Summary
A prior may be noninformative for one parameter at the cost of being informative for another parameter. This leads to the idea of tradeoff priors: priors that give up noninformativity for some parameters to achieve noninformativity for others. We propose a general framework where priors are selected by optimizing a functional with two components. The first component formalizes the requirement that the optimal prior be noninformative for the parameter of interest. The second component is a penalty term that forces the optimizing prior to be close to some target prior. Optimizing such a functional results in a parameterized family of priors from which a specific prior may be selected as the tradeoff prior. An important particular example of such functionals is provided by choosing the first term to be the marginal missing information for the parameter of interest (generalizing Bernardo’s notion of missing information) and the second term to be the relative entropy between the unknown prior and the Jeffreys prior. In this case we find a closed form expression for the tradeoff prior and we make explicit connections with the Berger-Bernardo prior. In particular, we show that under certain conditions, the Berger-Bernardo prior and the Jeffreys prior are special cases of the tradeoff prior. We consider several examples.
Similar content being viewed by others
References
Berger, J. and Bernardo, J. (1989). Estimating the product of means: Bayesian analysis with reference priors.J. Amer. Statist. Assoc. 84, 200–207.
Berger, J. and Bernardo, J. (1992a). On the development of the reference prior method.Bayesian Statistics 4 (J. M. Bernardo, J. O. Berger, A. P. Dawid and A. F. M. Smith, eds.). Oxford: University Press, 35–60, (with discussion).
Berger, J. and Bernardo, J. (1992b). Ordered group reference, priors with application to the multinomial problem.Biometrika,79, 25–37.
Bernardo, J. (1979). Reference posterior distributions for Bayesian inference.J. Roy. Statist. Soc. 41, 113–147, (with discussion).
Clarke, B. and Barron, A. (1990). Bayes and minimax asymptotics of entropy risk.Tech. Rep. 90-11, Dept. of Statistics, Purdue, University.
Clarke, B. and Barron, A. (1994). Jeffreys prior is asymptotically least favorable under entropy risk.J. Statist. Planning and Inference 41, 37–60.
Clarke, B. and Sun, D. (1993) Reference priors under the Chi-squared distance.Tech. Rep. 124, UBC Department of Statistics.
Clarke, B. and Wasserman, L. (1993). Noninformative priors and nuisance parameters.J. Amer. Statist. Assoc. 88, 1427–1432.
Courant, R. and Hilbert, D. (1965).Methods of Mathematical Physics. 1. New York: Interscience.
Cover, T. M. and Thomas J. A. (1991).Elements of Information Theory. New York: Wiley.
Crowder, M. and Sweeting, T. (1989). Bayesian inference for a bivariate binomial.Biometrika 76, 599–604.
Datta, G. and Ghosh, M. (1993). On the invariance of noninformative priors.Tech. Rep. 93-17 University of Georgia, Department of Statistics.
Elsgolts, L. (1970).Differential Equations and the Calculus of Variations. Moscow: Mir.
Ghosh, J. K. and Mukerjee, R. (1992). Noninformative priors.Bayesian Statistics 4 (J. M. Bernardo, J. O. Berger, A. P. Dawid and A. F. M. Smith, eds.) Oxford: University Press, 195–210, (with discussion).
Ibrigamov, I. A. and H’asminsky, R. Z. (1973). On the information contained in a sample about a parameter.2nd Int. Symp. on Info., Theory, 295–309.
Jeffreys, H. (1961).Theory of Probability. (Third edition) Oxford: Clarendon Press.
McCulloch, R. (1989). Local model influence.J. Amer. Statist. Assoc. 84, 473–478.
Mukerjee, R. and Dey, D. K. (1992). Frequentist validity of posterior quantiles in the presence of a nuisance parameter: higher order asymptotics.Tech. Rep. 92-07, Department of Statistics, The University of Connecticut.
Polson, N. (1992). On the expected amount of information from a non-linear model.R. Roy. Statist. Soc.,54, 889–895.
Polson, N. and Wasserman, L. (1990) Prior distributions for the bivariate binomial.Biometrika 77, 901–904.
Tibshirani, R. (1989). Noninformative priors for one parameter of many.Biometrika 76, 604–608.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wasserman, L., Clarke, B. Information tradeoff. Test 4, 19–38 (1995). https://doi.org/10.1007/BF02563101
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02563101