Copula-based Berkson measurement error models

In this work, we consider the joint distribution function as well as the copula of (X+Z,Y) where the random vector (X, Y, Z)  is characterized by a copula C_{X,Y,Z}. We use this copula to analyze a Berkson measurement error model. By presenting a general form of a Berkson measurement error model with copula-dependent random variables, we investigate some of its special cases. Some theoretical results, several examples as well as a simulation study, are proposed for illustration.

Keywords:

Copula , noise , perturbation of copula , Measurement Error