Create paired dataset for testing FitCorCbm

The paired dataset is generated using bivariate sampling; details are in referenced publication

DfCreateCorCbmDataset(
  seed = 123,
  K1 = 50,
  K2 = 50,
  desiredNumBins = 5,
  muX = 1.5,
  muY = 3,
  alphaX = 0.4,
  alphaY = 0.7,
  rhoNor = 0.3,
  rhoAbn2 = 0.8
)

Arguments

seed

The seed variable, default is 123; set to NULL for truly random seed

K1

The number of non-diseased cases, default is 50

K2

The number of diseased cases, default is 50

desiredNumBins

The desired number of bins; default is 5

muX

The CBM \(\mu\) parameter in condition X

muY

The CBM \(\mu\) parameter in condition Y

alphaX

The CBM \(\alpha\) parameter in condition X

alphaY

The CBM alpha parameter in condition Y

rhoNor

The correlation of non-diseased case z-samples

rhoAbn2

The correlation of diseased case z-samples, when disease is visible in both conditions

Value

The desired dataset suitable for testing FitCorCbm.

Details

The ROC data is bined to 5 bins in each condition.

References

Zhai X, Chakraborty DP (2017) A bivariate contaminated binormal model for robust fitting of proper ROC curves to a pair of correlated, possibly degenerate, ROC datasets. Medical Physics. 44(6):2207–2222.

Examples

## seed <- 1 
## this gives unequal numbers of bins in X and Y conditions for 50/50 dataset
dataset <- DfCreateCorCbmDataset()

# \donttest{
## this takes very long time!! used to show asymptotic convergence of ML estimates 
## dataset <- DfCreateCorCbmDataset(K1 = 5000, K2 = 5000)
# }