RJafroc (version 0.0.1)

DBMHAnalysis: DBM analysis with Hillis improvements

Description

Performs Dorfman-Berbaum-Metz significance testing, with Hillis improvements, for the specified dataset.

Usage

DBMHAnalysis(dataset, fom = "wJAFROC", alpha = 0.05, option = "ALL")

Arguments

dataset

The dataset to be analyzed, see RJafroc-package.

fom

The figure of merit to be used in the analysis, default is wJAFROC, see FigureOfMerit.

alpha

The significance level of the test of the null hypothesis that all treatment effects are zero (default alpha is 0.05).

option

The analysis option: it can be RRRC, FRRC, RRFC or ALL (the default), corresponding random readers and random cases, fixed readers and random cases and random readers and fixed cases, respectively; this

Value

• The return value is a list with following elements:
• fomArray
  The figure of merit array of each reader and modality.
• anovaY
  The ANOVA table of the pseudovalues.
• anovaYi
  The ANOVA table of the pseudovalues for each modality.
• varComp
  The DBM variance components estimates.
• fRRRC
  The F statistic for testing the null hypothesis, for the RRRC condition.
• ddfRRRC
  The denominator degrees of freedom of the F statistic, for the RRRC condition.
• pRRRC
  The p-value of the significance test of the NH for the RRRC condition.
• ciDiffTrtRRRC
  The confidence intervals and related tests for the FOM differences between pairs of modalities, for the RRRC condition.
• ciAvgRdrEachTrtRRRC
  The confidence intervals and related tests for rdr. avg. FOM in each modality, for the RRRC condition.
• fFRRC
  The F statistic for testing the null hypothesis, for the FRRC condition.
• ddfFRRC
  The denominator degrees of freedom of the FRRC F statistic.
• pFRRC
  The p-value of the significance test of the NH, for the FRRC condition.
• ciDiffTrtFRRC
  The confidence intervals and related tests for the FOM differences between pairs of modalities, for the FRRC condition.
• ciAvgRdrEachTrtFRRC
  The confidence intervals and related tests for rdr. avg. FOM in each modality, for the FRRC condition.
• ssAnovaEachRdr
  The sum of squares table of the ANOVA of the pseudovalues for each reader (based on the data only for the specified reader).
• msAnovaEachRdr
  The mean squares table of the ANOVA of the pseudovalues for each reader (based on the data only for the specified reader).
• ciDiffTrtEachRdr
  The confidence intervals and related tests of the FOM differences between pairs of modalities for each reader.
• fRRFC
  The F statistic for testing the null hypothesis, for the RRFC condition.
• ddfRRFC
  The denominator degrees of freedom of the F statistic, for the RRFC condition.
• pRRFC
  The p-value of the significance test of the NH, for the RRFC condition.
• ciDiffTrtRRFC
  The confidence intervals and related tests for the FOM differences between pairs of modalities, for the RRFC condition.
• ciAvgRdrEachTrtRRFC
  The confidence intervals and related tests for rdr. avg. FOM in each modality, for the RRFC condition.

Examples

retDbmRoc  <- DBMHAnalysis(rocData, fom = "Wilcoxon")

retDbmwJAFROC  <- DBMHAnalysis(frocData) # default is weighted JAFROC

retDbmHrAuc  <- DBMHAnalysis(frocData, fom = "HrAuc")
print(retDbmHrAuc)

retDbmSongA1  <- DBMHAnalysis(frocData, fom = "SongA1")
print(retDbmSongA1)

retDbmSongA2  <- DBMHAnalysis(frocData, fom = "SongA2")
print(retDbmSongA2)

retDbmwJafroc1  <- DBMHAnalysis(frocData, fom = "wJAFROC1")
print(retDbmwJafroc1)

retDbmJafroc1  <- DBMHAnalysis(frocData, fom = "JAFROC1")
print(retDbmJafroc1)

retDbmJAFROC  <- DBMHAnalysis(frocData, fom = "JAFROC")
print(retDbmJAFROC)

retDbmROI  <- DBMHAnalysis(roiData, fom = "ROI")
print(retDbmROI)