Member-only story
Since data science is fourth career in as many decades, I am continually taking courses and watching tutorials on new techniques in data science. One such machine learning technique, although not necessarily new, is new to me. This technique is called the roc curve.The link to my most recent post where I prepared roc curves on two classification models can be found here:- https://tracyrenee61.medium.com/a-comparison-of-logistic-regression-versus-decision-tree-in-a-heart-disease-dataset-e7cb15db082d
Roc curves summarise the trade offs between the true positive rate and the false positive rate for a predictive model using different probability thresholds. These curves are appropriate when the observations are balanced between each class. The roc curve plots the false alarm rate versus the hit rate.
A roc curve (receiver operating characteristic curve) is a graph showing the performance of a classification model at all classification thresholds. This curve plots two parameters, being:-
1.True positive rate (TPR) is calculated as the number of true positives divided by the sum of the number of true positives and the number of false negatives. It describes how good the model is at predicting the positive class when the actual outcome is positive. TPR can also be referred to as sensitivity:-
