Ch03FactorAnalysis.pptVIP

Ch02 Factor Analysis;Stage 1: Objectives of FA;Stage 2: Designing a FA;2. The design of the study in terms of number of variables, measurement properties of variables, and the types of allowable variables Metric measurement In some cases, dummy variables can be used Boolean FA The strength of FA lies in finding patterns among groups of variables, and it is of little use in identifying factors composed of only a single variable.;3. The sample size necessary, both in absolute terms and as a function of the number of variables in the analysis Do not factor analyze a sample of fewer than 50 observations Preferably the sample size should be 100 or larger. The minimum: cases-per-variable ratio is at least 5. More acceptable size: a 10-to-1 ratio. The researcher should always try to obtain the highest cases-per-variable ratio to minimize the chances of overfitting the data.;Stage 3: Assumptions in FA;2. If “true” factors exist in the data, the partial correlation should be small, because the variable can be explained by the factors. If the partial correlations are high, then there are no “true” underlying factors, and the FA is inappropriate. 3. Larger partial or anti-image correlations are indicative of a data matrix perhaps not suited to FA.;4. The Bartlett test of sphericity: 变量间相关关系的检验 5. MSA (the measurement of sampling adequacy). 0-1. 1表示每个变量都可以由其他变量完美无误地predicted. 大于等于0.8: meritorious; 大于等于0.7: middling; 大于等于0.6: mediocre; 大于等于0.5: miserable; 小于0.5:　　 unacceptable. 要检查每个变量的MSA，把小于.5的去掉，再做FA。若有多个变量小于.5，则先去掉最小的一个，再做一次，看MSA和overall MSA.;Conceptual assumptions: Some underlying structure does exist in the set of selected variables. 把自变量和因变量放在一起做FA是不合适的。 The sample is homogeneous with respect to the underlying factor structure. 已知items对性别是差异的，而对男女样本的数据进行FA是不合适的。 样本中存在差异的组，应该分组做FA，然后比较结果，再去比较合并组的FA的结果。看差异的性质。;Stage 4: Deriving factors and assessing overall fit;选择标准： FA的目的 有关变量的事先知识 PCA合适： 目的：有关prediction或找到代表原变量集的方差最大部分的最少因子 事先知识：特殊的和误方差只占总方差