Hi,

I am estimating a model by FE and the constant I get is not close to the mean of my only explanatory variable, but when I run the same specification but using xtreg re for a Hausman test the constant is much closer to the mean. is this of any significance? and I am not quite sure what it means when the constant differs so much from the mean and if this might be an indicator of a problem?

any advice would be appreciated