主成分分析を用いた集団のグルーピング

抄録

This research proposed a new method of grouping of people after principal component analysis. First, we show that the scale of the normalized principal component scores is dependent on the number of the variables so that it is difficult to compare many results with each other. We proposed to renormalize principal component scores by two ways in grouping of the members in two-dimensional map. One is grouping of individuality, the other is grouping of selecting specially outlier. The nine classified areas can be given meaning. This method is an excellent way to classify all people according to their tendencies or to select extreme people based on rules. The advantage of this method is that no one is left out in the classification, and the classification is calculated automatically. The meaning of the axis is absolute and the comparison can be made in various mapping of any data.