Article

A quasi F-test for functional linear models with functional covariates and its application to longitudinal data

Department of Statistics, University of California, Los Angeles, CA 90095, USA.
Statistics in Medicine (Impact Factor: 1.83). 10/2011; 30(23):2842-53. DOI: 10.1002/sim.4316
Source: PubMed

ABSTRACT

Functional linear models are useful in analyzing data from designed experiments and observational studies with functional responses, as well as longitudinal data with a large number of repeated measures on each subject. We propose a quasi F-test for functional linear models with functional covariates and outcomes. We develop a numerical procedure and an efficient approximation for computing p-values, and present a simple way to test individual predictors. For illustration, we apply the proposed procedure to a longitudinal depression data set with repeatedly measured methamphetamine use as a predictor. We conduct a simulation study to assess the size and the power of the test.

1 Follower
 · 
12 Reads