Abstract
Abstract Model selection and inference are usually treated as separate stages of regression analysis, even though both tasks are performed on the same set of data. Once a model has been selected, one typically proceeds as though one has a fresh data set generated by the selected model. Here, we present Monte Carlo results on the coverage rates of confidence regions for the regression parameters, conditional on the selected model order. The conditional coverage rates are much smaller than the nominal coverage rates, obtained by assuming that the model was known in advance. Furthermore, the overall coverage rate is much smaller than the nominal value. A possible remedy based on data splitting is suggested.
Keywords
InferenceStatisticsModel selectionLinear regressionData setRegression analysisSelection (genetic algorithm)EconometricsRegressionConfidence intervalMathematicsSet (abstract data type)Monte Carlo methodComputer scienceArtificial intelligence
Affiliated Institutions
Related Publications
MCMC Methods for Multi-Response Generalized Linear Mixed Models: The<b>MCMCglmm</b><i>R</i>Package
Generalized linear mixed models provide a flexible framework for modeling a range of data, although with non-Gaussian response variables the likelihood cannot be obtained in clo...
Model Averaging and Bayes Factor Calculation of Relaxed Molecular Clocks in Bayesian Phylogenetics
We describe a procedure for model averaging of relaxed molecular clock models in Bayesian phylogenetics. Our approach allows us to model the distribution of rates of substitutio...
Latent Class Model Diagnosis
Summary. In many areas of medical research, such as psychiatry and gerontology, latent class variables are used to classify individuals into disease categories, often with the i...
Bootstrap Methods: Another Look at the Jackknife
We discuss the following problem: given a random sample $\\mathbf{X} = (X_1, X_2, \\cdots, X_n)$ from an unknown probability distribution $F$, estimate the sampling distribution...
Comparison of Bayesian and maximum-likelihood inference of population genetic parameters
Abstract Comparison of the performance and accuracy of different inference methods, such as maximum likelihood (ML) and Bayesian inference, is difficult because the inference me...
Publication Info
- Year
- 1990
- Type
- article
- Volume
- 44
- Issue
- 3
- Pages
- 214-217
- Citations
- 276
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
276
OpenAlex
Cite This
Clifford M. Hurvich,
Chih‐Ling Tsai
(1990).
The Impact of Model Selection on Inference in Linear Regression.
The American Statistician
, 44
(3)
, 214-217.
https://doi.org/10.1080/00031305.1990.10475722
Identifiers
- DOI
- 10.1080/00031305.1990.10475722