Multi-Parameter Regression Survival Modeling: An Alternative to Proportional Hazards
- 28 November 2016
- journal article
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 73 (2) , 678-686
Abstract
It is standard practice for covariates to enter a parametric model through a single distributional parameter of interest, for example, the scale parameter in many standard survival models. Indeed, the well-known proportional hazards model is of this kind. In this article, we discuss a more general approach whereby covariates enter the model through more than one distributional parameter simultaneously (e.g., scale and shape parameters). We refer to this practice as “multi-parameter regression” (MPR) modeling and explore its use in a survival analysis context. We find that multi-parameter regression leads to more flexible models which can offer greater insight into the underlying data generating process. To illustrate the concept, we consider the two-parameter Weibull model which leads to time-dependent hazard ratios, thus relaxing the typical proportional hazards assumption and motivating a new test of proportionality. A novel variable selection strategy is introduced for such multi-parameter regression models. It accounts for the correlation arising between the estimated regression coefficients in two or more linear predictors—a feature which has not been considered by other authors in similar settings. The methods discussed have been implemented in the mpr package in R.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Parametric Quantile Regression Based on the Generalized Gamma DistributionJournal of the Royal Statistical Society Series C: Applied Statistics, 2013
- On the Cox Model With Time-Varying Regression CoefficientsJournal of the American Statistical Association, 2005
- Evaluating the performance of the Framingham risk equations in a population with diabetesDiabetic Medicine, 2004
- Indicator and Stratification Methods for Missing Explanatory Variables in Multiple Linear RegressionJournal of the American Statistical Association, 1996
- Proportional hazards tests and diagnostics based on weighted residualsBiometrika, 1994
- Flexible Methods for Analyzing Survival Data Using Splines, with Applications to Breast Cancer PrognosisJournal of the American Statistical Association, 1992
- Cox Analysis of Survival Data with Non-Proportional Hazard FunctionsJournal of the Royal Statistical Society: Series D (The Statistician), 1992
- Restricted Mean Life with Adjustment for CovariatesJournal of the American Statistical Association, 1987
- A General Model for the Hazard Rate with CovariablesBiometrics, 1979
- Nonparametric Estimation from Incomplete ObservationsJournal of the American Statistical Association, 1958