Diagnostic Testing: ROC Curves

Our third and final lecture on diagnostic testing explores how to handle continuous predictors to predict a disease state (or some other binary outcome). Receiver operating characteristic (ROC) curves are introduced along with their corresponding area under the curve (AUC).

A video for the Biostatistical Methods I (BIOS 6611) course in the Department of Biostatistics and Informatics at the University of Colorado-Anschutz Medical Campus taught by Dr. Alex Kaizer. Slides and additional material available at https://www.alexkaizer.com/bios_6611.

Table of Contents:

00:00 - Intro Song
00:16 - Welcome
00:45 - ROC Background and Motivating Example
04:32 - ROC Curves in Practice
07:34 - Example with pROC Package in R
08:46 - Area Under the Curve (AUC)
12:17 - Picking the "Best" Threshold
15:09 - Diagnostic Testing Summary