A simulation-based approach to estimate joint model of longitudinal and event-time data with many missing longitudinal observations

TL;DR

This paper introduces a novel simulation-based method for estimating joint models of longitudinal and event-time data, effectively handling missing data and large datasets, with proven statistical properties and practical application to consumer loan prepayment analysis.

Contribution

A new simulation-based estimation procedure for joint models that manages missing data efficiently and is scalable to massive datasets, with theoretical guarantees.

Findings

Method performs well with low-quality data and missing observations.

Estimation procedure is consistent and asymptotically normal.

Applied successfully to large consumer-loan dataset for pre-payment prediction.

Abstract

Joint models of longitudinal and event-time data have been extensively studied and applied in many different fields. Estimation of joint models is challenging, most present procedures are computational expensive and have a strict requirement on data quality. In this study, a novel simulation-based procedure is proposed to estimate a general family of joint models, which include many widely-applied joint models as special cases. Our procedure can easily handle low-quality data where longitudinal observations are systematically missed for some of the covariate dimensions. In addition, our estimation procedure is compatible with parallel computing framework when combining with stochastic descending algorithm, it is perfectly applicable to massive data and therefore suitable for many financial applications. Consistency and asymptotic normality of our estimator are proved, a simulation study is conducted to illustrate its effectiveness. Finally, as an application, the procedure is applied to estimate pre-payment probability of a massive consumer-loan dataset drawn from one biggest P2P loan platform of China.