[Gretl-users] Re: Normality, no autocorrelation, and no heteroscedasticity in Fixed-effect and Random-effects models
Am 19.01.2022 um 15:52 schrieb 3J LEMA:
What are the assumptions to be tested and reported when we use
Fixed-effect and Random-effects models? The same assumptions such as
normality, no autocorrelation, and no heteroscedasticity?
Hi, I would suggest to read chapters 23 and 24 of the gretl manual about
panel models and dynamic panel models. Plus perhaps some standard panel
econometric textbook. If you're then missing some kind of test in gretl
(or think that gretl carries out the wrong kind of test), please get
back with more specifics.
thanks
sven