n Annual Proceedings of the South African Statistical Association Conference - Diagnostics for detecting influential observations in joint survival models

Volume 2018 Number Congress 1
  • ISSN :


Joint models for longitudinal and survival data are a class of models that jointly analyse an outcome repeatedly observed over time such as a bio-marker and associated event times. These models are useful in two practical applications; firstly focusing on survival outcome whilst accounting for time varying covariates measured with error and secondly focusing on the longitudinal outcome while controlling for informative censoring. Interest in the estimation of these joint models has grown in the past two and a half decades. However, minimal effort has been directed towards developing diagnostic assessment tools for these models. The available diagnostic tools have mainly been based on separate analysis of residuals for the longitudinal and survival sub-models which could be sub-optimal. In this studywe develop Cook’s statistics for detecting influential observations or subjects for joint model estimates. We conducted simulation studies to evaluate these diagnostic statistics. These diagnostic techniques are further illustrated using data from a multi-center clinical trial on TB pericarditis.

Loading full text...

Full text loading...


Article metrics loading...


This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error