Treatments of non-metric variables in partial least squares and principal component analysis. Issue 6 (26th April 2018)

• Record Type: Journal Article
• Authors: Yoon, Jisu; Krivobokova, Tatyana
• Is Part Of: Journal of applied statistics. Volume 45:Issue 6(2018)
• Page Start: 971
• Page End: 987
• Publication Date: 2018-04-26
• Subjects: Composite index -- wealth -- principal component analysis -- partial least squares -- non-metric variables; Statistics -- Periodicals; 519.5
• DOI: 10.1080/02664763.2017.1346065
• Languages: English
• ISSNs: 0266-4763

Abstract

ABSTRACT: This paper reviews various treatments of non-metric variables in partial least squares (PLS) and principal component analysis (PCA) algorithms. The performance of different treatments is compared in an extensive simulation study under several typical data generating processes and associated recommendations are made. Moreover, we find that PLS-based methods are to prefer in practice, since, independent of the data generating process, PLS performs either as good as PCA or significantly outperforms it. As an application of PLS and PCA algorithms with non-metric variables we consider construction of a wealth index to predict household expenditures. Consistent with our simulation study, we find that a PLS-based wealth index with dummy coding outperforms PCA-based ones.