Issue Date

2023

Abstract

Traditional multivariate analysis of covariance test is based on restrictive assumptions like homoscedasticity and normality of errors. A semiparametric multivariate analysis of covariance model is postulated. Nonparametric regression and multivariate analysis of variance are imbedded into the backfitting algorithm to estimate the model. The responses are adjusted for covariate effect through a nonparametric function of the covariates. Simulation study indicates that a bootstrap-based test for treatment effects is correctly sized. The proposed semiparametric multivariate analysis of covariance is shown to be powerful in detecting multivariate differences in the presence of nonlinear covariates and is robust to different error distributions with homogeneous, heterogeneous, and singular variance-covariance matrices. Moreover, the test is advantageous over the classical multivariate analysis of covariance in various error variance-covariance structures especially with unbalanced sample sizes.

Source or Periodical Title

UP Los Baños Journal

Volume

21

Issue

1

Page

86-101

Document Type

Article

College

College of Arts and Sciences (CAS)

Subject

Nonparametric regression, Backfitting algorithm, Variance-covariance matrix

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.