Examining heterogeneity through response-based unit segmentation in PLS-SEM: a study of human capital and firm performance in upscale restaurants

ABSTRACT

Response-based unit segmentation (REBUS) is an advanced partial least squares–structural equation modelling technique that clusters observations into classes based on the relationships among model constructs. In this paper, we demonstrate the application of REBUS in examining human capital (HC) and firm performance in the upscale restaurant sector – an important segment of gastronomic tourism in a destination. The model framework is developed from HC theory which posits individuals who develop higher levels of knowledge, skills, education and other competencies will outperform others [(Bruce, M., McNally, J. J., & Kay, M. (2013, March). Examining the formation of human capital in entrepreneurship: A meta-analysis of entrepreneurship education outcomes. Journal of Business Venturing, 28(2), 211–224; Mincer, J. (1958). Investment in human capital and personal income distribution. Journal of Political Economy, 66, 281–302)]. We operationalize HC to include operators’ (1) previous ownership/management experience, (2) level of education, (3) length of time in current position, (4) years spent in hospitality and (5) entrepreneurial qualifications and examine the structural effects on performance. Data were collected through telephone-based surveys of 308 restaurant operators in Australia and France. REBUS results found that the effects of HC on performance differed across identified segments from the data, presenting new insights on the complexity of the relationship and the presence of moderator effects.

KEYWORDS:

• Response-based unit segmentation
• PLS-SEM
• upscale restaurants
• human capital

Acknowledgements

The authors would like to thank Le Cordon Bleu Australia and the School of Management, University of South Australia, for providing the research funds for this project. We are also grateful to the restaurant operators who donated their time and participated in this study.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by Le Cordon Bleu Australia and School of Management, University of South Australia: [Grant Number LCB/UniSA Grant Scheme].