Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: interaction term of logritham of raw data----what form it should be?


From   "Justin Smith" <smithjd5@univmail.cis.mcmaster.ca>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: interaction term of logritham of raw data----what form it should be?
Date   Mon, 19 Jun 2006 21:43:25 -0400

In addition to my last comment, you should be very careful when you
calculate the marginal effects of interactions in nonlinear models...

Be sure to consult this paper before calculating those effects...

http://www.unc.edu/~enorton/AiNorton.pdf

Justin Smith

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Xiaoheng Zhang
Sent: June 19, 2006 5:32 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: interaction term of logritham of raw data----what form it
should be?

Hello all,

I have two variables that are

agglopharma = number of firms (ranging from 5 to 300)
eatr = effective average tax rate (ranging from 8.5 to 55)

They all enter the conditional logit regression in log form.I would like to
use
interaction term of these two variables(also in log form),which one should I
use?

ln(agglopharma*eatr) = ln(agglopharma)+ln(eatr)

or

ln(agglopharma)*ln(eatr) = ln(agglopharma+eatr)?

Thanks for reading anf TIA!

Kevin

*
*   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/


*
*   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