Mahalanobis Distances on Factor Model Based Estimation

Econometrics

Deliang Dai¹ 

[1] Department of Economics and Statistics, Linnaeus university, 351 95 Växjö, Sweden;

关键词: dimension reduction;    covariance matrix estimation;    outlier detection;    multivariate analysis;   

DOI  :  10.3390/econometrics8010010

来源: DOAJ

【 摘 要 】

A factor model based covariance matrix is used to build a new form of Mahalanobis distance. The distribution and relative properties of the new Mahalanobis distances are derived. A new type of Mahalanobis distance based on the separated part of the factor model is defined. Contamination effects of outliers detected by the new defined Mahalanobis distances are also investigated. An empirical example indicates that the new proposed separated type of Mahalanobis distances predominate the original sample Mahalanobis distance.

【 授权许可】

Unknown