hide
Free keywords:
Dependent data; Latent variable model; Nonstationary process; Partial least squares; Protein dynamics
Abstract:
We consider the partial least squares algorithm for dependent data and study the consequences of ignoring the dependence both theoretically and numerically. Ignoring nonstationary dependence structures can lead to inconsistent estimation, but a simple modification yields consistent estimation. A protein dynamics example illustrates the superior predictive power of the proposed method.