Title: Gaussian copula regression
Authors: Guido Masarotto - University of Padova (Italy)
Cristiano Varin - Ca Foscari University of Venice (Italy) [presenting]
Abstract: A general framework for modelling dependence in regression models is presented based on a working Gaussian copula. Model properties, likelihood inference and computational aspects will be discussed in detail. Emphasis will be given to the validation of the Gaussian copula assumption and methods to make inference robust to departures from that assumption. The methodology will be illustrated with a variety of real data examples about time series, longitudinal and spatial data. Computations are based on the new version of the R package gcmr available through the CRAN archive.