The Specification of Aggregate Market Models
- 1 February 1987
- journal article
- review article
- Published by Emerald Publishing in European Journal of Marketing
- Vol. 21 (2) , 5-47
- https://doi.org/10.1108/eum0000000004681
Abstract
The adoption of a model‐building approach to marketing is today inevitable, due to improvements in hardware and software and the increased professionalisation of marketing and its techniques. Aggregate response models are focused upon, particularly the issues of which responses are realistic and should be modelled, how the response can be expressed and how a choice can be made between options available. The traditional model‐building process is described, and the inclusion of correct variables found to be critical, the primary means of doing this being statistical analysis. Simple expressions perform as effectively as more complex ones, and should be used if able to give operationally meaningful results. Cross‐correlation analysis and biased estimation techniques provide good guides to usable variables and their effects.Keywords
This publication has 97 references indexed in Scilit:
- Using Ridge Regression to Estimate Directly Lagged Effects in MarketingJournal of the American Statistical Association, 1981
- A Study of Marketing GeneralizationsJournal of Marketing, 1980
- Territory Sales ResponseJournal of Marketing Research, 1979
- Biased Estimation in Regression: An Evaluation Using Mean Squared ErrorJournal of the American Statistical Association, 1977
- Identification of Dynamic Regression (Distributed Lag) Models Connecting Two Time SeriesJournal of the American Statistical Association, 1977
- Checking the Independence of Two Covariance-Stationary Time Series: A Univariate Residual Cross-Correlation ApproachJournal of the American Statistical Association, 1976
- Comparing the Box-Jenkins Approach with the Exponentially Smoothed Forecasting Model Application to Hawaii TouristsJournal of Marketing Research, 1975
- Latent Root Regression AnalysisTechnometrics, 1974
- A Generalized Logistic Function with an Application to the Effect of AdvertisingJournal of the American Statistical Association, 1973
- Investigating Causal Relations by Econometric Models and Cross-spectral MethodsEconometrica, 1969