Accounting for Unobserved Heterogeneity in the Analysis of Antecedents and Consequences of Corporate Reputation: An Application of FIMIX-PLS

Ringle, Christian M. ; Schloderer, Matthias P. and Schwaiger, Manfred (2008): Accounting for Unobserved Heterogeneity in the Analysis of Antecedents and Consequences of Corporate Reputation: An Application of FIMIX-PLS. 37th Annual Conference of the European Marketing Academy (EMAC), University of Brighton, Brighton, UK, 27–30 May 2008. In: Proceedings of the 37th Annual Conference of the European Marketing Academy (EMAC), pp. 1-9

Abstract

The following contribution presents a novel response-based approach, finite mixture partial least squares (FIMIX-PLS), with which to classify data based on the heterogeneity of the es-timates in the inner path model. Subsequently the approach is applied to a previous study by Eberl (2008) that analyses the stakeholder-specific relationships between customer satisfac-tion, customer loyalty and corporate reputation as well as its drivers. This new approach opens the way for reliable identification of distinctive customer segments and their character-istic estimates regarding the latent relationships between variables in the inner model. Our analysis demonstrates that an aggregate analysis can be seriously misleading and, thus, pro-vide a strong case for segment-specific reputation management analysis.

• Item Type: Conference or Workshop Item (Paper)
• Keywords: Partial Least Squares, Latent Classes, FIMIX-PLS, Corporate Reputation Track: Marketing Research and Research Methodology
• Faculties: Munich School of Management > Institute for Market-based Management
• Subjects: 300 Social sciences > 330 Economics
• Annotation: Erschienen als CD-ROM.
• Language: English