Principal Component Models for Patterned Covariance Matrices, with Applications to Canonical Correlation Analysis of Several Sets of Variables
Bernard D. Flury, Beat E. Neuenschwander · 1995
Abstract In this chapter we discuss in detail a common principal component model for dependent random vectors which arises naturally in an variety of situations. The best way to motivate it is probably by presenting some examples. Example 5.1. Jackson (1991) reports audiometric measurements taken on N=100 men of the same age. Hearing loss (in decibel) was measured for frequencies of 500 Hz, 1000 Hz, 2000 Hz, and 5000 Hz on both ears.