Package: wevid 0.6.2.9000
wevid: Quantifying Performance of a Binary Classifier Through Weight of Evidence
The distributions of the weight of evidence (log Bayes factor) favouring case over noncase status in a test dataset (or test folds generated by cross-validation) can be used to quantify the performance of a diagnostic test (McKeigue (2019), <doi:10.1177/0962280218776989>). The package can be used with any test dataset on which you have observed case-control status and have computed prior and posterior probabilities of case status using a model learned on a training dataset. To quantify how the predictor will behave as a risk stratifier, the quantiles of the distributions of weight of evidence in cases and controls can be calculated and plotted.
Authors:
wevid_0.6.2.9000.tar.gz
wevid_0.6.2.9000.zip(r-4.5)wevid_0.6.2.9000.zip(r-4.4)wevid_0.6.2.9000.zip(r-4.3)
wevid_0.6.2.9000.tgz(r-4.4-any)wevid_0.6.2.9000.tgz(r-4.3-any)
wevid_0.6.2.9000.tar.gz(r-4.5-noble)wevid_0.6.2.9000.tar.gz(r-4.4-noble)
wevid_0.6.2.9000.tgz(r-4.4-emscripten)wevid_0.6.2.9000.tgz(r-4.3-emscripten)
wevid.pdf |wevid.html✨
wevid/json (API)
| # Install 'wevid' in R: |
| install.packages('wevid', repos = c('https://mcol.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/mcol/wevid/issues
Last updated 5 years agofrom:9483c34bb6. Checks:OK: 7. Indexed: yes.
| Target | Result | Date |
|---|---|---|
| Doc / Vignettes | OK | Sep 10 2024 |
| R-4.5-win | OK | Sep 10 2024 |
| R-4.5-linux | OK | Sep 10 2024 |
| R-4.4-win | OK | Sep 10 2024 |
| R-4.4-mac | OK | Sep 10 2024 |
| R-4.3-win | OK | Sep 10 2024 |
| R-4.3-mac | OK | Sep 10 2024 |
Exports:auroc.crudeauroc.modellambda.crudelambda.modelplotcumfreqsplotrocplotWdistsprop.belowthresholdWdensitiesweightsofevidence
Dependencies:clicolorspacefansifarverggplot2gluegtableisobandlabelinglatticelifecyclemagrittrMASSMatrixmclustmgcvmunsellnlmepillarpkgconfigplyrpROCR6RColorBrewerRcppreshape2rlangscalesstringistringrtibbleutf8vctrsviridisLitewithrzoo
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Quantifying performance of a diagnostic test using the sampling distribution of the weight of evidence favouring case over noncase status | wevid-package wevid |
| Plot the cumulative frequency distributions in cases and in controls | plotcumfreqs |
| Plot crude and model-based ROC curves | plotroc |
| Plot the distribution of the weight of evidence in cases and in controls | plotWdists |
| Proportions of cases and controls below a threshold of weight of evidence | prop.belowthreshold |
| Recalibrate posterior probabilities | recalibrate.p |
| Summary evaluation of predictive performance | auroc.crude auroc.model lambda.crude lambda.model mean.Wdensities summary-densities summary.Wdensities |
| Compute densities of weights of evidence in cases and controls | Wdensities |
| Calculate weights of evidence in natural log units | weightsofevidence |
| Example datasets | cleveland fitonly pima wevid.datasets |
