Multilevel Mixed Effects Survival Analysis
Michael J. Crowther, PhD
Biostatistician, Karolinska Institutet
Honorary Senior Lecturer, University of Bristol
Founder and CEO, Red Door Analytics
Clustered survival data is often observed in a variety of settings, such as epidemiology, health services research, public health, and sociology. Patients treated, or living, in the same area may share unobserved characteristics (frailty), such as environmental aspects or medical care access.
Another common example is the analysis of recurrent event data, where individual patients can experience the event of interest multiple times throughout the follow-up period, and the inherent correlation within patients can be accounted for using a frailty/random intercept. Recurrent event analyses can also be impacted by the competing event of death, posing further challenges in the statistical analysis.
Using official Stata commands, and the community contributed merlin package (and one of its more user-friendly wrapper functions, stmixed), we will explore multilevel mixed effects survival models to tackle the above settings, with a range of applied datasets and example code. We will also discuss extensions, such as the addition of expected mortality to allow estimation of multilevel relative survival models.
Statisticians and researchers with a good working knowledge of the principles and practice of survival analysis, including modelling of survival data.
- Provide an overview of multilevel mixed effects survival analysis including recurrent event analysis and joint recurrent-terminal event models
- Introduce and illustrate tools in Stata for conducting multilevel survival analysis, including both modelling and prediction, with a focus on calculating clinically useful predictions.
Lectures with time for questions and discussion. No computer labs, but practical exercises and solutions will be provided, presented, and discussed.
Crowther MJ. Multilevel mixed effects parametric survival analysis: Estimation, simulation and application. Stata Journal 2019;19(4):931–949. (Pre-print: https://arxiv.org/abs/1709.06633)
Crowther MJ, Look MP, Riley RD. Multilevel mixed effects parametric survival models using adaptive Gauss-Hermite quadrature with application to recurrent events and individual participant data meta-analysis. Statistics in Medicine 2014;33(22):3844–3858.
Crowther MJ. merlin - a unified framework for data analysis and methods development in Stata. Stata Journal 2020;20(4):763–784.