ROC ANALYSIS
ROC ANALYSIS is available in Statistics Base Edition.
ROC ANALYSIS assess the accuracy of model predictions by plotting sensitivity
versus (1-specificity) of a classification test (as the threshold varies over an entire range of
diagnostic test results). The full area under a given ROC curve, or AUC, formulates an important
statistic that represents the probability that the prediction is in the correct order when a test
variable is observed (for one subject that is randomly selected from the case group, and the other
randomly selected from the control group). ROC Analysis supports the inference regarding a single
AUC, precision-recall (PR) curves, and provides options for comparing two ROC curves that are
generated from either independent groups or paired subjects.
ROC ANALYSIS varList BY varName({varvalue} {'varvalue'})
[ /MISSING
[ USERMISSING = {EXCLUDE**} {INCLUDE} ] ]
[ /CRITERIA
[ CUTOFF = {INCLUDE**} {EXCLUDE} ]
[ TESTPOS = {LARGE**} {SMALL} ]
[ CI = {95**} {value} ]
[ DISTRIBUTION = {FREE**} {NEGEXPO} ] ]
[ /DESIGN
[ PAIR = {FALSE**} {TRUE} ]
[ GROUP = groupVarName ]
[ SELECT = {LEVEL(value1/string1 value2/string2)} {MIDPOINT} {CUTPOINT(value)} ] ]
[ /PLOT
[ CURVE = {ROC**[(REFERENCE)] [PR]} {NONE} ]
[ PR_INTERPOLATE = {TP**} {FP} ]
[ MODELQUALITY = {FALSE**} {TRUE} ] ]
[ /PRINT
[ SE = {FALSE**} {TRUE} ]
[ COORDINATES = [ROC[(YOUDEN)] [PR] ] ]
[ CLASSIFIER ={FALSE**}{TRUE}]
** Default if subcommand is omitted.
The old ROC Curve procedure supports the statistical inference about a single ROC curve. This may also be recovered by the new ROC Analysis procedure. Furthermore, the new ROC Analysis procedure can compare two ROC curves that are generated from either independent groups or paired subjects.
This command reads the active dataset and causes execution of any pending commands. See the topic Command Order for more information.
Syntax for the ROC
ANALYSIS command can be generated from the ROC Analysis
dialog.
Release History
- YOUDEN keyword introduced.
- CLASSIFIER keyword introduced
- Command introduced