DSE220EvaluationValidationMAS42015

.pdf
School
University of California, San Diego **We aren't endorsed by this school
Course
DSE 220
Subject
Statistics
Date
Sep 3, 2023
Pages
55
Uploaded by MegaFangFinch27 on coursehero.com
Evaluation & Validation Credibility: Evaluating what has been learned
How predictive is a learned model? How can we evaluate a model Test the model Statistical tests Considerations in evaluating a Model How was the model created, contributing factors Amount of Data "Quality" of data - Labeled data is usually limited How will model perform on unseen data? Training/Validation/Test Data sets Splitting Data
Evaluation Significance tests - Statistical reliability of estimated differences in performance Performance measures Number of correct classifications Accuracy of probability estimates Error in numeric predictions Different costs assigned to different types of errors
Page1of 55
Uploaded by MegaFangFinch27 on coursehero.com