A0192
Title: Linear models for doubly multivariate data with exchangeably distributed errors and site-dependent covariates
Authors: Anuradha Roy - The University of Texas at San Antonio (United States) [presenting]
Timothy Opheim - The University of Texas at San Antonio (United States)
Abstract: Doubly multivariate repeated measures data, where observations are made on $p$ response variables and each response variable is measured over $n$ sites or time points, construct matrix-valued response variable, and arise across a wide range of disciplines, including medical, environmental and agricultural studies. In many practical situations, response variables are affected by several explanatory variables, and these explanatory variables may vary over sites or time points too. In this case, we say that the data have site-dependent covariates, which construct a matrix-valued explanatory variable. Rao's score test (RST) for testing the intercept and slope parameters for doubly multivariate linear models with site-dependent covariates is developed and applied to an agricultural dataset. Monte Carlo simulations indicate that the RST statistic is much more accurate than its counterpart likelihood ratio test (LRT) statistic and it takes significantly less computation time than the LRT statistic.
