On the Validity of Principal Component Analysis as a Method of Analysis of the Variations in Human Physique:Establishment of the Validity of Measurement Selection
スポンサーリンク
概要
- 論文の詳細を見る
In the previous paper 20 measurement items were selected on the basis of principal component analysis and cluster analysis of 44 somatic measurements taken from 112 young adult males for the purpose of obtaining an objective selection of somatometric measurement items (KOUCHI, 1979).In this paper, two analyses were carried out using Pearson's product moment and Spearman's rank correlation coefficients for the purpose of establishing the validity of this selection. First, the accordance between the matrices of inter-subject similarity coefficients obtained from the original set and from the selected set of measurements was examined using mean square distances, Penrose's size and shape distances and Q-mode correlation coefficients.Secondly, the accordance between the scores of six interpretable principal components obtained from the original set (O-scores) and from the selected set of measurements (S-scores) was examined.The results show that: 1) the informations contained in the original set as a whole is well represented by the selected set; 2) O-scores are satisfactorily represented by S-scores in six of the seven aspects. It is concluded that the validity of the selection is established because the informationscarried by the selected measurements satisfactorily represents the whole as well as six relatively independent aspects of the informations carried by the original set of measurements, and that S-scores may be used instead of O-scores as a convenient indicator.
- 日本人類学会の論文
日本人類学会 | 論文
- 静的姿勢の局所筋エネルギ-代謝量〔英文〕
- 局所筋エネルギ-代謝量の推定方法
- 寒冷適応に関する研究-1-心拍数変化および局所筋産熱の観点から
- 各種静的姿勢保持における筋活動量のエネルギ-代謝量及び拍数に及ぼす影響
- 現代ケニア人における抜歯風習