RJafroc (version 1.3.2)

StSignificanceTestingSingleFixedFactor: Perform significance testing for single fixed factor analysis

Description

Significance testing for datasets with a single reader in multiple (at least two) treatments, or a single treatment with multiple (at least two) readers, where reader or treatment, respectively, is regarded as a fixed factor and a common case-set, regarded as random, is assumed.

Usage

StSignificanceTestingSingleFixedFactor(
  dataset,
  FOM,
  FPFValue = 0.2,
  alpha = 0.05
)

Arguments

dataset

A single-treatment or single-reader dataset.

FOM

The figure of merit, see UtilFigureOfMerit.

FPFValue

Only needed for LROC data and FOM = "PCL" or "ALROC"; where to evaluate a partial curve based figure of merit. The default is 0.2.

alpha

The significance level (alpha, default 0.05) of the test of the null hypothesis that FOMs of all levels of the fixed factor are identical.

Value

The return value is a list containing:

f

The observed F-statistic for testing the null hypothesis of no treatment effect.

ddf

The denominator degrees of freedom of the F statistic. The numerator degrees of freedom is always the number of levels of the fixed factor minus one.

pValue

The p-value for rejecting the NH.

fomStats

Statistics for FOM for each level of the fixed factor.

diffFomStats

Statistics for FOM-differences for all distinct pairings of the levels of the fixed factor

Details

This function performs implements Hillis et al. 2005, Eqn. 23. Following an overall F-test, reader-pairings are compared using paired t-tests. In order for a specific pairing to be declared significant, the F-test must also be significant.

References

Hillis SL, Obuchowski NA, Schartz KM, Berbaum KS (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.

Hillis SL (2007) A comparison of denominator degrees of freedom methods for multiple observer ROC studies, Statistics in Medicine. 26:596-619.

Hillis SL (2014) A marginal mean ANOVA approach for analyzing multireader multicase radiological imaging data, Statistics in medicine 33, 330-360.

Examples

# NOT RUN {
## Create a single treatment ROC dataset with one treatment and four readers
singleFactorData <- DfExtractDataset(dataset02, 1, 1:4)

## Performs single treatment fixed reader analysis
StSignificanceTestingSingleFixedFactor(singleFactorData, FOM = "Wilcoxon")

# }