The following function is used to validate the predicted observations with the actual values based on some threshold.
spT.validation2(z,zhat,cutoff,names=FALSE)
Arguments
z: The original values (matrix or vector).
zhat: The predicted values (matrix or vector).
cutoff: The threshold value or cut-off point.
names: Logical, if TRUE then print the names of the validation statistics.
Returns
TPR: True Positive Rate, Sensitivity, Hit rate, Recall
FPR: False Positive Rate, False alarm
FNR: False Negative Rate, Miss rate
TNR: True Negative Rate, Specificity
Prevalence: Prevalence
Accuracy: Accuracy
Precision: Precision, Positive Predictive Value
FOR: False Ommission Rate
LRp: Positive Likelihood Ratio
LRn: Negative Likelihood Ratio
FDR: False Discovery Rate
NPV: Negative Predictive Value
DOR: Diagnostic Odds Ratio
F1score: F1 score
Heidke.Skill: Heidke Skill
See Also
spT.pCOVER,spT.validation.
Examples
### Create `x', which is the true values.# Create `y', which is the predicted values.x <- rnorm(100,0,0.1)y <- rnorm(100,0,1)spT.validation2(x, y, cutoff=0,names=TRUE)##