Bootstrap-based model selection criteria for beta regressions
From MaRDI portal
Abstract: The Akaike information criterion (AIC) is a model selection criterion widely used in practical applications. The AIC is an estimator of the log-likelihood expected value, and measures the discrepancy between the true model and the estimated model. In small samples the AIC is biased and tends to select overparameterized models. To circumvent that problem, we propose two new selection criteria, namely: the bootstrapped likelihood quasi-CV (BQCV) and its 632QCV variant. We use Monte Carlo simulation to compare the finite sample performances of the two proposed criteria to those of the AIC and its variations that use the bootstrapped log-likelihood in the class of varying dispersion beta regressions. The numerical evidence shows that the proposed model selection criteria perform well in small samples. We also present and discuss and empirical application.
Recommendations
- The bootstrap-based selection criteria: an optimal choice for model selection in linear regression
- Asymptotic bootstrap corrections of AIC for linear regression models
- Bootstrap variants of the Akaike information criterion for mixed model selection
- Information criteria for Fay-Herriot model selection
- Model selection criteria in beta regression with varying dispersion
Cites work
- A note on a general definition of the coefficient of determination
- A small-sample correction for the Schwarz SIC model selection criterion.
- An improved Akaike information criterion for state-space model selection
- Asymptotic bootstrap corrections of AIC for linear regression models
- Beta Regression for Modelling Rates and Proportions
- Bootstrap methods: another look at the jackknife
- Bootstrap Model Selection
- Bootstrap variants of the Akaike information criterion for mixed model selection
- Bootstrapping log likelihood and EIC, an extension of AIC
- Cross validation model selection criteria for linear regression based on the Kullback-Leibler discrepancy
- Estimating the dimension of a model
- Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation
- Further analysis of the data by Akaike's information criterion and the finite corrections
- Generalized linear model selection using R^2
- How Biased is the Apparent Error Rate of a Prediction Rule?
- scientific article; zbMATH DE number 3143969 (Why is no real title available?)
- scientific article; zbMATH DE number 47310 (Why is no real title available?)
- scientific article; zbMATH DE number 3635352 (Why is no real title available?)
- scientific article; zbMATH DE number 1219611 (Why is no real title available?)
- scientific article; zbMATH DE number 700041 (Why is no real title available?)
- scientific article; zbMATH DE number 1012992 (Why is no real title available?)
- scientific article; zbMATH DE number 1034043 (Why is no real title available?)
- scientific article; zbMATH DE number 1034048 (Why is no real title available?)
- scientific article; zbMATH DE number 3444596 (Why is no real title available?)
- scientific article; zbMATH DE number 236854 (Why is no real title available?)
- Identification in Parametric Models
- Improved AIC selection strategy for survival analysis
- Improved estimators for a general class of beta regression models
- Improved likelihood inference in beta regression
- Improvements on Cross-Validation: The .632+ Bootstrap Method
- Model selection criteria in beta regression with varying dispersion
- On identifiability of parametric statistical models
- Parametric links for binary choice models: a Fisherian-Bayesian colloquy
- Regression analysis of variates observed on (0, 1): percentages, proportions and fractions
- Regression and time series model selection in small samples
- Regression Model Selection—A Residual Likelihood Approach
- Testing inference in variable dispersion beta regressions
- The model selection criterion AICu.
- The Relationship between Variable Selection and Data Agumentation and a Method for Prediction
- Unifying the derivations for the Akaike and corrected Akaike information criteria.
Cited in
(19)- Bootstrap variants of the Akaike information criterion for mixed model selection
- Bessel regression model: Robustness to analyze bounded data
- Information criteria for Fay-Herriot model selection
- A note on bootstrap model selection criterion
- Bootstrap-based testing inference in beta regressions
- Residual and influence analysis to a general class of simplex regression
- Improved testing inferences for beta regressions with parametric mean link function
- Model selection criteria in beta regression with varying dispersion
- The bootstrap-based selection criteria: an optimal choice for model selection in linear regression
- Beta seasonal autoregressive moving average models
- The comparison study of the model selection criteria on the Tobit regression model based on the bootstrap sample augmentation mechanisms
- Skewness of maximum likelihood estimators in the varying dispersion beta regression model
- Resampling-based prediction intervals in beta regressions under correct and incorrect model specification
- A procedure for variable selection in double generalized linear models
- On nonlinear beta regression residuals
- Bootstrap Bartlett correction in inflated beta regression
- Prediction intervals in the beta autoregressive moving average model
- Log-symmetric regression models: information criteria and application to movie business and industry data with economic implications
- Lasso penalization for high-dimensional beta regression models: computation, analysis, and inference
This page was built for publication: Bootstrap-based model selection criteria for beta regressions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q905106)
