Diagnostics for Semiparametric Accelerated Failure Time Models with R Package afttest

TL;DR

The paper introduces afttest, an R package providing efficient diagnostic tools for semiparametric AFT models, including new resampling strategies that reduce computation time while maintaining validity.

Contribution

It develops a new influence-function-based resampling method for AFT diagnostics, improving computational efficiency over existing bootstrap approaches.

Findings

The package supports various estimators and tests.

It offers graphical tools for residual analysis.

Application demonstrates practical utility.

Abstract

The semiparametric accelerated failure time (AFT) model offers a direct and interpretable alternative to the Cox proportional hazards model, yet practical diagnostic tools for this framework remain limited. We introduce afttest, an R package that implements martingale-residual-based goodness-of-fit procedures for semiparametric AFT models. In addition to the recently developed multiplier bootstrap diagnostics, the package introduces a new computationally efficient resampling strategy based on an influence-function linear approximation. Unlike the original approach, which requires repeatedly solving estimating equations for each bootstrap replicate, the proposed method avoids iterative optimization and substantially reduces computation time while preserving asymptotic validity. Both the standard multiplier bootstrap and the accelerated linear approximation are implemented, allowing users to balance finite-sample performance and computational scalability. The package supports rank-based and least-squares estimators, provides omnibus, link function, and functional form tests, and includes graphical tools for visualizing residual processes. An application to the Mayo Clinic primary biliary cirrhosis study illustrates the workflow.