Regresión no lineal

Modelos de regresión de efectos mixtos y fijos no lineales

En un modelo de regresión no lineal, la variable de respuesta no necesita expresarse como una combinación lineal de las variables predictoras y los coeficientes del modelo. Puede realizar una regresión no lineal con o sin el objeto `NonLinearModel` o usando la herramienta interactiva `nlintool`.

Funciones

expandir todo

 `fitnlm` Ajustar un modelo de regresión no lineal `feval` Evaluate nonlinear regression model prediction `predict` Predict response of nonlinear regression model `random` Simulate responses for nonlinear regression model `partialDependence` Compute partial dependence (desde R2020b) `plotPartialDependence` Create partial dependence plot (PDP) and individual conditional expectation (ICE) plots `plotResiduals` Plot residuals of nonlinear regression model
 `nlinfit` Regresión no lineal `nlintool` Interactive nonlinear regression `nlparci` Intervalos de confianza de los parámetros de regresión no lineal `nlpredci` Nonlinear regression prediction confidence intervals
 `nlmefit` Nonlinear mixed-effects estimation `nlmefitsa` Fit nonlinear mixed-effects model with stochastic EM algorithm
 `dummyvar` Create dummy variables `hougen` Modelo Hougen-Watson `statset` Create statistics options structure `statget` Access values in statistics options structure

Objetos

 `NonLinearModel` Nonlinear regression model

Temas

Efectos mixtos

• Mixed-Effects Models
Mixed-effects models account for both fixed effects (which represent population parameters, assumed to be the same each time data is collected) and random effects (which act like additional error terms).
• Mixed-Effects Models Using nlmefit and nlmefitsa
Fit a mixed-effects model, plot predictions and residuals, and interpret the results.
• Examining Residuals for Model Verification
Examine the `stats` structure, which is returned by both `nlmefit` and `nlmefitsa`, to determine the quality of your model.