Cm. Schaffer et Pe. Green, AN EMPIRICAL-COMPARISON OF VARIABLE STANDARDIZATION METHODS IN CLUSTER-ANALYSIS, Multivariate behavioral research, 31(2), 1996, pp. 149-167
Citations number
13
Categorie Soggetti
Social Sciences, Mathematical Methods","Psychologym Experimental","Statistic & Probability","Mathematical, Methods, Social Sciences","Statistic & Probability","Mathematics, Miscellaneous
It is common practice in marketing research to standardize the columns
(to mean zero and unit standard deviation) of a persons by variables
data matrix, prior to clustering the entities corresponding to the row
s of that matrix. This practice is often followed even when the column
s are all expressed in similar units, such as ratings on a 7-point, eq
ual interval scale. This study examines six different ways of standard
izing matrix columns and compares them with the null case of no column
standardization. The analysis is replicated for ten large-scale data
sets, comprising derived importances of conjoint-based attributes. Our
findings indicate that the prevailing column standardization practice
may be problematic for some kinds of data that marketing researchers
use for segmentation. However, we also find that in the background dat
a profiling step, results are reasonably robust to column standardizat
ion method.