3.1.3.2 Likely Sources of Heteroscedasticity For heteroscedasticity, it is likely to be a problem when the values of the variables in the sample vary substantially indifferent observations. Given that
, the variations in the omitted variables and the measurement errors that are jointly responsible for the disturbance term (u) would be somewhat small when Yand Xare small and large when they are large. This is simply because economic variables in such a true relationship tend to move in size together.
