Further properties of frequentist confidence intervals in regression that utilize uncertain prior information
From MaRDI portal
Publication:2802848
DOI10.1111/ANZS.12038zbMATH Open1335.62116arXiv1111.2113OpenAlexW2040018716MaRDI QIDQ2802848FDOQ2802848
Authors: Khageswor Giri, Paul Kabaila 
Publication date: 27 April 2016
Published in: Australian \& New Zealand Journal of Statistics (Search for Journal in Brave)
Abstract: Consider a linear regression model with n-dimensional response vector, regression parameter �eta = (�eta_1, ..., �eta_p) and independent and identically N(0, sigma^2) distributed errors. Suppose that the parameter of interest is heta = a^T �eta where a is a specified vector. Define the parameter au = c^T �eta - t where c and t are specified. Also suppose that we have uncertain prior information that au = 0. Part of our evaluation of a frequentist confidence interval for heta is the ratio (expected length of this confidence interval)/(expected length of standard 1-alpha confidence interval), which we call the scaled expected length of this interval. We say that a 1-alpha confidence interval for heta utilizes this uncertain prior information if (a) the scaled expected length of this interval is significantly less than 1 when au = 0, (b) the maximum value of the scaled expected length is not too much larger than 1 and (c) this confidence interval reverts to the standard 1-alpha confidence interval when the data happen to strongly contradict the prior information. Kabaila and Giri, 2009, JSPI present a new method for finding such a confidence interval. Let hat�eta denote the least squares estimator of �eta. Also let hatTheta = a^T hat�eta and hat au = c^T hat�eta - t. Using computations and new theoretical results, we show that the performance of this confidence interval improves as |Corr(hatTheta, hat au)| increases and n-p decreases.
Full work available at URL: https://arxiv.org/abs/1111.2113
Recommendations
- Confidence intervals in regression that utilize uncertain prior information about a vector parameter
- Confidence intervals in regression utilizing prior information
- A comparison of Bayesian and frequentist interval estimators in regression that utilize uncertain prior information
- Confidence intervals for the normal mean utilizing prior information
- Confidence intervals utilizing prior information in the Behrens-Fisher problem
Linear regression; mixed models (62J05) Parametric tolerance and confidence regions (62F25) Analysis of variance and covariance (ANOVA) (62J10)
Cites Work
- Confidence intervals in regression utilizing prior information
- Confidence intervals utilizing prior information in the Behrens-Fisher problem
- Theory of Preliminary Test and Stein‐Type Estimation With Applications
- Title not available (Why is that?)
- Numerical Specification of Discrete Least Favorable Prior Distributions
- Admissibility of the usual confidence interval in linear regression
- Employing vague prior information in the construction of confidence sets
- Controlling risks under different loss functions: The compromise decision problem
Cited In (10)
- Confidence intervals for the normal mean utilizing prior information
- Computation of the expected value of a function of a chi-distributed random variable
- Lower bounds on integrated risk, subject to inequality constraints
- Confidence intervals centred on bootstrap smoothed estimators: an impossibility result
- Confidence intervals in regression that utilize uncertain prior information about a vector parameter
- Confidence intervals in general regression models that utilize uncertain prior information
- Two sources of poor coverage of confidence intervals after model selection
- A comparison of Bayesian and frequentist interval estimators in regression that utilize uncertain prior information
- Confidence intervals in regression utilizing prior information
- On confidence intervals centred on bootstrap smoothed estimators
This page was built for publication: Further properties of frequentist confidence intervals in regression that utilize uncertain prior information
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2802848)
