ABSTRACT
The estimation of and inference from the regression model depend on several assumptions. These assumptions should be checked using regression diagnostics before using the model in earnest. We divide the potential problems into three categories: Error We have assumed that ε∼ N(0,σ2I) or in words, that the errors are indepen-
dent, have equal variance and are normally distributed. Model We have assumed that the structural part of the model, Ey = Xβ, is correct. Unusual observations Sometimes just a few observations do not fit the model.
