The HEX-ACO-18: Developing an age-invariant HEXACO short scale using Ant Colony Optimization
Date created: | Last Updated:
: DOI | ARK
Creating DOI. Please wait...
Description: In this study, we developed an age-invariant 18-item short form of the HEXACO Personality Inventory for use in developmental personality research. We employed a combination of the model estimation approach local structural equation modeling (LSEM) and the item selection procedure ant colony optimization (ACO). LSEM allows for model estimation and measurement invariance testing across a continuous age variable by weighting participants based on their age, rather than splitting the sample into artificial age groups. ACO is a metaheuristic algorithm that selects and evaluates items based on the quality of the resulting short scale, thus allowing for the direct optimization of criteria that can only be estimated based on combinations of items, such as model fit and measurement invariance across age. Using a HEXACO-100 dataset of N = 6,419 participants ranging from 16 to 90 years of age, we selected a short form optimized for model fit, measurement invariance, facet coverage, and balance of item keying. The resulting HEX ACO 18 short scale showed adequate model fit, scalar measurement invariance across age, and covered three out of four facets from each HEXACO trait domain. Furthermore, the usefulness and versatility of the item and person sampling procedures ACO and LSEM is demonstrated. In this repository, you can find all R scripts we used for the analyses, as well as an overview on the results of the 20 ant colony runs. The overview shows the necessity to start several runs of ACO before selecting a solution, as the quality of the final solutions were highly variable between the different seeds. The data used for this study was obtained upon request from Kibeom Lee and Michael C. Asthon. We used a subsample of the data presented in: Lee, K., & Ashton, M. C. (2020). Sex differences in HEXACO personality characteristics across countries and ethnicities. Journal of personality, 88(6), 1075-1090. https://doi.org/10.1111/jopy.12551 GO had a lead role in writing the original draft and revision. KJ had a lead role in data analysis. Both had a equal role in the conceptualization of this study.