prtScoreRocBayesianBootstrap   Generate a reciever operator characteristic curve with Bayesian Boostrapping
 
    prtScoreRocBayesianBootstrap(DECSTATS,LABELS) plots the receiver operator
    characteristic curve for the decision statistics DECSTATS and the
    corresponding labels LABELS. DECSTATS must be a Nx1 vector of decision
    statistics. LABELS must be a Nx1 vector of binary class labels.
 
    prtScoreRocBayesianBootstrap performs Bayesian boot strap sampling of
    an ROC curve and generates the 100*(1-alpha) percent percentile uniform
    credible band. The default alpha is .05, corresponding to a 95%
    credible band. This is done following the methodology in:
 
    Non-parametric estimation of ROC curve
    J. Gu, S. Ghosal, and A. Roy
    Statistics in Medicine, Vol. 27, 5407—5420, 2008.
    http://www4.stat.ncsu.edu/~ghosal/papers/ROCBB.pdf
 
    prtScoreRocBayesianBootstrap(DECSTATS,LABELS, NBOOTSAMP) Specifies the
    nummber of boostrap samples NBOOTSAMP. The default value is 1000.
 
    prtScoreRocBayesianBootstrap(DECSTATS,LABELS, [], NPFSAMP) Specfies the
    number of samples of probability of false alarm at with which to sample
    the ROC curve. The default is 500.
 
    prtScoreRocBayesianBootstrap(DECSTATS,LABELS, [], [], ALPHA) Specifies
    ALPHA, the size of the credible interval 100*(1-alpha). The default is
    0.05, corresponding to a 95% credible band
 
    [PFSAMPLES, PDMEAN,PDCONFREGION, BOOTSTRAPPEDPDS] =
    prtScoreRocBayesianBootstrap(...) outputs PFSAMPLES, the False alarm
    probabilities at which the bootstrapped ROC curves are evaluated.
    PDMEAN, the mean of the bootstrapped ROC curves, PDCONFREGION, the
    100*(1-alpha) percent percentile uniform credible band reported as the
    upper and lower Pd curves. BOOTSTRAPPEDPDS, all samples of the
    bootstrapped ROC curves
 
     Example:     
     TestDataSet = prtDataGenSpiral;       % Create some test and
     TrainingDataSet = prtDataGenSpiral;   % training data
     classifier = prtClassSvm;             % Create a classifier
     classifier = classifier.train(TrainingDataSet);    % Train
     classified = run(classifier, TestDataSet);     
     %  Plot the ROC
     prtScoreRocBayesianBootstrap(classified.getX, TestDataSet.getY,[],[],.2);