This article is a critique of reported analyses relating market shares to both advertising expenditure and measures of the Schwerin system of testing TV commercials. Technical difficulties are found with the particular data and analyses procedures, and with the claimed interpretations. The observed association between the Schwerin test measures and market shares is weak, and quite generally the broad kind of data analysed is irrelevant to the question of whether the Schwerin system is valid or not.
Get full access to this article
View all access options for this article.
References
1.
BuzzellR. D., “Predicting Short-Term Changes in Market Share as a Function of Advertising Strategy,” Journal of Marketing Research, 1 (August 1964), 27–31.
2.
BuzzellR. D., and KolinMarshall, “Competitive Preference and Sales Effectiveness,” New York: The Schwerin Research Corporation, September 1964.
3.
DoddA. R. and KellyP. J., “New Study Tells TV Advertisers How Advertising Builds Sales and Share of Market,” Printers Ink, (May 1964), 27–38.
4.
EhrenbergA. S. C., “Bivariate Regression Analysis is Useless,” Applied Statistics, 12 (September 1963), 161–79.
5.
FerberRobert, “Are Correlations any Guide to Predictive Value?” Applied Statistics, 5 (June 1956), 113–21.
6.
MurphyM. P. and BuzzellR. D., “How Advertising Creative Strategies Influence Sales Results,” paper read at the A.N.A. Workshop on Advertising and Planning Evaluation, New York, December 5, 1963.
7.
MurphyM. P., “The Conceptual Basis of the Schwerin Advertising Effectiveness Model,” and “The Multiple Correlation Model and its Application in Seven Product Fields,” papers read at the Operations Research Workshop of the Advertising Research Foundation, New York, November 7, 1963.
