University of Michigan - Ann Arbor

R-Squared ($R^2$)—the proportion of variance explained—measures how well a prediction model for "regression" fits the given data. It is independent of the scale of $Y$.
$$0 \leq R^2 \leq 1$$
The larger the R-Squared value, the closer it is to 1, the better the regression model explains the variation of observations around its mean.
$$ R^2 = \frac{TSS-RSS}{TSS} = 1 - \frac{RSS}{TSS} = 1 - \frac{\sum_{i=1}^{n} (y_i - \hat{y}_i)^2}{\sum_{i=1}^{n} (y_i - \bar{y})^2} $$

R-Squared (Coefficient of Determination)

What does $R^2 = 0$ Mean?

Adjusted R-Squared is a version of R-Squared ($$R^2$$) that is adjusted for the number of predictors (independent variables) in a model. Its advantage over $$R^2$$ is that it accounts for statistical shrinkage. The normal $$R^2$$ statistic tends to increase when more independent variables occur in the system; i.e., we cannot use it to compare models with different numbers of predictors. The adjusted R-Squared can be negative, but it is usually not. It is always lower than or equal to the $$R^2$$.

$$\bar{R}^2 = 1 - (1 - R^2)\frac{n - 1}{n - p - 1}$$

Where $$p$$ is the number of predictors and $$n$$ is the sample size.

Adjusted R-Squared

The difference between the R-squared statistics measuring goodness of fit in both directions: $$C_{R2} = R_y^2 - R_x^2$$

Learn Before

Related

Related