bootLR: Bootstrapped Confidence Intervals for (Negative) Likelihood Ratio Tests

Computes appropriate confidence intervals for the likelihood ratio tests commonly used in medicine/epidemiology. It is particularly useful when the sensitivity or specificity in the sample is 100%. Note that this does not perform the test on nested models--for that, see 'epicalc::lrtest'.

Author
Keith A. Marill and Ari B. Friedman
Date of publication
2015-07-13 00:52:09
Maintainer
Ari B. Friedman <abfriedman@gmail.com>
License
LGPL-2.1
Version
1.0

View on CRAN

Man pages

BayesianLR.test
Compute the (positive/negative) likelihood ratio with...
bca
Internal function to analyze LR bootstrap finding median, and...
confusionStatistics
Compute sensitivity, specificity, positive likelihood ratio,...
drawMaxedOut
Internal function to draw a set of sensitivities or...
medianConsistentlyOne
Find the lowest population probability whose median is...
print.lrtest
Prints results from the BayesianLR.test As is typical for R,...
run.BayesianLR.test
The actual function that runs the test. BayesianLR.test is a...
sequentialGridSearch
Optimize a function returning a single numeric value subject...

Files in this package

bootLR
bootLR/inst
bootLR/inst/CITATION
bootLR/tests
bootLR/tests/testthat
bootLR/tests/testthat/test_bootLR.R
bootLR/tests/testthat/test_optimization.R
bootLR/tests/test-all.R
bootLR/NAMESPACE
bootLR/demo
bootLR/demo/00Index
bootLR/demo/examples.R
bootLR/NEWS
bootLR/R
bootLR/R/bootLR.R
bootLR/MD5
bootLR/DESCRIPTION
bootLR/man
bootLR/man/drawMaxedOut.Rd
bootLR/man/medianConsistentlyOne.Rd
bootLR/man/bca.Rd
bootLR/man/run.BayesianLR.test.Rd
bootLR/man/sequentialGridSearch.Rd
bootLR/man/print.lrtest.Rd
bootLR/man/confusionStatistics.Rd
bootLR/man/BayesianLR.test.Rd