Assessing Model Accuracy

Free SOA Exam SRM (Statistics for Risk Modeling) lesson in Basics of Statistical Learning. 13 min read, ~1,944 words.

Training error always falls as flexibility rises; test error is U-shaped. Minimize test error, not training error. Regression uses mean squared error (MSE); classification uses misclassification rate, ROC/AUC, or log-loss. k-fold cross-validation (typically k=5 or k=10) is the workhorse. LOOCV is k=n: low bias, high variance, expensive. Test MSE decomposes...

Read the full lesson, free →
Worked examples, audio narration, and practice. No signup to read.

What this lesson covers

Learning objectives

Browse all free Exam SRM lessons or jump into free Exam SRM practice questions.