Another look at Chow's test for the equality of two heteroscedastic regression models

This paper reviews tests of equality between the sets of coefficients in the two linear regression models, and examines the effect of heteroscedasticity in each model on the behaviour of one such test. A Monte Carlo evaluation, of the size in particular, shows that the usual Chow's F-ratio is well behaved as long as the sample sizes in the two models are equal and the two models exhibit the same form of heteroscedasticity which is moderate in the context of the values used. In such situations it is recommended that the test be used directly to avoid the extra efforts involved in transforming the original data in order to attain homoscedasticity.