Hogar » Coefficient of Determination (R²)

Coefficient of Determination (R²)

1900
  • Karl Pearson
Statistician analyzing regression model data in an office setting.

A statistic indicating the goodness of fit of a model, representing the proportion of the variance in the dependent variable that is predictable from the independent variable(s). An R² of 1 indicates a perfect fit, while 0 indicates no linear relationship. It is calculated as [latex]R^2 \equiv 1 – \frac{SS_{res}}{SS_{tot}}[/latex], where [latex]SS_{res}[/latex] is the residual sum of squares.

The coefficient of determination, R-squared, is a key metric for evaluating regression models. It provides an intuitive measure of how much of the variability in the outcome is captured by the model. It is derived from two key components. The first is the Total Sum of Squares ([latex]SS_{tot} = \sum_i (y_i – \bar{y})^2[/latex]), which measures the total variance in the dependent variable [latex]y[/latex]. The second is the Residual Sum of Squares ([latex]SS_{res} = \sum_i (y_i – \hat{y}_i)^2[/latex]), which measures the variance left unexplained by the model, where [latex]\hat{y}_i[/latex] is the predicted value.

The formula [latex]R^2 = 1 – SS_{res}/SS_{tot}[/latex] can be interpreted as the percentage of total variance that is ‘explained’ by the regression model. For instance, an R² of 0.75 means that 75% of the variability in the outcome can be accounted for by the predictors in the model. In simple linear regression, R² is simply the square of Pearson’s correlation coefficient (r) between the observed and predicted values.

However, R² has a significant limitation: it never decreases when a new predictor variable is added to the model, even if the new variable is irrelevant. This can be misleading and encourage overfitting. To counteract this, the Adjusted R-squared is often used. It modifies the R² value to account for the number of predictors in the model, providing a more accurate measure of goodness of fit for multiple regression.

UNESCO Nomenclature: 1209
- Estadísticas

Tipo

Sistema abstracto

Disrupción

Sustancial

Utilización

Uso generalizado

Precursores

  • Concept of variance and standard deviation
  • Method of least squares
  • Pearson’s product-moment correlation coefficient
  • Análisis de varianza (ANOVA) principios

Aplicaciones

  • evaluating the performance of predictive models in science and engineering
  • model selection in econometrics and social sciences
  • quantifying the proportion of variance explained by a set of predictors
  • validating financial models for risk assessment

Patentes:

NA

Posibles ideas innovadoras

Membresía obligatoria de Professionals (100% free)

Debes ser miembro de Professionals (100% free) para acceder a este contenido.

Únete ahora

¿Ya eres miembro? Accede aquí
Related to: r-squared, coefficient of determination, goodness of fit, model evaluation, explained variance, sum of squares, regression diagnostics, statistical significance, adjusted r-squared, correlation.

Deja una respuesta

Tu dirección de correo electrónico no será publicada. Los campos obligatorios están marcados con *

DISPONIBLE PARA NUEVOS RETOS
Ingeniero Mecánico, Gerente de Proyectos, Ingeniería de Procesos o I+D
Desarrollo eficaz de productos

Disponible para un nuevo desafío a corto plazo.
Contáctame en LinkedIn
Integración de electrónica de metal y plástico, diseño a coste, GMP, ergonomía, dispositivos y consumibles de volumen medio a alto, fabricación eficiente, industrias reguladas, CE y FDA, CAD, Solidworks, cinturón negro Lean Sigma, ISO 13485 médico

Estamos buscando un nuevo patrocinador

 

¿Su empresa o institución se dedica a la técnica, la ciencia o la investigación?
> Envíanos un mensaje <

Recibe todos los artículos nuevos
Gratuito, sin spam, correo electrónico no distribuido ni revendido.

o puedes obtener tu membresía completa -gratis- para acceder a todo el contenido restringido >aquí<

Contexto histórico

(si se desconoce la fecha o no es relevante, por ejemplo "mecánica de fluidos", se ofrece una estimación redondeada de su notable aparición)

Invención, innovación y principios técnicos relacionados

Scroll al inicio

También te puede interesar