×

Strong matching of frequentist and Bayesian parametric inference. (English) Zbl 1005.62005

Summary: We define a notion of strong matching of frequentist and Bayesian inference for a scalar parameter, and show that for the special case of a location model strong matching is obtained for any interest parameter linear in the location parameters. Strong matching is defined using one-sided interval estimates constructed by inverting test quantities. A brief survey of methods for choosing a prior, of principles relating to the Bayesian paradigm, and of confidence and related procedures leads to the development of a general location reparameterization. This is followed by a brief survey of recent likelihood asymptotics which provides a basis for examining strong matching to third order in general continuous statistical methods. It is then shown that a flat prior with respect to the general location parameterization gives third-order strong matching for linear parameters; and for nonlinear parameters the strong matching requires an adjustment to the flat prior which is based on the observed Fisher information.
A computationally more accessible approach then uses full dimensional pivotal quantities to generate default priors for linear parameters; this leads to second-order matching. A concluding section describes a confidence, fiducial, or default Bayesian inversion relative to the location parameterization. This provides a method to adjust interval estimates by means of a personal prior taken relative to the flat prior in the location parameterization.

MSC:

62A01 Foundations and philosophical topics in statistics
62F15 Bayesian inference
62F99 Parametric inference
62F12 Asymptotic properties of parametric estimators
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Andrews, D.F., Fraser, D.A.S., Wong, A., 2002. Extended gaussian quadrature and the computation of distribution functions from likelihood functions. Annals Inst. Statist. Math., submitted.; Andrews, D.F., Fraser, D.A.S., Wong, A., 2002. Extended gaussian quadrature and the computation of distribution functions from likelihood functions. Annals Inst. Statist. Math., submitted.
[2] Barndorff-Nielsen, O. E., Inference on full or partial parameters based on the standardized, signed log likelihood ratio, Biometrika, 73, 307-322 (1986) · Zbl 0605.62020
[3] Barndorff-Nielsen, O. E., Modified signed log likelihood ratio statistic, Biometrika, 78, 557-563 (1991) · Zbl 1192.62052
[4] Bayes, T., An essay towards solving a problem in the doctrine of chances, Biometrika, 50, 293-315 (1763)
[5] Birnbaum, A., On the foundations of statistical inference, Amer. Statist. Assoc., 57, 269-306 (1962) · Zbl 0107.36505
[6] Bernardo, J. M., Reference posterior distributions for Bayesian inference, J. Roy. Statist. Soc. B, 41, 113-147 (1979) · Zbl 0428.62004
[7] Bernardo, J. M.; Smith, A. F.M., Bayesian Theory. (1994), Wiley: Wiley Chichester
[8] Cakmak, S., Fraser, D.A.S., McDunnough, P., Reid, N., Yuan, X., 1998. Likelihood centered asymptotic model: exponential and location model versions. J. Statist. Planning Inference 66, 211-222. Some corrections are recorded on the web site http://www.math.yorku.ca/Who/Faculty/AWong.; Cakmak, S., Fraser, D.A.S., McDunnough, P., Reid, N., Yuan, X., 1998. Likelihood centered asymptotic model: exponential and location model versions. J. Statist. Planning Inference 66, 211-222. Some corrections are recorded on the web site http://www.math.yorku.ca/Who/Faculty/AWong. · Zbl 0953.62017
[9] Cakmak, S.; Fraser, D. A.S.; Reid, N., Multivariate asymptotic model: exponential and location model approximation, Utilitas Math., 76, 604-608 (1994) · Zbl 0814.62005
[10] Daniels, H. E., Saddlepoint approximations in statistics, Ann. Math. Statist., 46, 21-31 (1954) · Zbl 0058.35404
[11] Fraser, D. A.S., Local conditional sufficiency, J. Roy. Statist. Soc. B, 26, 52-62 (1964) · Zbl 0128.38403
[12] Fraser, D. A.S., Bayes, likelihood or structural, Ann. Math. Statist., 43, 777-790 (1972) · Zbl 0281.62005
[13] Fraser, D. A.S., Tail probability from observed likelihood, Biometrika, 77, 65-76 (1990) · Zbl 0692.62032
[14] Fraser, D. A.S.; Reid, N., Simple asymptotic connections between densities and cumulant generating function leading to accurate approximations for distribution functions, Statist. Sinica, 3, 67-82 (1993) · Zbl 0831.62016
[15] Fraser, D. A.S.; Reid, N., Ancillaries and third order significance, Utilitas Math., 47, 33-53 (1995) · Zbl 0829.62006
[16] Fraser, D. A.S.; Reid, N., Bayes posteriors for scalar interest parameters, Bayesian Statist., 5, 581-585 (1996)
[17] Fraser, D.A.S., Reid, N., Wu, J., 1998. On the informative presentation of likelihood. Appl. Statist. Sci. III, 253-266. Nova Science, Huntington, New York.; Fraser, D.A.S., Reid, N., Wu, J., 1998. On the informative presentation of likelihood. Appl. Statist. Sci. III, 253-266. Nova Science, Huntington, New York.
[18] Fraser, D.A.S., Reid, N., 2001. Ancillary information for statistical inference. In: Ahmed, E., Reid, N. (Eds.), Empirical Bayes and Likelihood Inference, Springer, Berlin, 185-207.; Fraser, D.A.S., Reid, N., 2001. Ancillary information for statistical inference. In: Ahmed, E., Reid, N. (Eds.), Empirical Bayes and Likelihood Inference, Springer, Berlin, 185-207.
[19] Fraser, D.A.S., Reid, N., Wu, J., 1999a. A simple general formula for tail probabilities for frequentist and Bayesian inference. Biometrika 86, 249-264.; Fraser, D.A.S., Reid, N., Wu, J., 1999a. A simple general formula for tail probabilities for frequentist and Bayesian inference. Biometrika 86, 249-264. · Zbl 0932.62003
[20] Fraser, D.A.S., Wong, A., Wu, J., 1999b. Regression analysis, nonlinear on nonnormal: simple and accurate \(p\); Fraser, D.A.S., Wong, A., Wu, J., 1999b. Regression analysis, nonlinear on nonnormal: simple and accurate \(p\) · Zbl 0998.62059
[21] Fraser, D.A.S., Yi, Y., 2002. Location reparameterization of multivariate models. Jour. Roy. Statist. Soc. B, submitted.; Fraser, D.A.S., Yi, Y., 2002. Location reparameterization of multivariate models. Jour. Roy. Statist. Soc. B, submitted.
[22] Hinkley, D. V., Likelihood as approximate pivotal distribution, Biometrika, 67, 287-292 (1980) · Zbl 0434.62021
[23] Jeffreys, H., An invariant form for the prior distribution in estimation problems, Proc. Roy. Soc. A, 186, 453-461 (1946) · Zbl 0063.03050
[24] Kass, R. E.; Wasserman, L., The selection of prior distributions by formal rules, J. Amer. Stat. Assoc., 435, 1343-1371 (1996) · Zbl 0884.62007
[25] Laplace, P. S., Essai Philsophique sur les Probabilités, Philos. Trans. Roy. Soc. London, 53, 370-418 (1814)
[26] Lugannani, R.; Rice, S. O., Saddlepoint approximation for the distribution of the sums of independent random variables, Adv. Appl. Probab., 12, 475-490 (1980) · Zbl 0425.60042
[27] Peers, H. W., On confidence points and Bayesian probability points in the case of several parameters, J. Roy. Statist. Soc. B, 27, 9-16 (1965) · Zbl 0144.41403
[28] Pratt, J. W., Discussion of Birnbaum (1962), J. Amer. Statist. Assoc., 57, 314-315 (1962)
[29] Tibshirani, R., Noninformative priors for one parameter of many, Biometrika, 76, 604-608 (1993) · Zbl 0678.62010
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.