Practice R-Squared (Coefficient of Determination) in Statistics
Use these practice problems to test your method after reviewing the concept explanation and worked examples.
Quick Recap
R-squared (the coefficient of determination) is the proportion of variance in the dependent variable that is explained by the independent variable(s) in a regression model. It ranges from 0 to 1, where 0 means the model explains none of the variability and 1 means it explains all of it.
means the model explains 80% of why values differ. The other 20% is unexplained variation. Higher = better predictions.
Showing a random 20 of 76 problems.
Example 1
easy. Express the explained variation as a percent.
Example 2
mediumTotal variation in is ; SSR (sum of squared residuals) is . Find .
Example 3
mediumAs increases from to , residuals tend to do what?
Example 4
easyIf , what does that mean about the regression?
Example 5
medium and the regression slope is positive. Find including its sign.
Example 6
hardA regression has on the training data but predicts poorly on new data. What problem is most likely?
Example 7
easyA correlation is . Find .
Example 8
medium. Find .
Example 9
easy. Find .
Example 10
easy cannot be negative. True or false?
Example 11
hardTotal sum of squares is ; SSR . Find .
Example 12
mediumTotal variation in is . Residual variation is . Compute .
Example 13
easyA correlation is . Find .
Example 14
easy. What is ?
Example 15
hardA regression model has . Interpret this value.
Example 16
mediumModel A: . Model B: . By how many percentage points does A explain more variance?
Example 17
medium on a sample of pairs. Find .
Example 18
challengeTwo simple regressions: Model P has , Model Q has . By what factor does Model Q explain more variance than Model P?
Example 19
mediumA model has . Explain why this alone does not guarantee good predictions on new data.
Example 20
hardA linear model has . What percentage of the variation is not explained by the model?