The Statistical Analysis of Gaussian and Poisson Signals Near Physical Boundaries
arXiv:hep-ex/9910041 · doi:10.1063/1.533433
Abstract
We propose a construction of frequentist confidence intervals that is effective near unphysical regions and unifies the treatment of two-sided and upper limit intervals. It is rigorous, has coverage, is computationally simple and avoids the pathologies that affect the Likelihood Ratio and related constructions. Away from non-physical regions, the results are exactly the usual central two-sided intervals. The construction is based on including the physical constraint in the derivation of the estimator, leading to an estimator with values that are confined to the physical domain.
20 pages, 4 figures. In press:JMP
References in corpus (1)
Cited by in corpus (7)
- Inference for bounded parameters
- Confidence intervals with a priori parameter bounds
- Are there nu_mu or nu_tau in the flux of solar neutrinos on earth?
- Optimal inferential models for a Poisson mean
- The Power of Confidence Intervals
- The Physical Significance of Confidence Intervals
- What is the Usefulness of Frequentist Confidence Intervals?