pmcalibration: Calibration Curves for Clinical Prediction Models

Fit calibrations curves for clinical prediction models and calculate several associated metrics (Eavg, E50, E90, Emax). Ideally predicted probabilities from a prediction model should align with observed probabilities. Calibration curves relate predicted probabilities (or a transformation thereof) to observed outcomes via a flexible non-linear smoothing function. 'pmcalibration' allows users to choose between several smoothers (regression splines, generalized additive models/GAMs, lowess, loess). Both binary and time-to-event outcomes are supported. See Van Calster et al. (2016) <doi:10.1016/j.jclinepi.2015.12.005>; Austin and Steyerberg (2019) <doi:10.1002/sim.8281>; Austin et al. (2020) <doi:10.1002/sim.8570>.

Version:	0.2.0
Imports:	Hmisc, MASS, mgcv, splines, graphics, stats, methods, survival, pbapply, parallel, grDevices
Suggests:	rmarkdown, data.table, ggplot2, rms, simsurv
Published:	2025-02-21
DOI:	10.32614/CRAN.package.pmcalibration
Author:	Stephen Rhodes [aut, cre, cph]
Maintainer:	Stephen Rhodes <steverho89 at gmail.com>
BugReports:	https://github.com/stephenrho/pmcalibration/issues
License:	GPL-3
URL:	https://github.com/stephenrho/pmcalibration
NeedsCompilation:	no
Citation:	pmcalibration citation info
Materials:	README, NEWS
CRAN checks:	pmcalibration results

Documentation:

Reference manual:

pmcalibration.html , pmcalibration.pdf

Downloads:

Package source:	pmcalibration_0.2.0.tar.gz
Windows binaries:	r-devel: pmcalibration_0.2.0.zip, r-release: pmcalibration_0.2.0.zip, r-oldrel: pmcalibration_0.2.0.zip
macOS binaries:	r-release (arm64): pmcalibration_0.2.0.tgz, r-oldrel (arm64): pmcalibration_0.2.0.tgz, r-release (x86_64): pmcalibration_0.2.0.tgz, r-oldrel (x86_64): pmcalibration_0.2.0.tgz
Old sources:	pmcalibration archive

Reverse dependencies:

Reverse imports:

pminternal

Linking:

Please use the canonical form https://CRAN.R-project.org/package=pmcalibration to link to this page.