因子分析模型及其Python/R实现
因子分析****基本思想
与主成分分析类似，在理论层面上而言，在理论层面而言，在理论层面而言
factor analysis is based on the assumption that a set of observed variables can be explained through a number of latent factors. To elaborate, for instance, consider a student's academic performance with scores such as 80 in Chinese, 95 in mathematics, 79 in English, 97 in physics, and 94 in chemistry. This suggests that the student possesses strong analytical thinking skills but has weaker language organization abilities. By identifying these latent factors—analytical thinking and language organization—we can observe that this student tends to excel in理科 subjects while finding文科 subjects challenging. This demonstrates how factor analysis operates differently from principal component analysis.
在研究领域中存在两种主要的方向：一种是探索性的因子分析（Exploratory Factor Analysis, EFA），另一种则是 confirmatory 因子分析（CFA）。在探索性的因子分析中无法预先确定一组潜在的公共因子数目；我们希望通过这种方法来识别这些潜在的公共因素。而验证性的因子分析则是基于某种理论模型假设一组潜在的公共因素数目，并通过该方法检验这些假设是否成立。需要注意的是，在进行验证性的因式分解时与结构方程模型有着密切的关系……后面我们会详细讲解这一部分内容，请关注后续文章。今天就让我们先了解一下探索性的因式分解吧！