Recent single-source analyses have shed new light on the media constru
ct '' effective frequency.'' These contingency table investigations es
tablish a relation between recent advertising exposure and brand choic
e, which can be misleading. Rich single-source data demands multivaria
te techniques that include other key variables like weight of category
purchases and viewing, category seasonality, brand loyalty, competito
rs' advertising, advertising decay rates, and response to brand advert
ising. The authors' analyses of single-source data suggest that other
considerations-the decay rate of advertising effects, market and media
cost seasonality-should have equal, if not greater importance, than t
he response function or effective frequency in scheduling television c
ampaigns.