Hierarchical Failure Time Regression Using Mixtures for Classification of the Immune Response of Atlantic Salmon

Abstract

This work presents a Bayesian hierarchical model with the dual objective to analyze stratified survival data and to automatically classify each stratum into a finite number of groups. This is achieved by specifying parametric as well as piecewise stratum-specific baseline hazards and a finite mixture distribution for the stratum-specific shape parameters. A proportional hazards or accelerated failure time regression component allows to identify the influence of covariates on the survival distribution. We illustrate the model using a dataset of Atlantic salmon, stratified by families, that have been challenged with infectious pancreatic necrosis virus (IPNV). The main objectives are to model the survival time in terms of certain covariates as well as to classify the salmon families into either an IPNV susceptible or resistant group with the ultimate goal of improving resistance to IPNV through a selective breeding program. We compare the fit of different models that include stratum-specific baselines and covariate effects. The classifications show a certain degree of robustness with respect to model choice.