Skip to content

v0.3.0

Choose a tag to compare

View all tags
@jzluo jzluo released this 04 Jan 05:17
· 100 commits to main since this release
v0.3.0
90cbaec

Summary

This release adds optional Numba acceleration for FirthLogisticRegression and FirthCoxPH, greatly accelerating both of them over the numpy/scipy backend. See #12 and #32 for benchmarking results.

It also improves numerical robustness when fitting models with rank-deficient or ill-conditioned design matrices, with column-pivoting QR fall-back for logistic regression and pivoted Cholesky for Cox.

What's Changed

  • Add optional Numba backend for FirthLogisticRegression by @jzluo in #35
  • Add optional Numba backend for FirthCoxPH by @jzluo in #37
  • Add QR with column pivoting fallback for compute_logistic_quantities by @jzluo in #38
  • Add pivoted Cholesky fallback for compute_cox_quantities by @jzluo in #39
  • numba: replace dpotri with dpotrs for matrix inversion by @jzluo in #40

Full Changelog: v0.2.2...v0.3.0

Contributors

jzluo
Assets 2
Loading