A Partly Parametric Additive Risk Model

Abstract

Aalen's additive risk model allows the influence of covariates on a hazard function to vary over time, and to do so in a different fashion for each covariate. Although allowing greater flexibility than a Cox model, which has a more parsimonious temporal structure, the number of covariates that can be handled by Aalen's model is quite limited. One way around this difficulty is to impose some a priori structure on the form of the model, thereby reducing the number of functions to be estimated. In this paper we introduce a partly parametric version of Aalen's model in which only a small number of the covariates are selected to have their influence vary nonparametrically over time, and the influence of the remaining covariates is restricted to be constant in time. Efficient procedures for fitting this new model are developed and studied. The approach is applied to data from the British Medical Research Council's myelomatosis trials.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1993
Accession Number
ADA260395

Entities

People

  • Ian W. Mckeague
  • Peter D. Sasieni

Organizations

  • Florida State University

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Biomedical Research
  • Classification
  • Confidence Limits
  • Covariance
  • Data Analysis
  • Data Science
  • Data Sets
  • Distribution Functions
  • Gaussian Processes
  • Information Science
  • Military Research
  • Probability
  • Regression Analysis
  • Scientific Research
  • Statistical Inference
  • Statistics
  • Universities

Fields of Study

  • Mathematics

Readers

  • Statistical inference.