How does xtreg treat covariates?

[Hugo Andre]

Hello, hopefully this is a relatively simple question but I haven't been able to find the answer online or in the reference manual on xtreg.

I am trying to estimate the effect of minimum wages on fringe benefits. For this purpose I have included state level time-varying covariates (log population, GDP per capita, etc). However I just realized that I am not sure how the command xtreg treats covariates that vary over time. If the minimum wage changes in some states between year 0 and year 1, what value does xtreg use for the controls? The value it takes in year 0, the value it takes in year 1 or the difference between the two?

[Carlo Lazzaro]

Hugo9:
welcome to this forum.
In addition to any decent textbook on panel data econometrics, see -xtreg- entry in Stata .pdf manual, pages 423-425.

[Hugo Andre]

Thank you Carlo. I didn't realize that the X in Stata's manual includes both the regressor and the covariates. I should have realized it though. Apologies for the stupid question.

[Carlo Lazzaro]

Hugo:
no trivial question at all.
When each new user starts its experience with Stata (it happened to me about 10 years ago), she/he is usually more interested in dealing with data than getting familiar with the manual.
However, later on the same user will discover that many of her/his doubts can be eased by the Stata manual and its references.