Asymptotic Distributions and Confidence Intervals of Component Loading in Principal Component Analysis
作者： Shin-ichi Tsukada , Takakazu Sugiyama
DOI: 10.1007/978-4-431-66996-8_79
关键词:
摘要: In principal component analysis, it is quite useful to know the values of a correlation coefficient between and an original variable. We seek for knowing meaning each from their values. However, we do not how reliable value loading is. For this purpose investigate distribution loading. But difficult obtain its exact distribution. Therefore, derive asymptotic expansion loading, also construct confidence intervals result.
springer.com
sci-hub.st 参考文章(4)
George A. Anderson, An Asymptotic Expansion for the Distribution of the Latent Roots of the Estimated Covariance Matrix Annals of Mathematical Statistics. ,vol. 36, pp. 1153- 1173 ,(1965) , 10.1214/AOMS/1177699989
Nariaki Sugiura, Asymptotic expansions of the distributions of the latent roots and the latent vector of the Wishart and multivariate F matrices Journal of Multivariate Analysis. ,vol. 6, pp. 500- 525 ,(1976) , 10.1016/0047-259X(76)90002-6
Ian T. Jolliffe, Principal Component Analysis ,(1986)
T. W. Anderson, ASYMPTOTIC THEORY FOR PRINCIPAL COMPONENT ANALYSIS Annals of Mathematical Statistics. ,vol. 34, pp. 122- 148 ,(1963) , 10.1214/AOMS/1177704248