bootLR (version 1.0.2)

diagCI: Compute values and confidence intervals for sensitivity, specificity, positive likelihood ratio, negative likelihood ratio for a single 2x2 table

Description

Compute values and confidence intervals for sensitivity, specificity, positive likelihood ratio, negative likelihood ratio for a single 2x2 table

Usage

diagCI(truePos, totalDzPos, trueNeg, totalDzNeg,
  calcLRCI = "BayesianLR.test", alpha = 0.05, binomMethod = "wilson",
  ...)

Arguments

truePos

The number of true positive tests.

totalDzPos

The total number of positives ("sick") in the population.

trueNeg

The number of true negatives in the population.

totalDzNeg

The total number of negatives ("well") in the population.

calcLRCI

Method to use to calculate the LR CI: "BayesianLR.test" "none" or "analytic"

alpha

The alpha for the width of the confidence interval (defaults to alpha = 0.05 for a 95 percent CI)

binomMethod

The method to be passed to binom.confint to calculate confidence intervals of proportions (sensitivity, etc.). See help("binom.confint") and the Newcombe article referenced below.

…

Arguments to pass to Bayesian.LRtest.

Value

A matrix containing sensitivity, specificity, posLR, negLR results and their confidence intervals

References

Deeks JJ, Altman DG. BMJ. 2004 July 17; 329(7458): 168-169. Newcombe RG. Statist Med. 1998; 17(857-872).

Examples

# NOT RUN {
diagCI( 25, 50, 45, 75 )
diagCI( truePos = c(25, 30), totalDzPos = c( 50, 55 ), trueNeg = c(5, 35), totalDzNeg = c(60,65) )
# }