This function calculates the C-statistic or AUC for logistic regression models.

ds.auc(pred = NULL, y = NULL, datasources = NULL)

Arguments

pred

the name of the vector of the predicted values

y

the name of the outcome variable. Note that this variable should include the complete cases that are used in the regression model.

datasources

a list of DSConnection-class objects obtained after login. If the datasources argument is not specified the default set of connections will be used: see datashield.connections_default.

Value

returns the AUC and its standard error

Details

The AUC determines the discriminative ability of a model.

Author

Demetris Avraam for DataSHIELD Development Team