Factor Analysis for Data Reduction

FACTOR ANALYSIS FOR DATA REDDUCTION

It is a common experience, for example, to find a marketing decision maker wondering what exactly makes a consumer buy his product. The possible purchasing criteria could range from just one or two to fifteen or twenty, and often, the marketing manager is shooting in the dark,, trying to figure out what really drives buyer behaviour. In other words, what are the underlying significant drivers of his behaviour? Factor analysis is a good way of resolving this confusion and identifying latent or underlying factors from an array of seemingly important variables. In a more general way, factors analysis is a asset of techniques which, by analysing correlations between variables, reduces their number into fewer factors which explain much of the original data, more economically. Even though a subjective interpretation can result from a factor analysis output, the procedure often provides an insight into relevant psychographic variables, and results in economical use of data collection efforts. The subjective element of factor analysis could be reduced by splitting the sample randomly into two, and extracting factors separately from both parts. If similar factors result, the analysis could be assumed as reliable or stable.

Other creative uses of factor analysis could be to do it separately for 2 groups such as users and non-users of a brand, and check what differences exist in the factors extracted, this would be an indirect way of finding out differences in buying criteria for the same product category among the two groups. Of course, if the objective is to classify a person by predicting whether he will be a buyer or non-buyer, the reader is advised to consider discriminant analysis instead of factor analysis.

Methods

There are two stages in factor analysis. Stage 1 can be called the factor Extraction process, where our objective is to identify how many factors will be extracted from the data. The most popular method for this is...