Selecting the best linear regression model. A classical approach
Parmi les différentes voies d'étude de ce problème classique, l'option adoptée ici est la suivante: on compare deux modèles de régression linéaire (sous hypothèse normale principalement) en testant une hypothèse d'équivalence selon un critère qui est ici celui de Kullback-Leibler (on évalue \(E^ 0 (Log h^ 0(y| x)/f(y| x;\theta))\) où \(E^ 0\) désigne l'espérance par rapport à la distribution conjointe ``vraie de (y,x), \(h^ 0\) la densité conditionnelle vraie, f la densité conditionnelle postulée dont le paramètre \(\theta\) est optimisé). Le premier cas étudié est celui où les deux modèles sont supposés incorrectement spécifiés; puis celui où il existe un modèle correctement spécifié qui les contient tous deux, enfin celui où l'un des deux est correctement spécifié. Les résultats fournis sont essentiellement asymptotiques. Ils sont établis dans une autre publication.
- scientific article; zbMATH DE number 4011695
- Estimation in a linear regression model under the Kullback-Leibler loss and its application to model selection
- scientific article; zbMATH DE number 4032843
- scientific article; zbMATH DE number 3883442
- Inference after separated hypotheses testing: an empirical investigation for linear models
- A Biometrics Invited Paper. The Analysis and Selection of Variables in Linear Regression
- Estimating the dimension of a model
- Generalized inverses and asymptotic properties of Wald tests
- Generalized Inverses, Wald's Method, and the Construction of Chi-Squared Tests of Fit
- scientific article; zbMATH DE number 3444596 (Why is no real title available?)
- scientific article; zbMATH DE number 3213229 (Why is no real title available?)
- scientific article; zbMATH DE number 3249515 (Why is no real title available?)
- scientific article; zbMATH DE number 3320085 (Why is no real title available?)
- scientific article; zbMATH DE number 3350922 (Why is no real title available?)
- scientific article; zbMATH DE number 3357756 (Why is no real title available?)
- scientific article; zbMATH DE number 3390199 (Why is no real title available?)
- Information Criteria for Discriminating Among Alternative Regression Models
- Likelihood Ratio Tests for Model Selection and Non-Nested Hypotheses
- Maximum Likelihood Estimation of Misspecified Models
- Model specification tests against non-nested alternatives
- On Information and Sufficiency
- On the comprehensive method of testing non-nested regression models
- On the General Problem of Model Selection
- Regularity conditions for Cox's test of non-nested hypotheses
- Selecting the best linear regression model. A classical approach
- Selection of Regressors
- Several Tests for Model Specification in the Presence of Alternative Hypotheses
- Some Comments on C P
- Testing Non-Nested Nonlinear Regression Models
- The Selection of Variates for Use in Prediction with Some Comments on the General Problem of Nuisance Parameters
- Using Least Squares to Approximate Unknown Regression Functions
- Selecting the best linear regression model. A classical approach
- Improving robust model selection tests for dynamic models
- Selection of regressors in econometrics: parametric and nonparametric methods selection of regressors in econometrics
- Model selection tests for nonlinear dynamic models
- Chi-squared tests for evaluation and comparison of asset pricing models
- Best-subset model selection based on multitudinal assessments of likelihood improvements
- Geometry of the log-likelihood ratio statistic in misspecified models
- Some selection criteria for nested binary choice models: a comparative study
This page was built for publication: Selecting the best linear regression model. A classical approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1094044)
