The performance of model averaged tail area confidence intervals

DOI10.1080/03610926.2016.1242741MaRDI QIDQ4595863zbMATH OpenOpenAlexFDO

Authors Rheanna Mainzer, Paul Kabaila, Alan H. Welsh

Publication date 6 December 2017

Published in Communications in Statistics: Theory and Methods (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1512.02764

zbMATH Keywords

model selectionconfidence intervalexpected lengthlinear regressioncoverage probabilityAkaike information criterion (AIC)nominal coveragemodel averaged tail area (MATA)

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Nonparametric tolerance and confidence regions (62G15)

Abstract: We consider the model averaged tail area (MATA) confidence interval proposed by Turek and Fletcher, CSDA, 2012, in the simple situation in which we average over two nested linear regression models. We prove that the MATA for any reasonable weight function belongs to the class of confidence intervals defined by Kabaila and Giri, JSPI, 2009. Each confidence interval in this class is specified by two functions b and s. Kabaila and Giri show how to compute these functions so as to optimize these intervals in terms of satisfying the coverage constraint and minimizing the expected length for the simpler model, while ensuring that the expected length has desirable properties for the full model. These Kabaila and Giri "optimized" intervals provide an upper bound on the performance of the MATA for an arbitrary weight function. This fact is used to evaluate the MATA for a broad class of weights based on exponentiating a criterion related to Mallows' C_P. Our results show that, while far from ideal, this MATA performs surprisingly well, provided that we choose a member of this class that does not put too much weight on the simpler model.

Recommendations

• Exact model averaged tail area confidence intervals
• On the minimum coverage probability of model averaged tail area confidence intervals
• Model-averaged confidence intervals
• Finite sample properties of confidence intervals centered on a model averaged estimator
• Comparison of the frequentist MATA confidence interval with Bayesian model-averaged confidence intervals

Cited in

(15)

• Exact model averaged tail area confidence intervals
• Computation of the expected value of a function of a chi-distributed random variable
• Confidence intervals centred on bootstrap smoothed estimators: an impossibility result
• Confidence intervals centred on bootstrap smoothed estimators
• An alternative to confidence intervals constructed after a Hausman pretest in panel data
• Confidence intervals in general regression models that utilize uncertain prior information
• Two sources of poor coverage of confidence intervals after model selection
• Comparison of the frequentist MATA confidence interval with Bayesian model-averaged confidence intervals
• Model-averaged confidence intervals
• Transformation-based model averaged tail area inference
• Model averaged tail area confidence intervals in nested linear regression models
• On the minimum coverage probability of model averaged tail area confidence intervals
• Finite sample properties of confidence intervals centered on a model averaged estimator
• Frequentist model averaging in structure equation model with ordinal data
• On confidence intervals centred on bootstrap smoothed estimators

This page was built for publication: The performance of model averaged tail area confidence intervals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4595863)