BJASS

BJASS (Buckley-James Assisted Sure Screening) is a software tool implemented in Matlab for variable screening in high-dimensional survival analysis. It is designed to reduce the dimensionality of datasets with many covariates before applying more refined methods for model selection and statistical analysis.

The key features of BJASS are:

1. It is based on a sparsity-restricted semiparametric accelerated failure time model, making it suitable for right-censored time-to-event data.

2. The screening procedure consists of an initial screening step using a sparsity-restricted least-squares estimate based on a synthetic time variable, followed by one or more refinement screening steps using a sparsity-restricted least-squares estimate with the Buckley-James imputed event times.