On a better lower bound for the frequentist probability of coverage of Bayesian credible intervals in restricted parameter spaces. (English) Zbl 1487.62022
Summary: For estimating a lower restricted parametric function in the framework of É. Marchand and W. E. Strawderman [IMS Lect. Notes, Monogr. Ser. 50, 112–126 (2006; Zbl 1268.62033)], we show how \((1-\alpha)\times 100\%\) Bayesian credible intervals can be constructed so that the frequentist probability of coverage is no less than \(1-\frac{3\alpha}{2}\). As in [É. Marchand and W. E. Strawderman, Electron. J. Stat. 7, 1419–1431 (2013; Zbl 1336.62097)], the findings are achieved through the specification of the spending function of the Bayes credible interval and apply to an “equal-tails” modification of the HPD procedure among others. Our results require a logconcave assumption for the distribution of a pivot, and apply to estimating a lower bounded normal mean with known variance, and to further examples include lower bounded scale parameters from Gamma, Weibull, and Fisher distributions, with the latter also applicable to random effects analysis of variance.
MSC:
| 62F15 | Bayesian inference |
| 62F25 | Parametric tolerance and confidence regions |
| 62C10 | Bayesian problems; characterization of Bayes procedures |
| 62F30 | Parametric inference under constraints |
Keywords:
Bayesian methods; credible sets; frequentist coverage probability; Fisher; gamma; lower bound; random effects; restricted parameter; spending function; WeibullReferences:
| [1] | Bagnoli, M.; Bergstrom, T., Log-concave probability and its applications, Econom. Theory, 26, 445-469 (2005) · Zbl 1077.60012 |
| [2] | Berger, J. O., Statistical Decision Theory and Bayesian Analysis (1985), Springer-Verlag: Springer-Verlag New York · Zbl 0572.62008 |
| [5] | Ghashim, E., Une classe d’intervalles bayésiens pour des espaces de paramètres restreints (2013), Département de mathématiques, Université de Sherbrooke, (http://savoirs.usherbrooke.ca/handle/11143/52) |
| [6] | Lindley, D. V., Fiducial distributions and Bayes’ theorem, J. R. Stat. Soc. Ser. B, 20, 102-107 (1958) · Zbl 0085.35503 |
| [7] | Mandelkern, M., Setting Confidence Intervals for Bounded Parameters with discussion, Statist. Sci., 17, 149-172 (2002) · Zbl 1013.62028 |
| [8] | Marchand, E.´; Strawderman, W. E., On the behaviour of Bayesian credible intervals for some restricted parameter space problems, (Recent Developments in Nonparametric Inference and Probability: A Festschrift for Michael Woodroofe. Recent Developments in Nonparametric Inference and Probability: A Festschrift for Michael Woodroofe, IMS Lecture Notes-Monograph Series, vol. 50 (2006)), 112-126 · Zbl 1268.62033 |
| [9] | Marchand, E.´; Strawderman, W. E., On Bayesian credible sets in restricted parameter space problems and lower bounds for frequentist coverage, Electron. J. Stat., 7, 1419-1431 (2013) · Zbl 1336.62097 |
| [10] | Marchand, E.´; Strawderman, W. E.; Bosa, K.; Lmoudden, A., On the frequentist coverage of Bayesian credible intervals for lower bounded means, Electron. J. Stat., 2, 1028-1042 (2008) · Zbl 1320.62040 |
| [11] | Rahman, M. S.; Gupta, R. P., Family of transformed chi-square distributions, Comm. Statist. Theory Methods, 22, 135-146 (1993) · Zbl 0777.62020 |
| [12] | Roe, B.; Woodroofe, M., Setting confidence belts, Phys. Rev. D, 63, Article 013009 pp. (2000) |
| [13] | Zhang, T.; Woodroofe, M., Credible and confidence sets for the ratio of variance components in the balanced one-way model, Sankhyā, 64, 545-560 (2002), Special issue in memory of D. Basu · Zbl 1192.62173 |
| [14] | Zhang, T.; Woodroofe, M., Credible and confidence sets for restricted parameter spaces, J. Statist. Plann. Inference, 115, 479-490 (2003) · Zbl 1030.62019 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
