Abstract
The problem of Bayesian nonparametric prediction and statistical inference is formulated and discussed. A solution is proposed based upon A n and H n as in Hill (1968, 1988). This solution gives rise to the posterior distribution of the number of species (or more generally, the number of distinct values) in a finite population of Hill (1968, 1979), and to the posterior distribution of percentiles of the population of Hill (1968). Next, the meaning of parameters in the subjective Bayesian theory of Bruno de Finetti is discussed in connection both with H n and with conventional parametric models. It is argued that the usual sharp distinction between prediction and parametric inference is largely illusory. The finite version of de Finettiās theorem is emphasized for the practice of statistics, with the infinite case used only to obtain approximations and insight.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aitchison, J., and Dunsmore, I. R. (1975), Statistical Prediction Analysis, Cambridge University Press.
Berger, J. (1984), The robust Bayesian viewpoint,ā in Robustness of Bayesian Analysis, J. Kadane, ed., North-Holland: Amsterdam, (with discussion), 321ā372.
Berkson, J. (1938), Some difficulties of interpretation encountered in the application of the chi-square test.ā Journal of the American Statistical Association, 33, 526ā542.
Berliner, L. M., and Hill, B. M. (1988), Bayesian nonparametric survival analysis, Journal of the American Statistical Association, 83, 772ā784 (with discussion).
Blackwell, D., and MacQueen, J. B. (1973), Ferguson distributions via PĆ³lya urn schemes, The Annals of Statistics, 1, 353ā355.
Boender, C. G. E., and Kan, A. H. G. Rinnooy (1987), A multinomial Bayesian approach to the estimation of population and vocabulary size, Biometrika, 74, 849ā856.
Borel, E. (1906), Sur les principes de le thĆ©orie cinĆ©tique des gaz, Annales de lĆcole Normale SupĆ©rieure, 9ā32. Reprinted in Selecta: JubilĆ© Scient de M. Ćmile Borei, Gauthier-Villars, Paris, 1940, 243ā265.
Borel, E. (1914). Introduction GĆ©omĆ©trique Ć Quelques ThĆ©ories Physiques, Gauthier-Villars, Paris.
Box, G. E. P., and Tiao, G. C. (1973), Bayesian Inference in Statistical Analysis, Addison-Wesley, Reading.
Chang, C. (1988), Bayesian Nonparametric Prediction Based on Censored Data, University of Michigan Doctoral Dissertation.
Chen, Wen-Chen (1978), On Zipfās Law, University of Michigan Doctoral Dissertation.
Chen, Wen-Chen (1980), On the weak form of Zipfās law, Journal of Applied Probability, 17, 611ā622.
Chen, Wen-Chen, Hill, B. M., Greenhouse, J., and Fayos, J. (1985). Bayesian analysis of survival curves for cancer patients following treatment (with discussion), in Bayesian Statistics 2, J. M. Bernardo, M. H. DeGroot, D. V. Lindley, A. F. M. Smith eds. North-Holland
de Finetti, B. (1937), La prĆ©vision: ses lois logiques, ses sources subjectives, Annales de lāInstitut Henri PoincarĆ©, 7, 1ā68.
de Finetti, B. (1974). Theory of Probability, Vol 1, London: John Wiley & Sons, Inc.
Dempster, A. P. (1963), On Direct Probabilities, Journal of the Royal Statistical Society B, 25, 100ā114.
Diaconis, P., and Freedman, D. (1980), Finite exchangeable sequences, The Annals of Probability, 8, 745ā764.
Diaconis, P., and Freedman, D. (1981), Partial exchangeability and sufficiency, Proceedings of the Indian Statistical Institute Golden Jubilee International Conference on Statistics: Applications and New Directions, 205ā236.
Dickey, J., and Kadane, J. (1980), Bayesian decision theory and the simplification of models, in Evaluation of Econometric Models, J. Kmenta and J. Ramsey, eds., Academic Press, 245ā268.
Einstein, A. (1921). Geometrie und Erfahrung. J. Springer, Berlin.
Feller, W. (1968), An Introduction to Probability Theory and its Applications, Third Edition, Revised Printing, New York: John Wiley & Sons.
Feller, W. (1971), An Introduction to Probability Theory and its Applications, Vol. 2, Second Edition, New York: John Wiley & Sons.
Ferguson, T. (1973), A Bayesian analysis of some nonparametric problems, The Annals of Statistics, 1, 209ā230.
Fisher, R. A. (1939), Student, Annals of Eugenics, 9, 1ā9.
Fisher, R. A. (1948), Conclusions Fiduciare, Annales de lāInstitut Henri PoincarĆ©, 10, 191ā213.
Fisher, R. A. (1959). Statistical Methods and Scientific Inference, Second Edition, New York: Hafner Publishing Co.
Good, I. J. (1965), The Estimation of Probabilities, MIT Research Monograph No. 30.
Hacking, I. (1967), Slightly more realistic personal probability, Philosophy of Science, 34, 311ā325.
Hartigan, J. (1983), Bayes Theory, New York: Springer-Verlag.
Heath, D., and Sudderth, W. (1976), de Finettiās theorem for exchangeable random variables, The American Statistician, 30, 188ā189.
Hewitt, E., and Savage, L. J. (1955), Symmetric measures on cartesian products, in The Writings of Leonard Jimmie Savage-A Memorial Selection, Published by The American Statistical Association and The Institute of Mathematical Statistics, 1981, 244ā275.
Hill, B. M. (1965), Inference about variance components in the one-way model, Jour. Amer. Statist. Assoc., 58, 918ā932.
Hill, B. M. (1967), Correlated errors in the random model, Journal of the Americann Statistical Association, 62, 1387ā1400.
Hill, B. M. (1968), Posterior distribution of percentiles: Bayes theorem for sampling from a finite population, Journal of the American Statistical Association, 63, 677ā691.
Hill, B. M. (1969), Foundations for the theory of least squares, Journal of the Royal Statistical Society, Series B, 31, 89ā97.
Hill, B. M. (1970), Zipfās law and prior distributions for the composition of a population, Journal of the American Statistical Association, 65, 1220ā1232.
Hill, B. M. (1974a), The rank frequency form of Zipfās law, Journal of the American Statistical Association, 69, 1017ā1026.
Hill, B. M. (1974b), On coherence, inadmissibility and inference about many parameters in the theory of least squares, in Studies in Bayesian Econometrics and Statistics in Honor of L. J. Savage, S. Fienberg and A. Zellner, eds., North Holland, 555ā584.
Hill, B. M. (1975a), A simple general approach to inference about the tail of a distribution, Annals of Statistics, 3, 1163ā1174.
Hill, B. M. (1975b), Aberrant behavior of the likelihood function in discrete cases, Journal of the American Statistical Association, 70, 717ā719.
Hill, B. M. (1977), Exact and approximate Bayesian solutions for inference about variance components and multivariate inadmissibility, in New Developments in the Application of Bayesian Methods, A. Aykac and C. Brumat, eds., North Holland, 129ā152.
Hill, B. M., (1978), Decision theory. In Studies in Statistics, Vol. 19, R.V. Hogg, ed., The Mathematical Association of America, 168ā209.
Hill, B. M. (1979), Posterior moments of the number of species in a finite population, and the posterior probability of finding a new species, Journal of the American Statistical Association, 74, 668ā673.
Hill, B. M. (1980a), Invariance and robustness of the posterior distribution of characteristics of a finite population, with reference to contingency tables and the sampling of species. In Bayesian Analysis in Econometrics and Statistics: Essays in Honor of Harold Jeffreys, ed A. Zellner, North-Holland, 383ā395.
Hill, B. M. (1980b), Robust analysis of the random model and weighted least squares regression, in Evaluation of Econometric Models, ed. by J. Kmenta and J. Ramsey, Academic Press, 197ā217.
Hill, B. M. (1980c), On finite additivity, non-conglomerability, and statistical paradoxes, (with discussion) in Bayesian Statistics, J. M. Bernardo, M. H. Degroot, D. V. Lindley, A. F. M. Smith, eds., University Press: Valencia, Spain, 39ā66.
Hill, B. M. (1981), A theoretical development of the Zipf (Pareto) law, in Studies on Zipfās Laws, ed. by H. Guiter, Sprachwissenschaftliches Institute, Ruhr-Universitat, Bochun.
Hill, B. M. (1985ā86), Some subjective Bayesian considerations in the selection of models, Econometric Reviews 4, No. 2, 191ā288 (with discussion).
Hill, B. M. (1987a), The validity of the likelihood principle, The American Statistician, 41, 95ā100.
Hill, B. M. (1987b), Parametric models for A n: Splitting Processes and Mixtures, Unpublished, Department of Statistics, The University of Michigan.
Hill, B. M. (1988), De Finettiās theorem, induction, and A n, or Bayesian nonparametric predictive inference, in Bayesian Statistics 3, J. M. Bernardo, M. H. Degroot, D. V. Lindley, and A. F. M. Smith, eds., Oxford University Press, 211ā241 (with discussion).
Hill, B. M., (1990a), A theory of Bayesian data analysis, in Bayesian and Likelihood Methods in Statistics and Econometrics: Essays in Honor of George A. Barnard, S. Geisser, J. Hodges, S. J. Press, A. Zellner (Eds.), North-Holland, 1990, 49ā73.
Hill, B. M., (1990b), Bayesian Statistics, in 1990 Yearbook of Encyclopedia of Physical Science and Technology, Academic Press.
Hill, B. M. (1990c), Discussion of An ancillarity paradox that appears in multiple linear regression, by L. D. Brown, in The Annals of Statistics, 1990.
Hill, B. M. (1990d), Dutch books, the Jeffreys-Savage theory of hypothesis testing, and Bayesian reliability. Unpublished technical report, the University of Michigan. Presented at the course-congress on Reliability and Decision Making, Siena, Italy.
Hill, B. M. (1990e), Robustness in Statistics. Unpublished technical report, the University of Michigan.
Hill, B. M. and Lane, David (1985), Conglomerability and countable additivity, SankhyĆ”, 47, Series A, 366ā379.
Hill, B. M., Lane, David, and Sudderth, William (1980), A strong law for some generalized urn processes, Annals of Probability, 8, 214ā226.
Hill, B. M., Lane, David, and Sudderth, William (1987), Exchangeable urn processes, Annals of Probability, 15, 1586ā1592.
Hill, B. M. and Woodroofe, M. (1975), Stronger forms of Zipfās law, Journ al of the American Statistical Association, 70, 212ā219.
Hoppe, F. (1987), The sampling theory of neutral alleles and an urn model in population genetics, Jour. of Mathematical Biology, 25, 123ā159.
Hume, David (1748), An Enquiry Concerning Human Understanding, London.
Ijiri, Y., and Simon, H. A. (1975), Some distributions associated with Bose-Einstein statistics, Proceeding of the National Academy of Science, USA, 72, 1654ā1657.
Jeffreys, H. (1957), Scientific Inference, Second Edition, Cambridge University Press.
Jeffreys, H. (1961), Theory of Probability, Third Edition, Oxford at the Clarendon Press.
Johnson, W. E. (1932), Probability: the deductive and inductive problems, Mind, 49, 409ā423. [Appendix on pages 421ā423 edited by R. B. Braithwaite].
Kingman, J. F. C. (1975), Random discrete distributions, Journal of the Royal Statistical Society, Series B, 37, 1ā22 (with discussion).
Lane, D., and Sudderth, W. (1978), Diffuse models for sampling and predictive inference, Annals of Statistics, 6, 1318ā1336.
Lane, D., and Sudderth, W. (1984), Coherent predictive inference, SankhyĆ” Ser. A, 46, 166ā185.
Lenk, P. (1984), Bayesian Nonparametric Predictive Distributions, Doctoral Dissertation, The University of Michigan.
Lewins, W. A., and Joanes, D. N. (1984), Bayesian estimation of the number of species, Biometrics, 40, 323ā328.
Lindley, D., and Smith, A. F. M. (1972), Bayes estimates for the linear model, Journal of the Royal Statistical Society, Series B, 34, 1ā41.
Luce, R. D., Narens, L. (1987), Measurement scales on the continuum, Science, 236, 1527ā1531.
Mandelbrot, B. B. (1982), The Fractal Geometry of Nature, W. H. Freeman and Co., New York.
PoincarƩ, H. (1912), Calcul des ProbabilitƩs, DeuxiƩme Edition, Gauthier-Villars.
Ramakrishnan, S. and Sudderth, W. (1988), A sequence of coin-toss variables for which the strong law fails, American Mathematical Monthly, 95, 939ā941.
RĆ©nyi, A. (1970), Probability Theory, New York: American Elsevier.
Savage, L. J., 1961. The Subjective Basis of Statistical Practice. Unpublished technical report, Department of Mathematics, University of Michigan.
Savage, L. J. et al., 1962. The Foundations of Statistical Inference. Methuen, London.
Savage, L. J. (1972), The Foundations of Statistics, Second Revised Edition, New York: Dover.
Schervish, M., Seidenfeld, T., and Kadane, J., (1984), The extent of non-conglomerability, Z. f. Wahrscheinlichkeitstheorie, 66, 205ā226.
Smith, A. F. M., (1986), Some Bayesian thoughts on modelling and model choice, The Statistician, 35, 97ā102.
Whitrow, G. J. (1980), The Natural Philosophy of Time, Second Edition, Oxford University Press.
Woodroofe, M. and Hill, B. M. (1975), On Zipfās law, Journal of Applied Probability, 12, 425ā434.
Zabell, S. L. (1982), W. E. Johnsonās sufficientness postulate, The Annals of Statistics, 10, 1091ā1099.
Additional References
Berger, J. (1985), Statistical Decision Theory and Bayesian Analysis, Second Edition, Springer-Verlag.
Berger, J. and Wolpert, R. (1988), The Likelihood Principle, Second Edition, IMS Lecture Notes-Monograph Series.
de Finetti, B. (1975) Theory of Probability, Vol. 1, London: John Wiley & Sons, Inc.
Heath, D., and Sudderth, W. (1978), āOn finitely additive priors, coherence, and extended admissibility,ā Annals Statist., 6, 333ā345.
Hill, B. M. (1980d), Review of Specification Searches, by Edward Learner, Journal of the American Statistical Association, 75, 252ā253.
Kolmogorov, A. N. (1950), Foundations of Probability, New York: Chelsea Publishing Co.
Lindley, D. (1971), Bayesian Statistics, A Review, Philadelphia: SIAM.
Robinson, G. K. (1979). Conditional properties of statistical procedures. Ann. Statist 7, 742ā755.
Samuels, S. (1989), āComment: Who will solve the secretary problem,ā Statistical Science, 4, 289ā229
Scozzafava, R. (1984), āA survey of some common misunderstandings concerning the role and meaning of finitely additive probabilities in statistical inference,ā Statistica, anno XLIV, 21ā45.
Zabell, S. (1988), Comment on āDe Finettiās theorem, induction, and A n, or Bayesian nonparametric predictive inference.ā In Bayesian Statistics 3, J. M. Bernardo, M. H. DeGroot, D. V. Lindley, and A. F. M. Smith, eds., Oxford University Press, 233ā236.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 1992 Springer-Verlag New York, Inc.
About this paper
Cite this paper
Hill, B.M. (1992). Bayesian Nonparametric Prediction and Statistical Inference. In: Goel, P.K., Iyengar, N.S. (eds) Bayesian Analysis in Statistics and Econometrics. Lecture Notes in Statistics, vol 75. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-2944-5_4
Download citation
DOI: https://doi.org/10.1007/978-1-4612-2944-5_4
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-97863-5
Online ISBN: 978-1-4612-2944-5
eBook Packages: Springer Book Archive