Abstract:

 

There are numerous techniques used to assess consumers’ motivations for product consumption. It is quite common to obtain data from rated degrees of agreement with statements about possible motivators. The responses are then analyzed using statistical tools such as the analysis of variance and factor analysis.

​

In this report we discuss a novel and complementary approach to these traditional statistical analyses. The concept underlying the method is that consumer motivations for using a product and consumer interpretation of statements of possible motivators co-exist in a joint space. As consumers answer questions about degrees of agreement with statements, they report degrees of similarity between their motivations for product use and their interpretation of the statements. Neither the statements themselves nor the consumers’ inferred motivations are treated as discrete points. They are represented by multivariate normal distributions to account for the fact that consumers are not equally certain about their motivations and do not agree perfectly on the meaning of the statements they evaluate. This probabilistic approach is consistent with techniques that we have previously described for a broad range of perceptual measurement methods.