ROC.ORC: ROC.ORC - ROC area matrix
In BushmanLab/hotROCs: Interactive Heatmaps for Areas under ROC Curves

Description Usage Arguments Details Value Author(s) Examples

View source: R/ROC.ORC.R

ROC curve areas, variances, and p-values for datasets in which the cases have ordinary random controls (i.e. not matched on any characteristic). The ROC areas and corresponding variances are estimated by the method of Delong et al. The data may derive from multiple datasets. Comparisons of different variables in a dataset compare the ROC curve areas relative to the controls. Comparisons of different datasets uses only the responses from each dataset and do not involve the random controls. It is the responsiibility of the caller to remove NA values from the arguments.

1	ROC.ORC(response, variables, origin = NULL, origin.levels = NULL)

`response`	logical vector identifying cases or character vector or factor vector with `"insertion"` marking the cases.
`variables`	a `matrix` or `data.frame` with `length(response)` rows and two or more columns.
`origin`	`NULL` or a vector of `length(response)` elements to identify different data sources.
`origin.levels`	optional character vector of origin levels

A matrix of ROC curve areas and variances.

list with elements ‘ROC’ giving a matrix of ROC curve areas, ‘var’ giving a list of variance matrices, and ‘pvalues’ giving a list of matrices containing pvalues for various contrasts.

Charles Berry

case <- rep(rep(c(TRUE,FALSE),c(1,3)),1000)
var1 <- case + rnorm(4000)
var2 <- case + rexp(4000)
var3 <- case + runif(4000,-1,1)
origin <- rep(factor(letters[1:4]),each=1000)
ROC.ORC(case,cbind(var1,var2,var3),origin)