探索性因素分析因子抽取方法的比较

探索性因素分析决定因子抽取的方法主要有Bartlett法、K1原则、碎石检验法、Aaker原则、PA、MAP等六种，通过对样本1的395名大学生的学习过程问卷调查获得真实数据，运用这六种方法进行因素分析分别抽取7、4、2、4、3、2个因子；应用样本2的383名大学生的问卷调查数据进行验证性因素分析，结果显示，碎石检验方法与MAP方法抽取的二因素模型更理想。研究表明，因子抽取需兼顾“简约性原则”与“完备性原则”，同时要根据一定的理论建构、专业知识和经验来决定因子数。

The Comparison of Factor Retaining Methods in Exploratory Factor Analysis

Generally, six statistical methods are used for determining the number of factors to be retameu m exptoratory factor analysis： Bartlettx^2 Principal, K1 Rule, the Scree Test, Aaker Rule, Parallel Analysis and Minimum Average Partial Method. In this article, six methods retain seven, four, two, four, three and two factors respectively from real data of study process questionnaire inventory in sample one including 395 college students. Confirmatory factor analysis using sample 2 of 383 college students indicates the two - factor model from the Scree Test and Minimum Average Partial Method and is the fit model. Retaining factors need consider parsimony and completeness principles. Moreover, the decision of factorial number should rely on theoretical construction, specifically knowledge and experience.