Gaussian Copula Regression in R

Abstract

This article describes the R package gcmr for fitting Gaussian copula marginal regression models. The Gaussian copula provides a mathematically convenient framework to handle various forms of dependence in regression models arising, for example, in time series, longitudinal studies or spatial data. The package gcmr implements maximum likelihood inference for Gaussian copula marginal regression. The likelihood function is approximated with a sequential importance sampling algorithm in the discrete case. The package is designed to allow a flexible specification of the regression model and the dependence structure. Illustrations include negative binomial modeling of longitudinal count data, beta regression for time series of rates and logistic regression for spatially correlated binomial data.

Gaussian Copula Marginal Regression Modeling for Technology Analysis

“…Gaussian copula regression is a statistical model to analyze various data sources such as time series, longitudinal, or spatial data [1]. In addition, the likelihood inference has been used for Gaussian copula models [2].…”

“…This method considers Gaussian copula model and marginal regression analysis. In addition, they developed an R package called "gcmr" [1]. The R is an efficient data language and its diverse packages are based on R data language like "gcmr" [9], [10].…”

“…This package provides diverse functions for GCMR such as model fitting or diagnostics plotting. In the GCMR, the model parameters are estimated the maximum likelihood and maximum simulated likelihood methods for continuous and discrete data types [1]. In general, we use various evaluation measures such as Akaike information criterion (AIC), Bayesian information criterion (BIC), and maximum log-likelihood to evaluate the performance of the GCMR model [1], [6].…”

“…In the GCMR, the model parameters are estimated the maximum likelihood and maximum simulated likelihood methods for continuous and discrete data types [1]. In general, we use various evaluation measures such as Akaike information criterion (AIC), Bayesian information criterion (BIC), and maximum log-likelihood to evaluate the performance of the GCMR model [1], [6]. Also, the "gcmr" package provides the function of residual analysis to check the model assumption [1].…”

“…In general, we use various evaluation measures such as Akaike information criterion (AIC), Bayesian information criterion (BIC), and maximum log-likelihood to evaluate the performance of the GCMR model [1], [6]. Also, the "gcmr" package provides the function of residual analysis to check the model assumption [1]. In this paper, we use the "gcmr" package and R data language to analyze the patent data related to target technology.…”