Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: margins after heckman


From   SIRENIA VAZQUEZ BAEZ <sirenia.vazquez@bbva.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: margins after heckman
Date   Thu, 3 Oct 2013 19:18:42 -0500

Hello,
I'm new with the -margins- command and I'm using it after -heckman-
with the eyex() option in Stata 13 to estimate the elasticity of
credit card purchases to credit cards interest rates using credit card
panel data. My dependent variable is the amount of credit card
purchases, and as explanatory variables I have the interest rate (with
time lags), credit limit, sex, geographic region, credit score, among
others.

When I type margins, eyex(interest_rate) atmeans , I get the following results:

ey/ex = -3.120104
Std.Err. = 6.181389
z-statistic = -0.50
P|>z|= 0.614

It surprises me that the p-value is 0.614 since I thought -margins-
automatically excluded the regressors that are not significantly
different from 0 (p>.10), but apparently it doesn't. Should I clean up
my regression and exclude the non-significant regressors before I run
-margins-?  and Am I interpreting correctly if I say that a 1%
increase in credit card interest rates is associated with a 3.12%
decrease in credit card purchases?

Many thanks,
Sirenia
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index