From Wikipedia, the free encyclopedia - View original article

Not to be confused with Coefficient of variation.

In statistics, the **coefficient of determination**, denoted ** R^{2}** and pronounced

There are several different definitions of *R*^{2} which are only sometimes equivalent. One class of such cases includes that of simple linear regression. In this case, if an intercept is included then *R*^{2} is simply the square of the sample correlation coefficient between the outcomes and their predicted values; in the case of simple linear regression, it is the square of the correlation between the outcomes and the values of the single regressor being used for prediction. If an intercept is included and the number of explanators is more than one, *R*^{2} is the square of the coefficient of multiple correlation. In such cases, the coefficient of determination ranges from 0 to 1. Important cases where the computational definition of *R*^{2} can yield negative values, depending on the definition used, arise where the predictions which are being compared to the corresponding outcomes have not been derived from a model-fitting procedure using those data, and where linear regression is conducted without including an intercept. Additionally, negative values of *R*^{2} may occur when fitting non-linear functions to data.^{[2]} In cases where negative values arise, the mean of the data provides a better fit to the outcomes than do the fitted function values, according to this particular criterion.^{[3]}

A data set has values *y _{i}*, each of which has an associated modelled value

In what follows is the mean of the observed data:

where *n* is the number of observations.

The "variability" of the data set is measured through different sums of squares:^{[disambiguation needed]}

- the total sum of squares (proportional to the sample variance);

- the regression sum of squares, also called the explained sum of squares.

- , the sum of squares of residuals, also called the residual sum of squares.

The notations and should be avoided, since in some texts their meaning is reversed to **R**esidual sum of squares and **E**xplained sum of squares, respectively.

The most general definition of the coefficient of determination is

In a general form, *R*^{2} can be seen to be related to the unexplained variance, since the second term compares the unexplained variance (variance of the model's errors) with the total variance (of the data). See fraction of variance unexplained.

In some cases the total sum of squares equals the sum of the two other sums of squares defined above,

See partitioning in the general OLS model for a derivation of this result for one case where the relation holds. When this relation does hold, the above definition of *R*^{2} is equivalent to

In this form *R*^{2} is expressed as the ratio of the explained variance (variance of the model's predictions, which is *SS*_{reg} / *n*) to the total variance (sample variance of the dependent variable, which is *SS*_{tot} / *n*).

This partition of the sum of squares holds for instance when the model values ƒ_{i} have been obtained by linear regression. A milder sufficient condition reads as follows: The model has the form

where the *q*_{i} are arbitrary values that may or may not depend on *i* or on other free parameters (the common choice *q*_{i} = *x*_{i} is just one special case), and the coefficients α and β are obtained by minimizing the residual sum of squares.

This set of conditions is an important one and it has a number of implications for the properties of the fitted residuals and the modelled values. In particular, under these conditions:

Similarly, in linear least squares regression with an estimated intercept term, *R*^{2} equals the square of the Pearson correlation coefficient between the observed and modeled (predicted) data values of the dependent variable.

Under more general modeling conditions, where the predicted values might be generated from a model different than linear least squares regression, an *R*^{2} value can be calculated as the square of the correlation coefficient between the original and modeled data values. In this case, the value is not directly a measure of how good the modeled values are, but rather a measure of how good a predictor might be constructed from the modeled values (by creating a revised predictor of the form α + βƒ_{i}). According to Everitt (2002, p. 78), this usage is specifically the definition of the term "coefficient of determination": the square of the correlation between two (general) variables.

*R*^{2} is a statistic that will give some information about the goodness of fit of a model. In regression, the *R*^{2} coefficient of determination is a statistical measure of how well the regression line approximates the real data points. An *R*^{2} of 1 indicates that the regression line perfectly fits the data.

Values of *R*^{2} outside the range 0 to 1 can occur where it is used to measure the agreement between observed and modeled values and where the "modeled" values are not obtained by linear regression and depending on which formulation of *R*^{2} is used. If the first formula above is used, values can be greater than one. If the second expression is used, there are no constraints on the values obtainable.

In many (but not all) instances where *R*^{2} is used, the predictors are calculated by ordinary least-squares regression: that is, by minimizing *SS*_{err}. In this case *R*^{2} increases as we increase the number of variables in the model (*R*^{2} is monotone increasing with the number of variables included, i.e. it will never decrease). This illustrates a drawback to one possible use of *R*^{2}, where one might keep adding variables (Kitchen sink regression) to increase the *R*^{2} value. For example, if one is trying to predict the sales of a model of car from the car's gas mileage, price, and engine power, one can include such irrelevant factors as the first letter of the model's name or the height of the lead engineer designing the car because the *R*^{2} will never decrease as variables are added and will probably experience an increase due to chance alone.

This leads to the alternative approach of looking at the adjusted *R*^{2}. The explanation of this statistic is almost the same as *R*^{2} but it penalizes the statistic as extra variables are included in the model. For cases other than fitting by ordinary least squares, the *R*^{2} statistic can be calculated as above and may still be a useful measure. If fitting is by weighted least squares or generalized least squares, alternative versions of R^{2} can be calculated appropriate to those statistical frameworks, while the "raw" *R*^{2} may still be useful if it is more easily interpreted. Values for *R*^{2} can be calculated for any type of predictive model, which need not have a statistical basis.

Consider a linear model of the form

where, for the *i*th case, is the response variable, are *p* regressors, and is a mean zero error term. The quantities are unknown coefficients, whose values are estimated by least squares. The coefficient of determination *R*^{2} is a measure of the global fit of the model. Specifically, *R*^{2} is an element of [0, 1] and represents the proportion of variability in *Y*_{i} that may be attributed to some linear combination of the regressors (explanatory variables) in *X*.

*R*^{2} is often interpreted as the proportion of response variation "explained" by the regressors in the model. Thus, *R*^{2} = 1 indicates that the fitted model explains all variability in , while *R*^{2} = 0 indicates no 'linear' relationship (for straight line regression, this means that the straight line model is a constant line (slope = 0, intercept = ) between the response variable and regressors). An interior value such as *R*^{2} = 0.7 may be interpreted as follows: "Seventy percent of the variation in the response variable can be explained by the explanatory variables. The remaining thirty percent can be attributed to unknown, lurking variables or inherent variability."

A caution that applies to *R*^{2}, as to other statistical descriptions of correlation and association is that "correlation does not imply causation." In other words, while correlations may provide valuable clues regarding causal relationships among variables, a high correlation between two variables does not represent adequate evidence that changing one variable has resulted, or may result, from changes of other variables.

In case of a single regressor, fitted by least squares, *R*^{2} is the square of the Pearson product-moment correlation coefficient relating the regressor and the response variable. More generally, *R*^{2} is the square of the correlation between the constructed predictor and the response variable. With more than one regressor, the *R*^{2} can be referred to as the coefficient of multiple determination.

In least squares regression, *R*^{2} is weakly increasing with increases in the number of regressors in the model. Because increases in the number of regressors increase the value of *R*^{2}, *R*^{2} alone cannot be used as a meaningful comparison of models with very different numbers of independent variables. For a meaningful comparison between two models, an F-test can be performed on the residual sum of squares, similar to the F-tests in Granger causality, though this is not always appropriate. As a reminder of this, some authors denote *R*^{2} by *R*_{p}^{2}, where *p* is the number of columns in *X* (the number of explanators including the constant).

To demonstrate this property, first recall that the objective of least squares linear regression is:

The optimal value of the objective is weakly smaller as additional columns of are added, by the fact that less constrained minimization leads to an optimal cost which is weakly smaller than more constrained minimization does. Given the previous conclusion and noting that depends only on *y*, the non-decreasing property of *R*^{2} follows directly from the definition above.

The intuitive reason that using an additional explanatory variable cannot lower the *R*^{2} is this: Minimizing is equivalent to maximizing *R*^{2}. When the extra variable is included, the data always have the option of giving it an estimated coefficient of zero, leaving the predicted values and the *R*^{2} unchanged. The only way that the optimization problem will give a non-zero coefficient is if doing so improves the *R*^{2}.

*R*^{2} does not indicate whether:

- the independent variables are a cause of the changes in the dependent variable;
- omitted-variable bias exists;
- the correct regression was used;
- the most appropriate set of independent variables has been chosen;
- there is collinearity present in the data on the explanatory variables;
- the model might be improved by using transformed versions of the existing set of independent variables;
- there are enough data points to make a solid conclusion.

See also: Omega-squared, ω2 in the article Effect size

The use of an adjusted *R*^{2} (often written as and pronounced "R bar squared") is an attempt to take account of the phenomenon of the *R*^{2} automatically and spuriously increasing when extra explanatory variables are added to the model. It is a modification due to Theil^{[4]} of *R*^{2} that adjusts for the number of explanatory terms in a model relative to the number of data points. The adjusted *R*^{2} can be negative, and its value will always be less than or equal to that of *R*^{2}. Unlike *R*^{2}, the adjusted *R*^{2} increases when a new explanator is included only if the new explanator improves the *R*^{2} more than would be expected in the absence of any explanatory value being added by the new explanator. If a set of explanatory variables with a predetermined hierarchy of importance are introduced into a regression one at a time, with the adjusted *R*^{2} computed each time, the level at which adjusted *R*^{2} reaches a maximum, and decreases afterward, would be the regression with the ideal combination of having the best fit without excess/unnecessary terms. The adjusted *R*^{2} is defined as

where *p* is the total number of regressors in the linear model (not counting the constant term), and *n* is the sample size.

Adjusted *R*^{2} can also be written as

where *df*_{t} is the degrees of freedom *n*– 1 of the estimate of the population variance of the dependent variable, and *df*_{e} is the degrees of freedom *n* – *p* – 1 of the estimate of the underlying population error variance.

The principle behind the adjusted *R*^{2} statistic can be seen by rewriting the ordinary *R*^{2} as

where and are the sample variances of the estimated residuals and the dependent variable respectively, which can be seen as biased estimates of the population variances of the errors and of the dependent variable. These estimates are replaced by statistically unbiased versions: and .

Adjusted *R*^{2} does not have the same interpretation as *R*^{2}—while *R*^{2} is a measure of fit, adjusted *R*^{2} is instead a comparative measure of suitability of alternative nested sets of explanators.^{[citation needed]} As such, care must be taken in interpreting and reporting this statistic. Adjusted *R*^{2} is particularly useful in the feature selection stage of model building.

Nagelkerke (1991) generalizes the definition of the coefficient of determination:

- A generalized coefficient of determination should be consistent with the classical coefficient of determination when both can be computed;
- Its value should also be maximised by the maximum likelihood estimation of a model;
- It should be, at least asymptotically, independent of the sample size;
- Its interpretation should be the proportion of the variation explained by the model;
- It should be between 0 and 1, with 0 denoting that model does not explain any variation and 1 denoting that it perfectly explains the observed variation;
- It should not have any unit.

The generalized *R*² (which was itself originally proposed by Cox & Snell (1989) ) has all of these properties.

where *L*(0) is the likelihood of the model with only the intercept, is the likelihood of the estimated model (i.e., the model with a given set of parameter estimates) and *n* is the sample size.

However, in the case of a logistic model, where cannot be greater than 1, *R*² is between 0 and : thus, Nagelkerke suggests the possibility to define a scaled *R*² as *R*²/*R*²_{max}.^{[5]}

The higher the correlation, the closer r2 is to "1".

Occasionally the norm of residuals is used for indicating goodness of fit. This term is encountered in MATLAB and is calculated by

Both *R*^{2} and the norm of residuals have their relative merits. For least squares analysis *R*^{2} varies between 0 and 1, with larger numbers indicating better fits and 1 represents a perfect fit. Norm of residuals varies from 0 to infinity with smaller numbers indicating better fits and zero indicating a perfect fit. One advantage and disadvantage of *R*^{2} is the term acts to normalize the value. If the *y _{i}* values are all multiplied by a constant, the norm of residuals will also change by that constant but

*R*^{2} = 0.997, and norm of residuals = 0.302. If all values of y are multiplied by 1000 (for example, in an SI prefix change), then *R*^{2} remains the same, but norm of residuals = 302.

- Fraction of variance unexplained
- Goodness of fit
- Nash–Sutcliffe model efficiency coefficient (hydrological applications)
- Pearson product-moment correlation coefficient
- Proportional reduction in loss
- Regression model validation
- Root mean square deviation

**^**Steel, R.G.D, and Torrie, J. H.,*Principles and Procedures of Statistics with Special Reference to the Biological Sciences.*, McGraw Hill, 1960, pp. 187, 287.)**^**Colin Cameron, A.; Windmeijer, Frank A.G.; Gramajo, H; Cane, DE; Khosla, C (1997). "An R-squared measure of goodness of fit for some common nonlinear regression models".*Journal of Econometrics***77**(2): 1790–2. doi:10.1016/S0304-4076(96)01818-0. PMID 11230695.**^**Imdadullah, Muhammad. "Coefficient of Determination".*itfeature.com*.**^**Theil, Henri (1961).*Economic Forecasts and Policy*. Holland, Amsterdam: North.^{[page needed]}**^**Nagelkerke, N. J. D. (1991). "A Note on a General Definition of the Coefficient of Determination".*Biometrika***78**(3): 691–2. doi:10.1093/biomet/78.3.691. JSTOR 2337038.

- Draper, N. R.; Smith, H. (1998).
*Applied Regression Analysis*. Wiley-Interscience. ISBN 0-471-17082-8. - Everitt, B. S. (2002).
*Cambridge Dictionary of Statistics*(2nd ed.). CUP. ISBN 0-521-81099-X. - Nagelkerke, Nico J. D. (1992).
*Maximum Likelihood Estimation of Functional Relationships, Pays-Bas*. Lecture Notes in Statistics**69**. ISBN 0-387-97721-X. - Glantz, S. A.; Slinker, B. K. (1990).
*Primer of Applied Regression and Analysis of Variance*. McGraw-Hill. ISBN 0-07-023407-8.