Often data for subsequent multivariate statistical analysis violate one or more of the assumptions upon which the technique is based. These violations can result in errors in structural interpretation and prediction. When these assumptions are not met, must one use a more complex statistical technique, or is there a way to get around the problem? Transformations help to expand the range of problems that a given technique can handle beyond what its assumptions would at first seem to permit. The author illustrates the principal types of transformations applied to model building in marketing.
Get full access to this article
View all access options for this article.
References
1.
DixonW. J. ed., BMD: Biomedical Computer Programs, Los Angeles, Calif: School of Medicine, University of California, January 1, 1964.
2.
FrankRonald E., “Store Location and Characteristic Analysis: A Progress Report,” Mimeographed, June 1963.
3.
FrankRonald E., and MassyWilliam F., “Market Segmentation and the Effectiveness of a Brand's Price and Dealing Policies,” Working Paper No. 3, Graduate School of Business, Stanford University, March 1964.
4.
MassyWilliam F., FrankRonald E., and LodahlThomas M., “Purchasing Behavior and Personality,” Working paper, forthcoming, Graduate School of Business, Stanford University, 1966.
5.
SnedecorGeorge W., Statistical Methods, Ames, Iowa: Iowa State College Press, 1956, 316–9.
6.
SpencerMilton H., ClarkColin G., and HougetPeter W., Business and Economic Forecasting, Homewood, Ill.: Richard D. Irwin, Inc., 1961.
7.
StoneJ. R. N., “The Measurement of Consumers’ Expenditure and Behavior in the United Kingdom, 1920 1938,”Cambridge, London, 1954.
