R-squared
FRM Part 1 glossary · Quantitative Analysis
Definition
The coefficient of determination — the fraction of the dependent variable's variance explained by the regression — equal to the squared correlation in a simple regression; it ranges from 0 to 1.
R-squared in plain English
R-squared tells you how much of the ups-and-downs in the thing you're trying to predict is actually captured by your prediction model. Imagine trying to explain students' test scores using hours studied: R-squared is the share of the score variation that "hours studied" accounts for. It runs from 0 to 1 — an R-squared of 0.7 means your model explains 70% of the variation, leaving 30% to other factors you haven't included. Higher looks better, but a high R-squared doesn't prove your model is right or that one thing causes another — it just measures how tightly the data hug your fitted line.
Related FRM Part 1 terms
FRM Part 1 practice questions · FRM Part 1 flashcards · FRM Part 1 study guide