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

# Re: st: interaction between sex and year dummies

 From Tirthankar Chakravarty To statalist@hsphsun2.harvard.edu Subject Re: st: interaction between sex and year dummies Date Mon, 5 Dec 2011 03:48:06 -0800

```Here is a simple example using another dataset from Prof. Wooldridge's
book (in the future, you should try to give the full reference to the
book) which illustrates how to substantively interpret a regression
with interaction terms (here the interaction is between married people
and years, as opposed to gender). If you'd like to see if the gender
gap decreases on average then those are the statistics you should
construct and interpret. In particular, you should not try to
interpret the coefficients on the interaction terms on their own.

******************************************************
use http://fmwww.bc.edu/ec-p/data/wooldridge/WAGEPAN, clear
xtset nr year
xtreg lwage exper educ union hisp black ///
i.married##i.year, fe
margins, over(married year)
marginsplot, xdimension(year) ///
plotdimension(married) xlabel(, angle(90))
******************************************************

As is probably clear from the plot, the estimation results indicate
that the average log-wage has increased over the years for both
married and unmarried people, but has remained higher for married
people.

T

On Mon, Dec 5, 2011 at 2:31 AM, valentina tortolini <valetort@gmail.com> wrote:
> Dear all, I'm carring out a fixed effect analysis on wage data. I'd
> like to see wether the gender gap descreases or increases over time as
> a results of the coefficients of the FE estimator.
> I'm estimating an equation like this:
> log_wage=b0+b2*year2+...+bT*yearT+c1*(sex*year1)+...cT(sex*yearT)
> As long as the wage gap (male wage vs female wage)  decreases over
> time as it likely in my data what kind of pattern should I expect from
> coefficient c1...cT?
> In Wooldridge 2010 (cap 10) there is a brief of explanation this
> problem but is it non clear how to interpretate the coefficients.
> Any help will be very appreciated!
> Best regards
> Valentina
> *
> *   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/

--
Tirthankar Chakravarty
tchakravarty@ucsd.edu
tirthankar.chakravarty@gmail.com

*
*   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/
```