Skip to main content

Statistical inference about right-censored c-indices

Project description

compare_concordance

This Python package implements a statistical test for the comparison of correlated right-censored concordance indices. The code is derived entirely from the GPLv3-licensed R package compareC. Accordingly, this package is also licensed under GPLv3. If you use it in published work, you should cite the original authors' paper (see below).

Installation

First, build the C library:

$ python3 setup.py build_ext

Then, install using Pip:

$ pip3 install .

This has been tested on 64-bit Linux with GCC version 7.5.0 and Python 3.6. If the installation step fails, it may be because your system names the .so file differently than expected.

Usage

from compare_concordance import compare_concordance

scores_1 = model1.predict(x)
scores_2 = model2.predict(x)

concordance_1, concordance2, difference, zscore, pvalue = compare_concordance(
    y['time'],
    y['status'],
    scores_1,
    scores_2
)

Citation

Kang L, Chen W, Petrick NA and Gallas BD (2015). "Comparing two correlated C indices with right-censored survival outcome: a one-shot nonparametric approach." Statistics in Medicine, 34(4), pp. 685-703. http://dx.doi.org/10.1002/sim.6370.

Bibtex

@Article{,
  title = {Comparing two correlated C indices with right-censored
    survival outcome: a one-shot nonparametric approach},
  author = {Le Kang and Weijie Chen and Nicholas A. Petrick and
    Brandon D. Gallas},
  year = {2015},
  volume = {34},
  number = {4},
  pages = {685-703},
  journal = {Statistics in Medicine},
  url = {http://dx.doi.org/10.1002/sim.6370},
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

compare_concordance-0.0.2.tar.gz (43.3 kB view details)

Uploaded Source

File details

Details for the file compare_concordance-0.0.2.tar.gz.

File metadata

  • Download URL: compare_concordance-0.0.2.tar.gz
  • Upload date:
  • Size: 43.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.9.5

File hashes

Hashes for compare_concordance-0.0.2.tar.gz
Algorithm Hash digest
SHA256 c4b71ab1a76dfa514cdf6c65ec03ab3fa7549bc39aa34e8a9b190a55c3fb9c82
MD5 8e8ae9ed3f3ef1ea0229b731d769f9ac
BLAKE2b-256 7fe75f2a7a171f68c38c65cd38ffc19c0564766c5a2fe67cf07a273710ccf332

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page