I know this is an easy question but I'm trying to get the format for the regression equation for a country and year fixed effect model I have built on Stata.

My code is as follows:

xtset country_code
xtreg difference i.year alcoholwarning cigarettewarning warningintroduced, fe robust

This is a country and year fixed effect model, but I have done the year fixed effects using the i.year command (I'm not sure how else to include both fixed effects on stata).

'difference' refers to differenced data on the percentage of poeple who smoke/drink in each country, and 'alcoholwarning' 'cigarettewarning' and 'warningintroduced' are all dummy variables. I'm just not sure how this would translate into a generic regression equation?

Also, would you say it is worth including fe robust and why?

  • $\begingroup$ If all the other RHS variables are dummies, you should also use the i. prefix (though that is not consequential here). I would read the pdf manual for xtreg, fe, then come back and edit your question with remaining confusion. Right now this is a mix of things that are documented in the manual, and teach me all of basic panel data econometrics. Also, you will need to elaborate on what differenced means. $\endgroup$ – Dimitriy V. Masterov May 6 at 21:22
  • $\begingroup$ Hi, thanks for this. Statistically speaking do you know what the equation would look like for this model? $\endgroup$ – summer_ZUGG May 7 at 8:04
  • $\begingroup$ I think you need to clarify "Differenced data". I am unsure what the difference could be: is it a percent change from a study? a year in year change? elaborate. I would use xtset country_code year and it will include both fixed effects when you specify the option , fe $\endgroup$ – Brennan Jun 27 at 21:33

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.