Summary
If we are interested in making inferences about the square norm of the mean in a multivariate normal model, the usual uniform prior for the mean is not sound, as revealed by Stein in his 1959 work.
This paper studies in what sense this prior must be modified by using the maximization of missing information procedure (Bernardo, 1979).
Resumen
Stein (1959), en su artículo sobre la gran discrepancia entre intervalos de confianza e intervalos fiduciales, puso de relieve el comportamiento poco convincente de la distribución inicial uniforme para el vector de medias de una normal multivariante si nuestro interés se centra en hacer inferencias sobre el cuadrado de su norma.
En este artículo, utilizando el método de maximización de la información desconocida (Bernardo, 1979), se estudia en qué sentido la distribución inicial del vector de medias debe ser “corregida” mediante la obtención de la distribución inicial mínimo-informativa para el cuadrado de su norma y se exponen los resultados a que dicha corrección conduce.
Similar content being viewed by others
Referencias
ABRAMOWITZ, M. & STEGUN, I.A. (1965/72).Handbook of Mathematical Functions. New York: Dover.
ANDERSON, T.W. (1958/74).An Introduction to Multivariate Statistical Analysis. New York: John Wiley & Sons.
BERNARDO, J.M. (1979). “Reference Posterior Distributions for Bayesian Inference”. (with Discussion).J. Roy. Statist. Soc., Ser B, 41, 113–147.
COX, D.R. & HINKLEY, D.V. (1974).Theoretical Statistics. London: Chapman & Hall.
DAWID, A.P., STONE, M. & ZIDEK, J.V.. (1973). “Marginalization Paradoxes in Bayesian and Structural Inference”.J. Roy. Statist. Soc., Ser. B, 35, 189–233.
JAYNES, E.T. (1980). “Marginalization and Prior Probabilities”, enBayesian Analysis in Econometrics and Statistics (Zellner A. ed.). Amsterdam: North Holland.
JOHNSON, N.L. & KOTZ, S. (1970).Continuous Univariate Distributions Vol. 2. New York: Houghton Mifflin.
KENDALL, M.G. & STUART, A. (1963/68).The Advanced Theory of Statistics, vol. 2. London: Charles Griffin & Co.
LINDLEY, D.V. (1956). “On a Measure of Information Provided by an Experiment”.Ann. Math. Statist., 27, 986–1005.
STEIN, C. (1956). “Inadmissibility of the Usual Estimator for the Mean of a Multivariate Normal Distribution”, enProc. III Berkeley Symp. 1, 197–206.
STEIN, C. (1959). “An Example of Wide Discrepancy Between Fiducial and Confidence Interval”.Ann. Math. Statist., 30, 877–880.
STEIN, C. (1962). “Confidence Stes for the Mean of a Multivariate Normal Distribution”.J. Roy. Statist. Soc., Ser. B, 24, 265–296.
WALKER, D.M. (1969). “On the Asymptotic Behaviour of a Posterior Distribution”.J. Roy. Statist. Soc., Ser. B, 31, 80–88.
WILKINSON, G.N. (1977). “On resolving the Controversy in Statistical Inference”.J. Roy. Statist. Soc., Ser. B, 39, 119–171.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ferrándiz, J.R. Una solucion bayesiana a la Paradoja de Stein. Trabajos de Estadistica Y de Investigacion Operativa 33, 31–46 (1982). https://doi.org/10.1007/BF02888621
Issue Date:
DOI: https://doi.org/10.1007/BF02888621