Document Type

Article

Language

eng

Format of Original

20 p.

Publication Date

3-2015

Publisher

Taylor & Francis

Source Publication

Journal of Computational and Graphical Statistics

Source ISSN

1061-8600

Original Item ID

doi: 10.1080/10618600.2014.891461

Abstract

Principal component analysis (PCA) is a popular dimension-reduction method to reduce the complexity and obtain the informative aspects of high-dimensional datasets. When the data distribution is skewed, data transformation is commonly used prior to applying PCA. Such transformation is usually obtained from previous studies, prior knowledge, or trial-and-error. In this work, we develop a model-based method that integrates data transformation in PCA and finds an appropriate data transformation using the maximum profile likelihood. Extensions of the method to handle functional data and missing values are also developed. Several numerical algorithms are provided for efficient computation. The proposed method is illustrated using simulated and real-world data examples. Supplementary materials for this article are available online.

Comments

Accepted version. Journal of Computational and Graphical Statistics, Vol. 24, No. 1 (March 2015): 84-103. DOI. © Taylor & Francis 2015. Used with permission.

Share

COinS