典型相關分析主要研究兩組變項間的相關，為多變量統計方法中之一種，它包含 了母數統計與無母數統計法（卡方分析），換言之，其他母數統計法均為典型相關分析的特 例。利用典型相關分析有助於學生瞭解，所有母數統計法均運用加權方式形成線性組合分數 ，而線性組合分數為分析的焦點所在。本文旨在運用實際研究資料，說明用典型相關分析所 得之結果，與用（一）簡單相關、（二）t檢定、（三）二因子變異數分析、（四）單因子 共變數分析、（五）單因子多變量變異數分析、（六）二因子多變量變異數分析、（七）多 元迴歸分析、（八）區別分析與（九）卡方分析等之結果相同，更可瞭解典型相關分析與其 他統計方法間之關係。

　　　　　Canonical correlation analysis explores the relationship between two sets of variables. It is a sophisticated multivariate technique that subsumes all parametric methods. In other words, all parametric methods are special cases of canonical correlation analysis. The instruction of canonical correlation analysis facilitates students to see that all parametric methods involve the creation of synthetic scores for each subject. The synthetic scores are the focus for analysis. The purpose of the present paper is to employ a real data set to demonstrate how canonical correlation analysis yields results the same as those results from other parametric methods. The parametric methods used in this paper are as follows: (1) Pearson product-moment correlation; (2) t-test; (3) two-way analysis of variane; (4) one-way analysis of covariance; (5) one-way multivariate analysis of variance; (6) two-way multivariate analysis of variance; (7) multiple regression analysis; (8) discriminant analysis; (9) chi-square test (nonparemetric method).