I am doing panel analysis of state drug policies. My data set includes 50 states and ten time points. I am using one-way state fixed-effect models, controlling for heteroskedasticity and autocorrelation using Stata xtscc command.
In one of the models, 48 of the state dummy variables are significant. Is this a problem? My model has ten IVs, five of which are significant in this model with an R-squared of .80.
Best Answer
No, that's not a problem.
If you have an intercept term in your model, one of the state dummies will be dropped, and the others then give the state means relative to the omitted state. In this case, statistically significant state dummies just mean that those states have means that are statistically significantly different from the omitted state. I can't see how this would be a problem.
If you instead have dropped your intercept term, and therefore can include dummies for all states, the state dummies simply capture the mean for each state. In this case, statistically significant dummies just mean that those states have means that are statistically significantly different from zero. I can't see how this would be a problem, either.