Coefficient of Determination (R²)
What you'll learn: How to interpret R² as a measure of how well your linear regression model explains the variance in your data.
What R² Tells You
After fitting a linear regression model, you need to know: how good is this fit? The Coefficient of Determination, written as R² (R-squared), answers this question by measuring what proportion of the variance in your target variable is explained by your model.
Think of variance as "how spread out" your data points are. R² compares two things:
- How much your predictions reduce uncertainty compared to just guessing the mean
- The total uncertainty in your data
Understanding R² Values
R² ranges from 0 to 1 (sometimes negative for terrible models):
- R² = 1.0: Perfect fit! Your model explains 100% of the variance. Every prediction is exactly right.
- R² = 0.75: Your model explains 75% of the variance. Pretty good—most variation is captured.
- R² = 0.5: Your model explains half the variance. There's room for improvement.
- R² = 0.0: Your model is no better than predicting the mean every time.
- R² < 0: Your model is worse than just using the mean. Something went very wrong!
Practical Interpretation
If you're predicting house prices and get R² = 0.82, it means your model (using square footage, bedrooms, etc.) explains 82% of why prices vary. The remaining 18% is due to factors your model doesn't capture—maybe location nuances or renovations.
Key Takeaway: R² measures the proportion of variance your model explains, ranging from 0 (no better than the mean) to 1 (perfect predictions), helping you quantify model fit quality before making decisions about whether your linear regression is good enough.