What is R-Squared?
Summary: This module briefly introduces r-squared. It also gives an example and an exercise.
R squared is a statistical measure of how well
a regression line approximates real data points [
DefR-Squared]. R squared is a descriptive measure between
zero and one, indicating how good one term is at predicting another
[
R-SquaredDef].
Example 1
If you have a model, the closer its R squared value is to one, the greater the ability of that model to predict a trend. A value of R squared equal to one, which only occurs in fairy tales and textbook exercises, would imply that your model provides perfect predictions.
Problem 1
Can R squared be used to indicate the strength of a relationship?
Solution 1
Yes.
R squared can be used as an indicator of the reliability of a relationship identified by regression analysis. An R squared of 0.8 indicates that 80% of the change in one variable is explained by a change in the related variable.
References:
- DefR-Squared. “Definition R-squared”. Accessed on February 22, 2006. At http://www.chartfilter.com/glossary/r11.htm
- R-SquaredDef. “Definition of R-Squared”. Accessed on February 22, 2006. At http://www.trade-ideas.com/Glossary/R-Squared.html
- Author of Assignment 3: Lekulana Kolobe
- Author of Assignment 1: Arnold Mwesigye
More about this content: Metadata | Version History | Cite This Content
This work is licensed by Lekulana Kolobe. See the Creative Commons License about permission to reuse this material.
Last edited by Lekulana Kolobe on Feb 22, 2006 6:41 am US/Central.