   Re: AW: st: re: beta coefficients for interaction terms
Date   Sun, 21 Jun 2009 18:04:20 +0200

But according to Ulrich Kohler first option is wrong. I included what he wrote a few months ago.

I think Lisa refer the section on standardized regression cofficients of
that book, particularly to the second item on pg. 201 (English edition).
That item states that one should not use b*s_x/s_y to create
standardized regression coefficients in the presence of interaction
terms. Based on Aiken/West 1991 (28-48) it is recommended that one
should standardize all variables that are part of the interaction in
advance. Hence, instead of coding

. sysuse auto, clear
. gen ia = head*length
. reg mpg head length ia, beta

you should code

. sysuse auto, clear
. egen shead = std(headroom)
. egen slength = std(length)
. egen smpg = std(mpg)
. gen ia2 = shead*slength
. egen sia2 = std(ia2)
. reg smpg shead slength sia2


So I guess the second option gives me the right beta coefficients.

But what do I get from the third option? Are those coefficients normally included in the regression results?

Best,
Lisa


Zitat von Martin Weiss <martin.weiss1@gmx.de>:


<>

Well, this thread has produced three options for you to choose from, and you
have heard all the pros and cons. Just to summarize:


*************
sysuse auto, clear

/*first option */
qui gen ia2 = head*length
reg mpg head length ia2, beta

/*second option */
qui{
	egen shead = std(headroom)
	egen slength = std(length)
	egen smpg = std(mpg)
	replace ia2 = shead*slength
	egen sia2 = std(ia2)
}

reg smpg shead slength sia2


/*third option */
reg mpg shead slength sia2
*************



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von
lschoele@rumms.uni-mannheim.de
Gesendet: Sonntag, 21. Juni 2009 17:33
An: statalist@hsphsun2.harvard.edu
Betreff: Re: st: re: beta coefficients for interaction terms

I am sorry, but I am getting kind of confused here. I am not a pro in
running regressions with interaction terms, I am sorry that I have to
ask so many questions.

To get the beta coefficients I have to run the regression

.reg smpg shead slength sia2


If I run the regression

.reg mpg shead slength sia2

I get the coefficients, that are not standardized?

Am I right?

Best,
Lisa


Zitat von Kit Baum <baum@bc.edu>:

<>
Martin said

" so it is not telling you anything for which you need to estimate the
regression to find out."

So the point estimate is equal to ouput of other commands, bout how
about
the CI?



The unconditional CI is larger:

. means mpg

     Variable |    Type        Obs        Mean       [95% Conf.
Interval]
-------------+----------------------------------------------------------
          mpg | Arithmetic      74     21.2973         19.9569
22.63769
              |  Geometric      74    20.58444        19.38034
21.86335
              |   Harmonic      74    19.92318        18.81185
21.17405
------------------------------------------------------------------------

because the standardized regressors that are added to the model are
indeed correlated with mpg:

        _cons |    21.2973   .4121741    51.67   0.000     20.47524
22.11935

but as you can see that doesn't make much difference in testing any
meaningful hypothesis about the mean of mpg.



Kit Baum   |   Boston College Economics & DIW Berlin   |
http://ideas.repec.org/e/pba1.html
                              An Introduction to Stata Programming  |
http://www.stata-press.com/books/isp.html
   An Introduction to Modern Econometrics Using Stata  |
http://www.stata-press.com/books/imeus.html



*
*   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/


*
*   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