Handling Missingness Value on Jointly Measured Time-Course and Time-to-event Data

TL;DR

This paper addresses the challenge of missing data in joint modeling of longitudinal and time-to-event data, proposing effective imputation methods and demonstrating their impact through simulation and real biomarker study analysis.

Contribution

It introduces a detailed approach for handling missing values in joint models and evaluates the effects of multiple imputation techniques on inference accuracy.

Findings

Multiple imputation improves parameter estimation in joint models.

Simulation confirms the effectiveness of the proposed methods.

Application to biomarker data demonstrates practical utility.

Abstract

Joint modeling technique is a recent advancement in effectively analyzing the longitudinal history of patients with the occurrence of an event of interest attached to it. This procedure is successfully implemented in biomarker studies to examine parents with the occurrence of tumor. One of the typical problem that influences the necessary inference is the presence of missing values in the longitudinal responses as well as in covariates. The occurrence of missingness is very common due to the dropout of patients from the study. This article presents an effective and detailed way to handle the missing values in the covariates and response variable. This study discusses the effect of different multiple imputation techniques on the inferences of joint modeling implemented on imputed datasets. A simulation study is carried out to replicate the complex data structures and conveniently perform our analysis to show its efficacy in terms of parameter estimation. This analysis is further illustrated with the longitudinal and survival outcomes of biomarkers' study by assessing proper codes in R programming language.