Accelerated Failure Time models are based on the assumption that different levels of a predictor (e. g. different treatments) have a multiplicative effect on the survival time. Plotting the predicted survival time quantiles of different predictor levels against each other allows to assess the validity of the assumption. If the assumption is valid, the quantile pairs will approximately lie on a straight line through the origin.
An object of class
model includes frailties, they have to be estimated with
sparse = FALSE to allow predictions.
M. J. Bradburn, T. G. Clark, S. B. Love, und D. G. Altman, „Survival analysis Part III: multivariate data analysis – choosing a model and assessing its adequacy and fit“, Br. J. Cancer, Bd. 89, Nr. 4, S. 605–611, Aug. 2003.
W. R. Swindell, „ACCELERATED FAILURE TIME MODELS PROVIDE A USEFUL STATISTICAL FRAMEWORK FOR AGING RESEARCH“, Exp Gerontol, Bd. 44, Nr. 3, S. 190–200, März 2009.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.