CONSTRUCTING JOB FAMILIES: AN ANALYSIS OF QUANTITATIVE TECHNIQUES USED FOR GROUPING JOBS
通过蒙特卡洛模拟研究，比较了多种定量分组策略在将工作归入工作族时的准确性，发现Q型因子分析和混合技术比传统层次聚类更稳健。
A Monte Carlo study was conducted to examine the performance of several quantitative grouping strategies for the purpose of grouping jobs into job families. Two factors were found to substantially affect the accuracy of these grouping strategies in terms of identifying the correct number of families, and accurately classifying jobs into those families. Through simulation of job analysis data sets designed to reflect various underlying structures among a set of jobs, it was found that techniques based on the commonly used hierarchical cluster analysis model were relatively inaccurate when applied to data containing measurement error or overlap between job families. Alternatively, Q‐type factor analysis and hybrid techniques involving a combination of factor and cluster analysis proved to be viable and robust grouping strategies for job classification research.