logit with country, industry and year fixed effect

[Abdramane Cherif]

Hello, I have a problem for you to consider. I am conducting a study on access to credit. My sample consists of 13400 firms from several countries (27 in total). I am facing a design problem. Indeed, although the survey questionnaire is identical in all countries, the year of administration is not the same. For example, in Chad the survey was carried out in 2018 whereas in CAMEROON it was in 2016. My question is: given that my study period is 2010 to 2018 and that in each country the survey was conducted once, is this a panel? Or is it cross-sectional data? Since in each country the survey was carried out only once. So no repetition. If so, is it possible to estimate a simple logit (my dependent variable is binary) with fixed effect (industry, country and year)? can you know a synthax or stata command to estimate this model?


Thank you.

[William Lisowski]

Welcome to Statalist.

You have accidentally posted your topic in Statalist's Mata Forum, which is used for discussions of Stata's Mata language, which is different than Stata's command language, and different than Stata's matrix commands. Your question will see a more appropriate, and much larger audience if you post it in Statalist's General Forum.