RJafroc (version 0.1.1)

PowerGivenJK: Calculate statistical power given numbers of readers J and cases K for ROC studies

Description

Calculate the statistical power with the given number of readers, number of cases and DBM or OR variances components.

Usage

PowerGivenJK(J, K, varYTR, varYTC, varYEps, cov1, cov2, cov3, varEps, msTR, KStar, alpha = 0.05, effectSize = 0.05, randomOption = "ALL")

Arguments

J

The number of readers to be used in the calculation.

K

The number of cases to be used in the calculation.

varYTR

The DBM variance component of treatment(modality)-by-reader interaction term.

varYTC

The DBM variance component of treatment(modality)-by-case interaction term.

varYEps

The variance component of DBM error term.

cov1

The OR covariances of the figure of merit estimates of same reader and different modalities.

cov2

The OR covariances of the figure of merit estimates of same reader and different modalities.

cov3

The OR covariances of the figure of merit estimates of same reader and different modalities.

varEps

The variance component of OR error term.

msTR

Treatment(modality)-by-reader mean square of the figure of merit.

KStar

See SampleSizeGivenJ.

alpha

The significantce level.

effectSize

The effect size to be used in the calculation.

randomOption

The random option. It can be "ALL", "READERS" or "CASES", which indicate predictions for (1) random readers and random cases, (2) random readers only and (3) random cases only.

Value

The statistical power with given components and condition.

Details

To calculate the statistical power, either the group of DBM variance components (varYTR, varYTC, and varYEps) or OR variance components (cov1, cov2, cov3, varEps, msTR and KStar) should be specified. If both of them are given, DBM variance components are used and OR variance components are ignored.

References

Hillis, S. L., Obuchowski, N. A., & Berbaum, K. S. (2011). Power Estimation for Multireader ROC Methods: An Updated and Unified Approach. Acad Radiol, 18, 129-142.

Hillis, S. L., Obuchowski, N. a, Schartz, K. M., & Berbaum, K. S. (2005). A comparison of the Dorfman-Berbaum-Metz and Obuchowski-Rockette methods for receiver operating characteristic (ROC) data. Statistics in Medicine, 24(10), 1579-607.

Examples

## Following is an example of sample size calculation with DBM variance componements.
retDbm <- DBMHAnalysis(data = rocData, fom = "Wilcoxon")
effectSize <- retDbm$ciDiffTrtRRRC$Estimate
varCompDBM <- retDbm$varComp
varYTR <- varCompDBM$varComp[3]
varYTC <- varCompDBM$varComp[4]
varYEps <- varCompDBM$varComp[6]
PowerGivenJK(J = 6, K = 251, varYTR = varYTR, varYTC = varYTC,
             varYEps = varYEps, effectSize = effectSize)

## Following is an example of sample size calculation with OR variance componements.
retOR <- ORHAnalysis(data = rocData, fom = "Wilcoxon", covEstMethod = "Jackknife")
effectSize <- retDbm$ciDiffTrtRRRC$Estimate
varCompOR <- retOR$varComp
cov1 <- varCompOR$varCov[3]
cov2 <- varCompOR$varCov[4]
cov3 <- varCompOR$varCov[5]
varEps <- varCompOR$varCov[6]
KStar <- length(rocData$NL[1,1,,1])
msTR <- retOR$msTR
PowerGivenJK(J = 6, K = 251, cov1 = cov1, cov2 = cov2, cov3 = cov3,
             varEps = varEps, msTR = msTR, KStar = KStar, effectSize = effectSize)