Perform the Cox regression and dynamic prediction methods under
the joint frailty-copula model between tumour progression and death for meta-analysis.
A penalized likelihood is employed for estimating model parameters, where the baseline hazard functions are approximated by smoothing splines.
The methods are applicable for meta-analytic data combining several studies.
The methods can analyze data having information on both terminal event time (e.g., time-to-death) and non-terminal event time (e.g., time-to-tumour progression).
See Emura et al. (2015)