Sorting Out Sorts
21 Pages Posted: 2 Jul 1997
Date Written: June 1997
In this paper we analyze the theoretical implications of sorting data into groups and then running asset pricing tests within each group. We show that the way this procedure is currently implemented introduces a severe bias in favor of rejecting the model under consideration. Indeed, by simply picking enough groups even the true asset pricing model can be shown to have no explanatory power within each group. The implication is that potentially, it is the method of sorting the data, rather than the model itself, that is responsible for the negative results obtained by empiricists employing this procedure.
JEL Classification: C51, C52, G12
Suggested Citation: Suggested Citation