CODEWITHSUNDEEP
rrandom-forest
SilverSpringbb
SilverSpringbb

Reputation: 51

Sensitivity/Specificity in Random Forest output

I created a Random Forest model in R. My outcome variable is "retain" with 1=retained and 0=left and I have the problem of case imbalance (many more in 0 than in 1) in the actual data, which is already shown in the confusion matrix for my training dataset. Based on my manual calculation, Sensitivity should be 0.05 and Specificity should be 0.67, which is consistent with the case imbalance problem. However, the numbers in the output are totally different. Below is the code and the output in console (rf is my Random Forest model):

retain_p <- rf %>% 
  predict(newdata = testing)

table(
  actualclass = testing$retain,
  predictedclass = retain_p
) %>% 
  confusionMatrix() %>% 
  print()

Confusion Matrix and Statistics

           predictedclass
actualclass    0    1
          0 1870   36
          1  911   47
                                          
               Accuracy : 0.6693          
                 95% CI : (0.6518, 0.6866)
    No Information Rate : 0.971           
    P-Value [Acc > NIR] : 1               
                                          
                  Kappa : 0.039           
                                          
 Mcnemar's Test P-Value : <2e-16          
                                          
            Sensitivity : 0.67242         
            Specificity : 0.56627         
         Pos Pred Value : 0.98111         
         Neg Pred Value : 0.04906         
             Prevalence : 0.97102         
         Detection Rate : 0.65293         
   Detection Prevalence : 0.66550         
      Balanced Accuracy : 0.61934         
                                          
       'Positive' Class : 0

Upvotes: 0

Views: 1190

Answers (1)

SilverSpringbb
SilverSpringbb

Reputation: 51

In confusionMatrix command, you have to specify what value goes into "positive".

retain_p <- rf %>% 
  predict(newdata = testing)

table(
  actualclass = testing$retain,
  predictedclass = retain_p
) %>% 
  confusionMatrix(positive='1') %>% 
  print()

Upvotes: 0

Related Questions