I have been looking for a simple way to test if my tobit model (panel data) suffers from heteroskedasticity and non-normality, but I have only found very complicated ways to do this... Does anyone know if there is a more simple way to test this? It is optional for me to do these tests and that is why I am not keen to make the most complicated tests. I have made histograms, scatter plots, qnorm and pnorm for the residuals, however... I'm sure that this is not enough (or correct).
↧