March 2019
Beginner to intermediate
448 pages
13h 14m
English
The Breusch-Pagan test works by regressing the squared residuals on the regressors used in the model. Under the null hypothesis, these regressors should not be relevant for explaining these squared values. If they are not, it means that the squared residuals depend on the regressor values; and what's the relationship between the squared residuals and the variance of the residuals? They are the same thing, because the expected value of the residuals is zero.
Read now
Unlock full access