Imagine we have already built our linear regression model, with a certain dataset.
Which order of tests would you follow to be sure that whatever conclusions you may want to extract are correct. For example:
- In the beginning we may want to test for non-linearities not present in our model, but present in reality (model misspecification). For this objective, we could use RESET. What others can we use and why?
- Now we could want to test for heteroskedasticity(Breusch-Pagan and White's tests
- Endogeneity (Durbin-Wu-Hausman test)
Which 'game plan' do you use and why?