Implements a two-stage estimation approach for Cox regression using five-parameter M-spline functions to model the baseline hazard. It allows for flexible hazard shapes and model selection based on log-likelihood criteria as described in Teranishi et al.(2025). In addition, the package provides functions for constructing and evaluating B-spline copulas based on five M-spline or I-spline basis functions, allowing users to flexibly model and compute bivariate dependence structures. Both the copula function and its density can be evaluated. Furthermore, the package supports computation of dependence measures such as Kendall's tau and Spearman's rho, derived analytically from the copula parameters.
The goal of splineCox is to ...
You can install the development version of splineCox from GitHub with:
# install.packages("pak")
pak::pak("Ren1227/splineCox")
This is a basic example which shows you how to solve a common problem:
library(splineCox)
## basic example code