A Two-Step Analysis with Common Quantification of Categorical Data

Japan Women’s University Journal: Faculty of Integrated Arts and Social Sciences, 2015, 26, 99-112. (published in 2016.05)

Yasuharu Okamoto

Abstract

A data from a psychological research may contain categorical variables.

This study proposes to use common quantification of categorical variables for various analyses,

so that results from those analyses can be interpreted according to common quantification.

The proposed method consists of two steps.

In step 1, categorical variables are quantified independently of the subsequent analyses.

After quantification, in step 2, various analyses are conducted based on common quantification.

A hypothetical data set, including two categorical variables and one continuous variable, was prepared.

Categorical variables were quantified in step 1; then in step 2, using the quantification in step 1,

principal components, regression, and discriminant analyses were successfully conducted.