Latent Growth Curve Modeling of the Relationships Among Revenue, Loyalty, and Customer Satisfaction By Generalized Structured Component Analysis (Gsca)

EXTENDED ABSTRACT - Many practitioners and academics alike presume that satisfaction leads to loyalty and because loyal consumers are less costly to do business with, revenues increase; and this, in turn, leads to higher profits (Yeung and Ennew 2001). Despite the intuitive appeal of this claim, results from past studies on the effects of satisfaction on performance have tended to be mixed and often conflicting. Bernhardt et al. (1999) attribute this phenomenon to a reliance on cross-sectional data (e.g., Rust and Zahorik 1993; Rust, Zahorik, and Keiningham 1995; for notable exceptions, see Anderson, Fornell, and Lehmann 1994; Bernhardt et al. 1999). The primary purpose of this paper is to empirically demonstrate systematic links between customer satisfaction, loyalty, and annual revenue in a longitudinal and causal manner.



Citation:

Heungsun Hwang, Youngchan Kim, and Marc A. Tomiuk (2005) ,"Latent Growth Curve Modeling of the Relationships Among Revenue, Loyalty, and Customer Satisfaction By Generalized Structured Component Analysis (Gsca)", in AP - Asia Pacific Advances in Consumer Research Volume 6, eds. Yong-Uon Ha and Youjae Yi, Duluth, MN : Association for Consumer Research, Pages: 215-217.

Asia Pacific Advances in Consumer Research Volume 6, 2005      Pages 215-217

LATENT GROWTH CURVE MODELING OF THE RELATIONSHIPS AMONG REVENUE, LOYALTY, AND CUSTOMER SATISFACTION BY GENERALIZED STRUCTURED COMPONENT ANALYSIS (GSCA)

Heungsun Hwang, HEC Montreal, Canada

Youngchan Kim, Yonsei University, Korea

Marc A. Tomiuk, HEC Montreal, Canada

EXTENDED ABSTRACT -

Many practitioners and academics alike presume that satisfaction leads to loyalty and because loyal consumers are less costly to do business with, revenues increase; and this, in turn, leads to higher profits (Yeung and Ennew 2001). Despite the intuitive appeal of this claim, results from past studies on the effects of satisfaction on performance have tended to be mixed and often conflicting. Bernhardt et al. (1999) attribute this phenomenon to a reliance on cross-sectional data (e.g., Rust and Zahorik 1993; Rust, Zahorik, and Keiningham 1995; for notable exceptions, see Anderson, Fornell, and Lehmann 1994; Bernhardt et al. 1999). The primary purpose of this paper is to empirically demonstrate systematic links between customer satisfaction, loyalty, and annual revenue in a longitudinal and causal manner.

In essence, the proposed model hypothesized an indirect link between satisfaction and revenue with loyalty as a mediator of this relationship. Five manifest variables measured across 83 US companies were used: Customer satisfaction in 1994 (CS_94), loyalty in 1994 (Loyalty_94), as well as three measures of annual revenue from 1994 to 1996 (Rev_94, Rev_95, and Rev_96). Customer satisfaction and loyalty scores for the 83 companies were measured on the basis of the American Customer Satisfaction Index (Fornell et al. 1996).

Latent growth curve modeling (Meredith and Tisak 190) was applied to this data. The model was first estimated under a covariance structure framework. However, a Heywood case appeared after estimation (see Bollen, 1989) and rendered respecification problematic. In order to avoid the improper solution encountered in the previous analysis, the use of Partial Least Squares (PLS, Wold 1966, 1973) was entertained. When compared to covariance structure analysis, PLS estimation has been presented as the method of choice for predictive purposes (see Joreskog and Wold 1982). It has been also strongly recommended as a method for estimating Consumer Satisfaction Index (CSI) models because it is not subjected to the strict assumptions about data which underlie the use of covariance structure analysis (Fornell 1992; Fornell and Cha 1994). The major limitation of PLS lies perhaps in that it does not solve a global optimization problem for parameter estimation (Fornell and Bookstein 1982; Joreskog and Wold 1982). This means that there exists no criterion consistently minimized or maximized to determine the estimates of model parameters. The lack of a global optimization criterion makes it difficult to evaluate the overall goodness of fit of the specified model. On the other hand, one of the principal objectives of using latent growth curve models is to choose an optimal temporal pattern of change on a longitudinal variable (McArdle and Bell 2000). To decide on the optimal pattern of change over time, it is necessary to look into the overall goodness of fit of the specified latent growth curve model. This also allows for comparisons among competing models involving different temporal patterns. Thus, PLS may not be an attractive alternative for latent curve modeling because of the difficulty of assessing overall model fit.

Next, it was decided to estimate the model with Generalized Structured Component Analysis (GSCA) (Hwang and Takane in press), a recently proposed method for path analysis with latent variables. GSCA was developed as an alternative to PLS. It defines latent variables as linear combinations of observed variables as in PLS. However, unlike PLS, it provides a global least squares optimization criterion, which is consistently minimized to obtain parameter estimates. The method thus enables the calculation of an overall measure of model fit called EV (Explained Variance) while fully maintaining all the advantages of PLS such as less restricted distributional assumptions, no improper solutions, and unique latent score estimates. As such, GSCA was deemed a suitable alternative to both covariance structure analysis and partial least squares for fitting the specified latent curve model.

GSCA estimation revealed that the specified model fitted the data quite well. Nevertheless, for a more rigorous model evaluation procedure, the specified model was compared to two alternate models: One assumed no time-specific trend or stability, and the other assumed a quadratic trend of change across the three measures of annual revenue. In both alternate models, loyalty had direct effects on all temporal patterns in annual revenue and customer satisfaction had a direct effect on loyalty. After an examination of the goodness-of-fit indices, it was difficult to ascertain whether the linear-trend model was most appropriate because the two alternate models also fitted the data well. Hence, further evaluation appeared necessary so as to ascertain whether the three models were significantly different with respect to their goodness of fit.

Next, the mean differences in EV, the goodness of fit measure, were compared between the fitted models. EV is an absolute index that directly provides certain information about the closeness between the data and a hypothesized model; and this enables comparisons. It was found that there was a significant mean difference between the stability and linear-trend models while there was no significant mean difference between the linear-trend and the quadratic-trend models. This indicated that the linear-trend model (i.e. the model originally proposed) provided a significantly better fit than the stability model while providing essentially the same fit as the quadratic-trend model. Therefore, it was deemed prudent and reasonable to select the linear-trend model as the final model for the data.

In sum, the latent growth curve model estimated by GSCA demonstrated that satisfaction positively impacts financial performance (annual revenue) over time through loyalty. In fact, loyalty appears to play a pivotal role in the model and it is clear that both satisfaction and loyalty are closely related as indicated in Oliver (1999).

To conclude, this study rejoins a few others that have used longitudinal data in an effort to demonstrate the impact of satisfaction on economic and financial performance measures. However, some unique contributions delineate it from others. In particular, a causal approach (latent curve modeling) was adopted here and this appears to have finally provided robust and convincing evidence for the widely held, but seemingly anecdotal, beliefs of practitioners and academics. Moreover, the recently proposed method of GSCA (Hwang and Takane, in press) did a good job at circumventing some of the problems associated with the analysis of covariance structures as well as PLS.

REFERENCES

Anderson, E. W., C. Fornell, and S. Mazvancheryl, (under review), "Customer Satisfaction and Shareholder Value," Journal of Marketing.

Anderson, E. W. and C. Fornell (2000), "Foundations of the American Customer Satisfaction Index," Journal of Total Quality Measurement, 11(7), S869-S882.

Anderson, E. W., C. Fornell, and R. T. Rust (1997), "Customer Satisfaction, Productivity, and Profitability: Differences Between Goods and Services," Marketing Science, 16(2), 129-45.

Anderson, E. W., C. Fornell, and D. R. Lehman (1994), "Customer satisfaction, Market Share, and Profitability: Findings from Sweden," Journal of Marketing, 58(July), 53-66.

Anderson, J. C., and D. Gerbing (1984), "The Effect of Sampling Error on Convergence, Improper Solutions, and Goodness-of-Fit Indices for Maximum Likelihood Confirmatory Factor Analysis," Psychometrika, 49, 155-173.

Arbuckle, J. L. (1999), Amos User’s Guide: Version 4.01. Chicago, IL: Small Waters.

Bentler, P. M., and D. G. Bonett (1980), "Significance Tests and Goodness of Fit in the Analysis of Covariance Structures," Psychological Bulletin, 88, 588-606.

Bernhardt, K. L., N. Donthu, and P. A. Kennett (2000), "A Longitudinal Analysis of Satisfaction and Profitability," Journal of Business Research, 47, 161-171.

Bollen, K. A. (1989), Structural Equations with Latent Variables. New York: Wiley.

Cassel, C., P. Hackl, and A. H. Westlund (2000), "On Measurement of Tangible Assets: A Study of Robustness of Partial Least Squares," Total Quality Management, 11, 897-907.

Chen, F., K. Bollen, P. Paxton, P. J. Curran, and J. Kirby (2001), "Improper Solutions in Structural Equation Models: Causes, Consequences, and Strategies," Sociological Methods and Research, 29, 468-508.

de Leeuw, J., F. W. Young, and Y. Takane (1976), "Additive Structure in Qualitative Data: An Alternating Least Squares Method with Optimal Scaling Features," Psychometrika, 41, 471-503.

Duncan, T. E., S. C. Duncan, L. A. Strycker, F. Li, and A. Alpert (1999), An Introduction to Latent Variable Growth Curve Modeling. New Jersey: Lawrence Erlbaum Associates.

Efron, B. (1982), The Jackknife, The Bootstrap and Other Resampling Plans. Philadelphia: SIAM

Fornell, C. (1992), "A National Customer Satisfaction Barometer: The Swedish Experience," Journal of Marketing, 56, 6-21.

Fornell, C., and F. L. Bookstein (1982), "Two Structural Equation Models: LISREL and PLS Applied to Consumer Exit-Voice Theory," Journal of Marketing Research, 19, 440-452.

Fornell, C., and J. Cha (1994), "Partial Least Squares", in Advanced Methods of Marketing Research, R. P. Bagozzi, ed. Oxford: Blackwell, 52-78.

Fornell, C., M. D., E. W. Johnson, J. Anderson, J. Cha, and B. E. Bryant (1996), "The American Customer Satisfaction Index: Nature, Purpose, and Findings," Journal of Marketing, 60, 7-18.

Fornell, C., and W. Wernerfelt (1988), "A Model for Customer Complaint Management," Marketing Science, 7(3), 287-98.

Fornell, C., and W. Wernerfelt (1987), "Defensive Marketing Strategy by Customer Complaint Management: A Theoretical Analysis", Journal of Marketing Research 24(4), 337-46.

Gerbing, D. W., and J. C. Anderson (1987), "Improper Solutions in the Analysis of Covariance Structures and a Comparison of Alternate Respecifications," Psychometrika, 52, 99-111.

Hwang, H., and Y. Takane (in press), "Generalized Structured Component Analysis," Psychometrika.

Ittner, C. D. and D. F. Larker (1998), "Are Nonfinacial Measures Leading Indicators of Financial Performance ? An Analysis of Customer Satisfaction," Journal of Accounting Research, 36, Supplement, 1-35.

Joreskog, K. G. and H. Wold (1982), "The ML and PLS Techniques for Modeling with Latent Variables: Historical and Comparative Aspects," in Systems under Indirect Observation: Causality, Structure, Prediction, I, H. Wold and K. G. Joreskog, eds. Amsterdam: North-Holland, 263-270.

Jusko, J. (1999), "Tried and True," Industry Week, 248(22), 78-84.

Kristensen, K., A. Martensen, and L. Gr°noldt (1999), "Measuring the Impact of Buying Behavior on Customer Satisfaction," Total Quality Management, 10, 602-614.

Martensen, A., L. Gronholdt, and K. Kristensen (2000), "The Drivers of Customer Satisfaction and Loyalty, Cross-Industry Findings From Denmark," Total Quality Management, 11, 8544-8533.

McArdle, J. J., and R. Q. Bell (2000), "Recent Trends in Modeling Longitudinal Data by Latent Growth Curve Methods," in Modeling longitudinal and multiple-group data, T. D. Little, K.U. Schnabel and J. Baumert, eds. Mahwah, NJ: Erlbaum.

Meredith, W. and J. Tisak (1990), "Latent curve analysis," Psychometrika, 55, 107-122.

Nelson, E. C., R. T. Rust, A. Zahorik, R. L. Rose, P. Batalden, and B. A. Siemanski (1992), "Do Patient Perceptions of Quality Relate to Hospital Financial Performance?," Journal of Health Care Marketing, December, 6-13.

Oliver, R. L. (1999) "Whence Consumer Loyalty," Journal of Marketing, 63(Special issue), 33-44.

Oliver, R. L. (1996), Satisfaction: A Behavioral Perspective on the Consumer. Boston, MA: Irwin-McGraw-Hill.

Reichheld, F. E. (1996), The Loyalty Effect: The Hidden Force Behind Growth, Profits, and Lasting Value. Harvard Business School Press. Boston, MA.

Reichheld, F. E., and W. E. Sasser (1990), "Zero Defections: Quality Comes to Services," Harvard Business Review, 68, 105-111.

Rust, R. T., and A. J. Zahorik (1993), "Customer Satisfaction, Customer Retention, and Market Share," Journal of Retailing, 69(Summer), 193-215.

Rust, R. T., A. J. Zahorik, and T. Keiningham (1995), "Return on Quality (ROQ): Making Service Quality Financially Accountable," Journal of Marketing, 59, 58-70.

Schneider, B. (1991), "Service Quality and Profits: Can You Have Your Cake and Eat it Too," Human Resource Planning, 14, 151-157.

Shoultz, D. (1989), "Service Firms are Customer Driven: Study," American Banker, February 23, 17-18.

Tornow, W. W., and J. W. Wiley (1991), "Service Quality and Management Practices: A Look at Employee Attitudes, Customer Satisfaction, and Bottom Line Consequences," Human Resource Planning, 14, 105-115.

Wiley, J. W. (1991), "Customer Satisfaction: A Supportive Work Environment and Its Financial Costs," Human Resource Planning, 117-127.

Wold, H. (1966), "Estimation of Principal Components and Related Methods by Iterative Least Squares," in Multivariate Analysis, P. R. Krishnaiah, ed. New York: Academic Press, 391-420.

Wold, H. (1973), "Nonlinear Iterative Partial Least Squares (NIPALS) Modeling: Some Current Developments," in Multivariate Analysis, P. R. Krishnaiah, ed. New York: Academic Press, 383-487.

Yeung, M. C. H., and C. T. Ennew (2001), "Measuring the Impact of Customer Satisfaction on Profitability: A Sectoral Analysis," Journal of Targeting, Measurement, and Analysis for Marketing, 10(2), 106-116.

Zahorik, A. J., and R. T. Rust (1992), "Modeling the Impact of Service Quality Profitability, in Advances in Services Marketing and Management, JAI, Grennwich, CT.

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

Authors

Heungsun Hwang, HEC Montreal, Canada
Youngchan Kim, Yonsei University, Korea
Marc A. Tomiuk, HEC Montreal, Canada



Volume

AP - Asia Pacific Advances in Consumer Research Volume 6 | 2005



Share Proceeding

Featured papers

See More

Featured

Intentionally “Biased”: People Purposefully Use To-Be-Ignored Information, But Can Be Persuaded Not To

Berkeley Jay Dietvorst, University of Chicago, USA
Uri Simonsohn, University of Pennsylvania, USA

Read More

Featured

Cultivating Collaboration and Value Cocreation in Consumption Journeys

Melissa Archpru Akaka, University of Denver
Hope Schau, University of Arizona, USA

Read More

Featured

All We Need is Love: Examining Differences in Time and Money Donations between Dyads and Individuals

Hristina Nikolova, Boston College, USA

Read More

Engage with Us

Becoming an Association for Consumer Research member is simple. Membership in ACR is relatively inexpensive, but brings significant benefits to its members.