The Spatial Representation of the Determinants of Customer Satisfaction: a Latent Structure Multidimensional Scaling Approach

EXTENDED ABSTRACT - Customer satisfaction has become a well-studied construct in marketing given its importance and established relationship with customer retention and firm profitability (e.g., Anderson, Fornell, and Lehmann1994). There is a rich literature concerning the determinants of customer satisfaction judgments, mostly from an aggregate market perspective (e.g., Mittal, Toss, and Baldasare 1998; Oliver 1980; Spreng, MacKenzie, and Olshavsky 1996). Such studies focus upon the impacts of various response determinants (e.g., performance, expectation, disconfirmation, attribution, equity, etc.) on satisfaction judgments, and report that these impacts on satisfaction are heterogeneous and are often dependent upon the product/service class under investigation. For example, Churchill and Surprenant (1982) find that for non-durable products, both expectation and disconfirmation have significant impact on satisfaction. However, for durable products, neither expectation nor disconfirmation has a significant impact.

Citation:

Jianan Wu, Wayne S. DeSarbo, Pu-Ju Chen, and Yao-Yi Fu (2002) ,"The Spatial Representation of the Determinants of Customer Satisfaction: a Latent Structure Multidimensional Scaling Approach", in AP - Asia Pacific Advances in Consumer Research Volume 5, eds. Ramizwick and Tu Ping, Valdosta, GA : Association for Consumer Research, Pages: 22-23.

Asia Pacific Advances in Consumer Research Volume 5, 2002      Pages 22-23

THE SPATIAL REPRESENTATION OF THE DETERMINANTS OF CUSTOMER SATISFACTION: A LATENT STRUCTURE MULTIDIMENSIONAL SCALING APPROACH

Jianan Wu, Tulane University, USA

Wayne S. DeSarbo, The Pennsylvania State University, USA

Pu-Ju Chen, The Pennsylvania State University, USA

Yao-Yi Fu, California State University, USA

EXTENDED ABSTRACT -

Customer satisfaction has become a well-studied construct in marketing given its importance and established relationship with customer retention and firm profitability (e.g., Anderson, Fornell, and Lehmann1994). There is a rich literature concerning the determinants of customer satisfaction judgments, mostly from an aggregate market perspective (e.g., Mittal, Toss, and Baldasare 1998; Oliver 1980; Spreng, MacKenzie, and Olshavsky 1996). Such studies focus upon the impacts of various response determinants (e.g., performance, expectation, disconfirmation, attribution, equity, etc.) on satisfaction judgments, and report that these impacts on satisfaction are heterogeneous and are often dependent upon the product/service class under investigation. For example, Churchill and Surprenant (1982) find that for non-durable products, both expectation and disconfirmation have significant impact on satisfaction. However, for durable products, neither expectation nor disconfirmation has a significant impact.

Even within a specific product or service, the salience or impact of these various determinants on satisfaction is heterogeneous. The marketing literature has attributed the heterogeneity of determinant impact on customer satisfaction predominately to two sources. First, observed heterogeneity may arise from individual consumer differences. For instance, Oliver and DSarbo (1988), using a manipulated experimental study on stock transactions, found three different clusters/segments of customers: 1) a performance and disconfirmation oriented cluster; 2) a disconfirmation oriented cluster; and 3) an equity oriented cluster. A more recent study on automobile tire quality by Kopalle and Lehmann (2001) suggests that consumers are heterogeneous with respect to disconfirmation sensitivity, that is, the impact of disconfirmation on overall satisfaction is high for some consumers, but low for others. Second, observed heterogeneity may arise from customers’ evaluations on multiple attributes of a product, or from multiple transactions/experiences with the product or service. For example, Mittal et al (1998) found that mixed evaluations toward a product or service are commonly observed phenomena. A customer can be both satisfied and dissatisfied with different aspects of the same product or service. For example, in a restaurant setting, a customer may simultaneously be highly satisfied with the food, but highly dissatisfied with the customer service provided.

Such studies contribute significantly to our understanding of the salience of the various response determinants on overall customer satisfaction judgments. However, they suffer from a common limitation, that is, they each address only one source of heterogeneity, and remain silent on the other. In reality, both of these sources are potentially important. On the one hand, attribute performance is essential in the measurement of customer satisfaction. For marketers, it is at the attribute level that they must make strategic decisions (Mittal et al 1998). For customers, they are more likely to render evaluations of their post-purchase experiences of satisfaction at an attribute level rather than at the product/service level (Westbrook and Oliver 1991). This fact is why most applied satisfaction studies frequently assess evaluations of determinants of the satisfaction (e.g., performance, expectation, disconfirmation, etc.) at the attribute level, rather than at the product level. On the other hand, consumers may differ in their evaluation of different attributes. As discussed in the restaurant setting, a satisfied aspect of a product or service for one customer can also be the dissatisfied aspect for another customer for the same product. With two people dinning in the same restaurant, one may be satisfied with both the food and the services, while the other may be satisfied with the services but dissatisfied with the food.

In this article, we propose a new latent structure MDS model that jointly represents both types of heterogeneity in such customer satisfaction studies. This proposed spatial methodology constitutes a methodological contribution to the marketing and statistics literatures in several ways. First, our model accommodates both sources of customer heterogeneity by jointly considering heterogeneity (at the derived market segment level) stemming from both individual customer differences and differing attribute performance. Compared to Oliver and DeSarbo (1988), our proposed latent structure MDS model has three important advantages: 1) the model does not require repeated measures from each consumer; 2) the proposed latent structure methodology is the only one in existence that is satisfaction theory based, unlike the cluster analysis utilized there; and, 3) our latent mixture specification makes the estimation of our model more efficient than the two-step method employed in their approach (cf. DeSarbo, Manrai, and Manrai 1994 for a critique of such two-step nanve approaches). Finally, an application to consumer trade show satisfaction data is presented.

REFERENCES

Anderson, Engene W., Claes Fornell, and Donald R. Lehmann (1994), "Customer Satisfaction, Market Share, and Profitbility: Findings From Sweden," Journal of Marketing, 59 (July), 53-66.

Churchill, A. Gilbert Jr. and Carol Surprenant (1982), "An Investigation Into the Determinants of Customer Satisfaction," Journal of Marketing Research, 19 (November), 491-504.

DeSarbo, S. Wayne, Ajay K. Manrai and Lalita A. Manrai (1994)," Latent Class Multidimensional Scaling: A Review of Recent Developments in the Marketing and Psychometric Literature," in Advanced Methods of Marketing Research, ed. R. P. Bagozzi, Oxford: Blackwell.

Kopalle, Praveen K. and Donald R. Lehmann (2001), "Strategic Management of Expectations: The Role of Disconfirmation Sensitivity and Perfectionism," Journal of Marketing Research, XXXVIII (August), 386-394.

Oliver, Richard(1980), "A Cognitive Model of the Antecedents and Consequences of Satisfaction Decisions," Journal of Marketing Research, 17 (November), 460-469.

Oliver, Richard and Wayne S. DeSarbo (1988), " Response Determinants in Satisfaction Judgements," Journal of Consumer Research, 14 (March), 495-507.

Mittal, Vikas, William T. Toss, Jr., and Patrick M. Baldasare (1998), "The Asymmetric Impact of Negative and Positive Attribute-Level Performance on Overall Satisfaction and Repurchase Intentions," Journal of Marketing, 62 (January), 33-47.

Spreng, Richard A., Scott B. MacKenzie, and Richard W. Olshavsky (1996), "A Reexamination of the Determinants of Consumer Satisfaction," Journal of Marketing, 60 (July), 15-32.

Westbrook, Robert A. and Richard L. Oliver (1991), "The Dimensionality of Consumption Emotion Patterns and Customer Satisfaction," Journal of Consumer Research, 18 (1), 84-91.

----------------------------------------