A LATENT LOOK AT EMPIRICAL GENERALIZATIONS

All empirical data and the resulting parameters are subject to error. In this paper we explicitly use the standard, but hardly profound, ''m odel'' Observed Value = True Score + Error as a lens for better viewin g empirical studies in search of empirical generalizations in marketin g. This lens is especially valuable when the unit of analysis is the i ndividual consumer. However, even when a macro study contrasts price e lasticities across cities, this O = T + E framework can be very helpfu l.