A0639
Title: Conditional dependence models under covariate measurement error
Authors: Elif Acar - University of Manitoba (Canada) [presenting]
Kaiqiong Zhao - York University (Canada)
Abstract: In many applications, covariates are subject to measurement error. While there is a vast literature on measurement error problems in regression settings, very little is known about the impact of covariate measurement error on the dependence parameter estimation in multivariate models. The latter problem is addressed using a conditional copula model, and it is shown that the dependence parameter estimates can be significantly biased if the covariate measurement error is ignored in the analysis. The underlying bias pattern from the direction and magnitude of marginal effect sizes is identified and an analytical bias correction method for the special case of the Gaussian copula is introduced. For general conditional copula models, a likelihood-based correction method is proposed, in which the likelihood function is computed via Monte Carlo integration. The consistency of the bias-corrected estimators is established. Numerical studies confirm that the proposed bias-correction methods achieve accurate estimation of the dependence parameter.