Regresión lineal múltiple

Regresión lineal con varias variables predictoras

En un modelo de regresión lineal múltiple, la variable de respuesta depende de más de una variable predictora. Puede realizar una regresión lineal múltiple con o sin el objeto LinearModel o usando la app Regression Learner.

Para aumentar la precisión en conjuntos de datos de dimensiones bajas y medianas, ajuste un modelo de regresión lineal mediante fitlm.

Para reducir el tiempo de cálculo en conjuntos de datos de altas dimensiones, ajuste un modelo de regresión lineal mediante fitrlinear.

Apps

Regression LearnerEntrenar modelos de regresión para predecir datos usando machine learning supervisado

Bloques

RegressionLinear PredictPredecir respuestas usando el modelo de regresión lineal (Desde R2023a)
IncrementalRegressionLinear PredictPredict responses using incremental linear regression model (Desde R2023b)
IncrementalRegressionLinear FitFit incremental linear regression model (Desde R2023b)
Detect DriftActualizar estados de un detector de deriva y el estado de deriva con nuevos datos (Desde R2024b)
Per Observation LossPer observation regression or classification error of incremental model (Desde R2025a)
Update MetricsUpdate performance metrics in incremental learning model given new data (Desde R2023b)

Funciones

expandir todo

Crear un objeto LinearModel

fitlmAjustar un modelo de regresión lineal
stepwiselmPerform stepwise regression

Crear un objeto CompactLinearModel

compactCompact linear regression model

Añadir o eliminar términos de un modelo lineal

addTermsAdd terms to linear regression model
removeTermsRemove terms from linear regression model
stepImprove linear regression model by adding or removing terms

Predecir respuestas

fevalPredict responses of linear regression model using one input for each predictor
predictPredecir respuestas de un modelo de regresión lineal
randomSimular respuestas con ruido aleatorio para un modelo de regresión lineal

Evaluar un modelo lineal

anovaAnalysis of variance for linear regression model
coefCIConfidence intervals of coefficient estimates of linear regression model
coefTestLinear hypothesis test on linear regression model coefficients
dwtestDurbin-Watson test with linear regression model object
partialDependenceCompute partial dependence

Visualizar un modelo lineal y estadísticas descriptivas

plotScatter plot or added variable plot of linear regression model
plotAddedAdded variable plot of linear regression model
plotAdjustedResponseAdjusted response plot of linear regression model
plotDiagnosticsPlot observation diagnostics of linear regression model
plotEffectsPlot main effects of predictors in linear regression model
plotInteractionPlot interaction effects of two predictors in linear regression model
plotPartialDependenceCreate partial dependence plot (PDP) and individual conditional expectation (ICE) plots
plotResidualsPlot residuals of linear regression model
plotSlicePlot of slices through fitted linear regression surface

Recopilar propiedades de un modelo lineal

gatherGather properties of Statistics and Machine Learning Toolbox object from GPU

Crear un objeto CensoredLinearModel

fitlmcensFit censored linear regression model (Desde R2025a)

Crear un objeto CompactCensoredLinearModel

compactCreate compact censored linear regression model (Desde R2025a)

Predecir respuestas

fevalPredict responses of censored linear regression model using one input for each predictor (Desde R2025a)
predictPredict responses of censored linear regression model (Desde R2025a)
randomSimulate responses with random noise for censored linear regression model (Desde R2025a)

Evaluar un modelo lineal censurado

coefCIConfidence intervals of coefficient estimates for censored linear regression model (Desde R2025a)
coefTestLinear hypothesis test on censored linear regression model coefficients (Desde R2025a)
partialDependenceCompute partial dependence

Visualizar un modelo lineal censurado y estadísticas descriptivas

plotPartialDependenceCreate partial dependence plot (PDP) and individual conditional expectation (ICE) plots
plotResidualsPlot residuals of censored linear regression model (Desde R2025a)
plotSlicePlot of slices through fitted censored linear regression surface (Desde R2025a)

Crear un objeto

fitrlinearFit linear regression model to high-dimensional data

Trabajar con un objeto RegressionLinear

predictPredict response of linear regression model
limeLocal interpretable model-agnostic explanations (LIME)
lossRegression loss for linear regression models
partialDependenceCompute partial dependence
plotPartialDependenceCreate partial dependence plot (PDP) and individual conditional expectation (ICE) plots
shapleyShapley values (Desde R2021a)
selectModelsSelect fitted regularized linear regression models

Trabajar con un objeto RegressionPartitionedLinear

kfoldLossRegression loss for cross-validated linear regression model
kfoldPredictPredict responses for observations in cross-validated linear regression model

Crear un objeto

fitrqlinearTrain quantile linear regression model (Desde R2024b)
compactReduce size of machine learning model
crossvalCross-validate machine learning model

Trabajar con un objeto RegressionQuantileLinear o CompactRegressionQuantileLinear

lossLoss for quantile linear regression model (Desde R2024b)
predictPredict response for quantile linear regression model (Desde R2024b)

Trabajar con un objeto RegressionPartitionedQuantileModel

kfoldLossLoss for cross-validated partitioned quantile regression model (Desde R2025a)
kfoldPredictPredict responses for observations in cross-validated quantile regression model (Desde R2025a)
kfoldfunCross-validate function for quantile regression (Desde R2025a)

Ajustar y evaluar una regresión lineal

dwtestDurbin-Watson test with residual inputs
invpredInverse prediction
linhyptestLinear hypothesis test
plsregressPartial least-squares (PLS) regression
regressRegresión lineal múltiple
regstatsDiagnóstico de regresiones
relieffRank importance of predictors using ReliefF or RReliefF algorithm
robustfitFit robust linear regression
stepwisefitFit linear regression model using stepwise regression

Ajuste polinomial de curvas

polyconfPolynomial confidence intervals
polyfitAjuste polinomial de curvas

Preparar los datos

x2fxConvert predictor matrix to design matrix
dummyvarCreate dummy variables

Herramientas interactivas

polytoolInteractive polynomial fitting
robustdemoInteractive robust regression
rsmdemoInteractive response surface demonstration
rstoolInteractive response surface modeling
stepwiseInteractive stepwise regression

Objetos

LinearModelModelo de regresión lineal
CompactLinearModelCompact linear regression model
CensoredLinearModelCensored linear regression model (Desde R2025a)
CompactCensoredLinearModelCompact censored linear regression model (Desde R2025a)
RegressionLinearLinear regression model for high-dimensional data
RegressionPartitionedLinearCross-validated linear regression model for high-dimensional data
RegressionQuantileLinearQuantile linear regression model (Desde R2024b)
CompactRegressionQuantileLinearCompact quantile linear regression model (Desde R2025a)
RegressionPartitionedQuantileModelCross-validated quantile model for regression (Desde R2025a)

Temas

Introducción a la regresión lineal

Flujos de trabajo de las regresiones lineales

Regresión de mínimos cuadrados parciales

  • Partial Least Squares
    Partial least squares (PLS) constructs new predictor variables as linear combinations of the original predictor variables, while considering the observed response values, leading to a parsimonious model with reliable predictive power.
  • Partial Least Squares Regression and Principal Components Regression
    Apply partial least squares regression (PLSR) and principal components regression (PCR), and explore the effectiveness of the two methods.