The authors investigate methods of evaluating marketing experiments in which the experimental territories have been determined a priori. Various matching and prediction schemes are offered to predict what sales in an experimental unit would have been if no experiment had been run. These schemes are developed for predictions of both single territory sales and total sales of groups of territories. A testing method for alternative schemes is described and applied to data for one specific firm.
Get full access to this article
View all access options for this article.
References
1.
BoxG. E. P., and TiaoG. C.“Intervention Analysis with Applications to Economic and Environmental Problems,”Journal of the American Statistical Association, 70 (March 1975), 70–3.
2.
ClellandW. P., and TiaG. L.“Decomposition of Seasonal Time Series: A Model for the Census X-11 Program,” Technical Report 332, Department of Statistics, University of Wisconsin, January 1974.
3.
RaiffaHoward, and SchlaiferRobert. “Applied Statistical Decision Theory.”Cambridge: MIT Press, 1961, 114–7.
4.
ShiskinJ., YoungA. H., and MusgraveJ. L.“The X-11 Variant of Census Method II Seasonal Adjustment Program,” Technical Paper No. 15, Bureau of the Census, U.S. Department of Commerce, 1967.
5.
WinklerRobert L.“Introduction to Bayesian Inference and Decisions.”New York: Holt, Rinehart & Winston, 1972, 363–4.
