K-Centres Functional Clustering: A Person-Centered Approach to Modeling Complex Nonlinear Growth Trajectories. (October 2018)

• Record Type: Journal Article
• Authors: Hofmans, Joeri; Vantilborgh, Tim; Solinger, Omar N.
• Other Names: Morin Alexandre J. S. guest-editor.; Bujacz Aleksandra guest-editor.; Gagné Marylène guest-editor.
• Is Part Of: Organizational research methods. Volume 21:Number 4(2018:Oct.)
• Page Start: 905
• Page End: 930
• Publication Date: 2018-10
• Subjects: functional data analysis -- functional principal component analysis -- functional clustering -- psychological contract breach -- organizational commitment; Organization -- Research -- Methodology -- Periodicals; Organizational sociology -- Research -- Methodology -- Periodicals; Management -- Research -- Methodology -- Periodicals; 302.350721
• DOI: 10.1177/1094428117725793
• Languages: English
• ISSNs: 1094-4281

Abstract

In the present paper, we introduce k -centres functional clustering ( k -centres FC), a person-centered method that clusters people with similar patterns of complex, highly nonlinear change over time. We review fundamentals of the methodology and argue how it addresses some of the limitations of the traditional approaches to modeling repeated measures data. The usefulness of k -centres FC is demonstrated by applying the method to weekly measured commitment data from 109 participants who reported psychological contract breach events. The k -centres FC analysis shows two substantively meaningful clusters, the first cluster showing reaction patterns with general growth in commitment after breach and the second cluster showing general decline in commitment after breach. Further, the reaction patterns in the second cluster appear to be the result of a combination of two interesting reaction logics: immediate and delayed reactions. We conclude by outlining how future organizational research can incorporate this methodology.