Processed METABRIC Dataset and R Scripts for Copula Regression Analysis

This repository contains the processed dataset and R scripts used in a copula-based joint regression analysis of overall survival (binary outcome) and age at diagnosis (continuous outcome) in breast cancer patients from the METABRIC cohort. The original dataset was obtained from Kaggle, with the primary source being cBioPortal for Cancer Genomics.The analysis employs Gaussian and Archimedean copula families to model the dependence structure between mixed outcome types. Marginal distributions are specified according to outcome type, and parameters are estimated using maximum likelihood methods. Model comparison is performed using information criteria (AIC and BIC), and diagnostic and graphical assessments are included.The dataset provided here is a processed version that contains only the variables used in the final analysis. No patient-identifiable information is included. As the data originated from publicly available sources, no additional ethical approval was required for this secondary analysis.