Presentation Profile
Why Ordinary Linear Regression should not be used to develop a correlation between test methods
Currently Scheduled: 10/14/2025 - 1:30 PM - 2:15 PM
Room: Tulip
Main Author
Alex Lau - Baytek
Abstract:
This brief seminar will provide a simple overview of the common uses and fundamental assumptions behind Ordinary Linear Regression (OLR), followed by an explanation of why the ReXY (Regression with errors in X and Y) technique in ASTM D6708 (Practice for Statistical Assessment and Improvement of Expected Agreement Between Two Test Methods that Purport to Measure the Same Property of a Material) should be used instead.
