stepwise in panel

[Rodrigo Monteiro Barbosa]

Hi

I'm running a panel data with N=399 and T=12, I'm looking for a way to run this panel with stepwise, but don't found nothing.
Here in blog I've read that stepwise isn't a good method but, please, someone can help me?

Thanks a lot

[Phil Bromiley]

Welcome to Statalist. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stata output, and sample data using dataex.

If you want fixed effects, you can do that with stepwise and reg with i.panel as an explanatory variable.

Many do not like stepwise because it often leads to over fitting - finding results that fit the idiosyncrasies of the sample but are not generalizable. If you do stepwise, you cannot then pretend you were generating the model from theory and run a regression on the selected variables.