In a multi-class classification problem with 5 classes, a data scientist in SAS wants to use a One-vs-Rest (OVR) strategy with PROC HPLOGISTIC. How many binary models must be trained?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you need five binary models because one-versus-rest trains one classifier for each class, pitting that class against all the others combined. With five classes, that's five models.
Full Explanation
The correct answer is the five-model answer because one-versus-rest trains one binary classifier per class, where each classifier distinguishes that class from all other classes combined. With 5 classes, this requires 5 binary models. The ten-model answer describes the one-versus-one strategy, which trains one model per pair: classes times (classes minus one) divided by two = 10 models. The four-model answer is the number needed with a reference category in a single multinomial model. The single multinomial logistic regression answer is a different strategy — multinomial logistic regression — not one-versus-rest.