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]

Re: st: Statistical Significance of the difference between two estimates from two separate regressions


From   John Antonakis <[email protected]>
To   [email protected]
Subject   Re: st: Statistical Significance of the difference between two estimates from two separate regressions
Date   Fri, 14 Mar 2014 11:14:12 +0100

Hi:

Two ways to do this:

reg y x if male = 0
est store zero
reg y x if male = 1
est store one
suest zero one

Then see -help suest- on how to test cross-equations coefficients. In your case it will be:

test x[zero_mean] = x[one_mean]

A more elegant and efficient way to do this is follows (assuming x is continuous, where we use factor variables, see -help factor variables-):

reg y c.x##i.male

...which will estimate the following:

y = b0 + b1x + b2male + b3x.male + e

The test of the coefficient b3 is the test of the difference of slopes of the effect of x for males and females.

Of course, for females, the effect of x on y is b1. For males the effect of x on y is b1 + b3

After estimation, you can see the interaction graphically (suppose the range of your x-axis is 1 through 20:

margins male, at(x = (1 20))

To better understand interactions see:

Aiken, L. S. & West, S. G. 1991. Multiple Regression: Testing and Interpreting Interactions. Newbury Park, CA: Sage Publications.

HTH,
J.

__________________________________________

John Antonakis
Professor of Organizational Behavior
Director, Ph.D. Program in Management

Faculty of Business and Economics
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland
Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305
http://www.hec.unil.ch/people/jantonakis

Associate Editor:
The Leadership Quarterly
Organizational Research Methods
__________________________________________

On 14.03.2014 11:03, Kyrizi, Andri wrote:
Dear Statalisters,

I am running two (pooled ols) wage regressions: one for males and one for females.

I would like to test whether there is a difference between the estimates of the two groups and if the difference is statistically significant.

Most importantly I am interested to see if the coefficient I receive for education is statistically different between the two groups.

Could anyone help me with this? Is there a test to do this?

Thank you,
Andri
*
*   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/

*
*   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