Residual sum of squares

This article needs additional citations for verification. Please help improve this article by adding citations to reliable sources. Unsourced material may be challenged and removed. Find sources: "Residual sum of squares" – news · newspapers · books · scholar · JSTOR (April 2013) (Learn how and when to remove this message)

In statistics, the residual sum of squares (RSS), also known as the sum of squared residuals (SSR) or the sum of squared estimate of errors (SSE), is the sum of the squares of residuals (deviations predicted from actual empirical values of data). It is a measure of the discrepancy between the data and an estimation model, such as a linear regression. A small RSS indicates a tight fit of the model to the data. It is used as an optimality criterion in parameter selection and model selection.

In general, total sum of squares = explained sum of squares + residual sum of squares. For a proof of this in the multivariate ordinary least squares (OLS) case, see partitioning in the general OLS model.

In a model with a single explanatory variable, RSS is given by:^[1]

$${\displaystyle \operatorname {RSS} =\sum _{i=1}^{n}\left(y_{i}-f(x_{i})\right)^{2}}$$

where y_i is the i^th value of the variable to be predicted, x_i is the i^th value of the explanatory variable, and ${\displaystyle f(x_{i})}$ is the predicted value of y_i (also termed ${\displaystyle {\hat {y_{i}}}}$). In a standard linear simple regression model, ${\displaystyle y_{i}=\alpha +\beta x_{i}+\varepsilon _{i}\,}$, where ${\displaystyle \alpha }$ and ${\displaystyle \beta }$ are coefficients, y and x are the regressand and the regressor, respectively, and ε is the error term. The sum of squares of residuals is the sum of squares of ${\displaystyle {\widehat {\varepsilon \,}}_{i}}$; that is

$${\displaystyle \operatorname {RSS} =\sum _{i=1}^{n}\left({\widehat {\varepsilon }}_{i}\right)^{2}=\sum _{i=1}^{n}\left(y_{i}-({\widehat {\alpha \,}}+{\widehat {\beta }}\,x_{i})\right)^{2}}$$

where ${\displaystyle {\widehat {\alpha \,}}}$ is the estimated value of the constant term ${\displaystyle \alpha }$ and ${\displaystyle {\widehat {\beta \,}}}$ is the estimated value of the slope coefficient ${\displaystyle \beta }$.

The general regression model with n observations and k explanators, the first of which is a constant unit vector whose coefficient is the regression intercept, is

$${\displaystyle y=X\beta +e}$$

where y is an n × 1 vector of dependent variable observations, each column of the n × k matrix X is a vector of observations on one of the k explanators, ${\displaystyle \beta }$ is a k × 1 vector of true coefficients, and e is an n× 1 vector of the true underlying errors. The ordinary least squares estimator for ${\displaystyle \beta }$ is

$${\displaystyle {\begin{aligned}&X{\hat {\beta }}=y\\[1ex]\iff &X^{\operatorname {T} }X{\hat {\beta }}=X^{\operatorname {T} }y\\[1ex]\iff &{\hat {\beta }}=\left(X^{\operatorname {T} }X\right)^{-1}X^{\operatorname {T} }y.\end{aligned}}}$$

The residual vector ${\displaystyle {\hat {e}}=y-X{\hat {\beta }}=y-X(X^{\operatorname {T} }X)^{-1}X^{\operatorname {T} }y}$; so the residual sum of squares is:

$${\displaystyle \operatorname {RSS} ={\hat {e}}^{\operatorname {T} }{\hat {e}}=\left\|{\hat {e}}\right\|^{2},}$$

(equivalent to the square of the norm of residuals). In full:

$${\displaystyle {\begin{aligned}\operatorname {RSS} &=y^{\operatorname {T} }y-y^{\operatorname {T} }X\left(X^{\operatorname {T} }X\right)^{-1}X^{\operatorname {T} }y\\[1ex]&=y^{\operatorname {T} }\left[I-X\left(X^{\operatorname {T} }X\right)^{-1}X^{\operatorname {T} }\right]y\\[1ex]&=y^{\operatorname {T} }\left[I-H\right]y,\end{aligned}}}$$

where H is the hat matrix, or the projection matrix in linear regression.

The least-squares regression line is given by

$${\displaystyle y=ax+b,}$$

where ${\displaystyle b={\bar {y}}-a{\bar {x}}}$ and ${\displaystyle a={\frac {S_{xy}}{S_{xx}}}}$, where ${\displaystyle S_{xy}=\sum _{i=1}^{n}({\bar {x}}-x_{i})({\bar {y}}-y_{i})}$ and ${\displaystyle S_{xx}=\sum _{i=1}^{n}({\bar {x}}-x_{i})^{2}.}$

Therefore,

$${\displaystyle {\begin{aligned}\operatorname {RSS} &=\sum _{i=1}^{n}\left(y_{i}-f(x_{i})\right)^{2}=\sum _{i=1}^{n}\left(y_{i}-(ax_{i}+b)\right)^{2}\\[1ex]&=\sum _{i=1}^{n}\left(y_{i}-ax_{i}-{\bar {y}}+a{\bar {x}}\right)^{2}=\sum _{i=1}^{n}\left[a\left({\bar {x}}-x_{i}\right)-\left({\bar {y}}-y_{i}\right)\right]^{2}\\[1ex]&=a^{2}S_{xx}-2aS_{xy}+S_{yy}=S_{yy}-aS_{xy}\\[1ex]&=S_{yy}\left(1-{\frac {S_{xy}^{2}}{S_{xx}S_{yy}}}\right)\end{aligned}}}$$

where ${\displaystyle S_{yy}=\sum _{i=1}^{n}({\bar {y}}-y_{i})^{2}.}$

The Pearson product-moment correlation is given by ${\displaystyle r={\frac {S_{xy}}{\sqrt {S_{xx}S_{yy}}}};}$ therefore, ${\displaystyle \operatorname {RSS} =S_{yy}(1-r^{2}).}$

• Draper, N.R.; Smith, H. (1998). Applied Regression Analysis (3rd ed.). John Wiley. ISBN 0-471-17082-8.