Joint modeling approach improves variable selection and estimation in mixed panel count data, suggesting enhanced accuracy in analyses involving informative observation processes.
Mixed panel count data occur in many studies, and many researchers have analysed them. However, there seems to be no established approach for their analysis with the focus on variable selection when involving an informative observation process. It is widely acknowledged that methods assuming noninformative observation times can yield biased results when this assumption is violated. To fill the gap, a joint modelling strategy is introduced. Specifically, we develop a penalized likelihood estimation method and an efficient EM algorithm for simultaneous variable selection and estimation. The oracle property of the suggested method is demonstrated, and a simulation study is conducted, revealing its effective performance in practice. In addition, an illustration using the Health and Retirement Study data is provided.
No takes yet. Share an insight, caveat, or question.
Ge et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: