A unique form of a multivariate time series model—a “seemingly unrelated autoregressive moving average” model (SURARMA)—is developed in the context of forecasting unit sales of a product in four states. Data from an anonymous firm are used to test the appropriateness of the model and are found to conform to the model's constraints. The model provides substantial improvement in parameter estimation efficiency and forecast performance in comparison with individual state univariate models. SURARMA is potentially relevant to many market forecasting problems involving multiple constituent time series subunits such as states, regions, or products from a product line.
Get full access to this article
View all access options for this article.
References
1.
BassFrank M. and ParsonsLeonard J. (1969), “Simultaneous-Equation Regression Analysis of Sales and Advertising,” Applied Economics, 1 (May), 104–24.
2.
BeckwithNeil E. (1972), “Multivariate Analysis of Sales Responses of Competing Brands to Advertising,” Journal of Marketing Research, 9 (May), 168–76.
3.
BoxGeorge E. P. and JenkinsGwilym M. (1976), Time Series Analysis: Forecasting and Control, revised edition. San Francisco: Holden-Day..
4.
ClarkeDarral G. (1973), “Sales-Advertising Cross-Elasticities and Advertising Competition,” Journal of Marketing Research, 10 (August), 250–61.
5.
GeurtsMichael D. and IbrahimI. B. (1975), “Comparing the Box-Jenkins Approach with the Exponentially Smoothed Forecasting Model Application to Hawaii Tourists,” Journal of Marketing Research, 12 (May), 182–8.
6.
GrangerC. W. J. and NewboldPaul (1977), Forecasting Economic Time Series. New York: Academic Press, Inc.
7.
HelmerRichard M. and JohanssonJohny K. (1977), “An Exposition of the Box-Jenkins Transfer Function Analysis with an Application to the Advertising-Sales Relationship,” Journal of Marketing Research, 14 (May), 227–39.
8.
LeoneRobert P. (1979), “Constructing Models of Competition: An Alternative to Traditional Econometric Analysis,” Invited Paper, TIMS/Stanford Conference, Special Topics on Marketing Measurement and Analysis, March 1979.
9.
MaddalaG. S. (1977), Econometrics. New York: McGraw-Hill Book Company, 174–5.
10.
NaylerR. H., SeaksT. G., and WichernD. W. (1972), “Box-Jenkins Methods: An Alternative to Econometric Forecasting,” International Statistical Review, 40 (June), 123–37.
11.
NelsonCharles R. (1972), “The Prediction Performance of the FRB-MIT-Penn Model of the U.S. Economy,” The American Economic Review, 62 (December), 902–17.
12.
NelsonCharles R. (1976), “Gains in Efficiency from Joint Estimation of Systems of Autoregressive-Moving Average Processes,” Journal of Econometrics, 4 (July), 331–48.
13.
NewboldP. and GrangerC. W. J. (1974), “Experience with Forecasting Univariate Time Series and the Combination of Forecasts,” Journal of the Royal Statistical Society-Series A, 137, 131–46.
14.
QuenouilleM. H. (1975), Analysis of Multiple Time Series. London: Griffin.
15.
WildtAlbert R. (1974), “Multifirm Analysis of Competitive Decision Variables,” Journal of Marketing Research, 11 (February), 50–62.
16.
ZellnerArnold (1962), “An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias,” Journal of the American Statistical Association, 57 (June), 348–68.
17.
ZellnerArnold and PalmFranz (1974), “Time Series Analysis and Simultaneous Equation Econometric Models,” Journal of Econometrics, 2 (May), 17–54.
