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

st: Marginal effects: at what value should you calculate?


From   "Sayer, Bryan" <BSayer@s-3.com>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: Marginal effects: at what value should you calculate?
Date   Wed, 2 Oct 2002 17:41:08 -0400

Korn, E. and Graubard, B. "Predictive Margins for Survey Data", Biometrics,
about June 1999.  You can ignore the survey design issues if they don't
apply to you, and the rest still holds.  BTW, they are only the same for
mean based models, like OLS, and the s.e. are different.

Bryan Sayer
Statistician, SSS Inc.
bsayer@s-3.com

(p.s. I might not have the title just right, but it's close)

-----Original Message-----
From: epowers@moore.sc.edu [mailto:epowers@moore.sc.edu]
Sent: Wednesday, October 02, 2002 3:20 PM
To: statalist@hsphsun2.harvard.edu
Subject: st: Marginal effects: at what value should you calculate?


In "Econometric Analysis" by William H. Greene, 3rd edition.  He 
states on page 876: "For computing marginal effects, one can 
evaluate the the expressions at the sample means of the data or 
evaluate the marginal effects at every observation and use the sample 
average fo the individual marginal effects.  The functions are 
continuous, so Theorem 4.3 (the Slutsky theorem) applies; in large 
samples these will give the same answer.  But that is not so in small or 
moderate sized samples.  Current practice favors averaging the 
individual marginal effects when it is possible to do so."

Is there any more definitive guidance out there for the values at which 
one should calculate marginal effects?  While I agree that it makes 
intuitive sense to do the calculations at every observation and 
average, is there a theoretically sound reason to do so?

Sincerely,

Eric A. Powers
Assistant Professor of Finance
The Moore School of Business
University of South Carolina
Columbia SC, 29208

---
[This E-mail scanned for viruses by Declude Virus]

*
*   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