On an application of the Student distribution

V. E. Bening   ; V. Yu. Korolev

Teoriâ veroâtnostej i ee primeneniâ, Tome 49 (2004) no. 3, pp. 417-435

Résumé

This paper deals with the mathematical basis of the possibility of using a Student distribution in problems of descriptive statistics. We especially separate the case where the Student distribution parameter (“the number of degrees of freedom”) is small. We show that the Student distribution with arbitrary “number of degrees of freedom” can be obtained as the limit when the sample size is random. We emphasize the possibility of using a family of Student distributions as a comfortable model with heavy tails since in this case many relations, in particular, a likelihood function, have the explicit form (unlike stable laws). As an illustration of the possibilities of statistical analysis based on the family of Student distributions, we consider a problem of statistical estimation of the center of the Student distribution under the assumption that the parameter of the form (the number of degrees of freedom) is known. We consider equivariant estimators of the center of the Student distribution based on order statistics, M-estimators, and maximum likelihood estimators, calculate their asymptotic relative efficiency, and study the behavior of the Student distribution when “the number of degrees of freedom” tends to zero.

Détail

Keywords: asymptotic normality, sample of a random size, Student distribution, asymptotic relative efficiency.

Bibliographie

[1] By Student, “On the probable error of the mean”, Biometrika, 6:1 (1908), 1–25 | DOI

[2] Praetz P. D., “The distribution of share prices changes”, J. Business, 45 (1972), 49–55 | DOI

[3] Blattberg R., Gonedes N., “A comparison of the stable and Student distributions as statistical models of stock prices”, J. Business, 47 (1974), 244–250 | DOI

[4] Korolev V. Yu., “Skhodimost sluchainykh posledovatelnostei s nezavisimymi sluchainymi indeksami. I”, Teoriya veroyatn. i ee primen., 39:2 (1994), 313–333 | MR | Zbl

[5] Korolev V. Yu., “Skhodimost sluchainykh posledovatelnostei s nezavisimymi sluchainymi indeksami. II”, Teoriya veroyatn. i ee primen., 40:4 (1995), 907–910 | MR | Zbl

[6] Korolev V. Yu., “A general theorem on the limit behavior of superpositions of independent random processes with applications to Cox processes”, J. Math. Sci., 81:5 (1996), 2951–2956 | DOI | MR | Zbl

[7] Zolotarev V. M., Odnomernye ustoichivye raspredeleniya, Nauka, M., 1983, 304 pp. | MR

[8] Uchaikin V. V., Zolotarev V. M., Chance and Stability. Stable Distributions and Their Applications, VSP, Utrecht, 1999, 570 pp. | MR | Zbl

[9] Gnedenko B. V., “Ob otsenivanii neizvestnykh parametrov raspredelenii po sluchainomu chislu nezavisimykh nablyudenii”, Teoriya veroyatnostei i matematicheskaya statistika, Trudy Tbilisskogo matematicheskogo instituta im. A. M. Razmadze, 1989, 146–150 | MR | Zbl

[10] Gurland J., “Some interrelations among compound and generalized distributions”, Biometrika, 44 (1957), 265–268 | Zbl

[11] Quenouille M. H., “A relation between the logarithmic, Poisson, and negative binomial series”, Biometrics, 5 (1949), 162–164 | DOI | MR

[12] Kendall M. Dzh., Styuart A., Teoriya raspredelenii, Nauka, M., 1966, 587 pp. | MR | Zbl

[13] Greenwood M., Udny Yule G., “An inquiry into the nature of frequency-distributions of multiple happenings, etc.”, J. Roy. Statist. Soc., 83 (1920), 255–279 | DOI

[14] Bickel P. J., “On some robust estimates of location”, Ann. Math. Statist., 36:3 (1965), 847–858 | DOI | MR | Zbl

[15] Leman E., Teoriya tochechnogo otsenivaniya, Nauka, M., 1991, 443 pp. | MR

[16] Ibragimov I. A., Khasminskii R. Z., Asimptoticheskaya teoriya otsenivaniya, Nauka, M., 1979, 527 pp. | MR

[17] Stone C. J., “Asymptotic properties of estimators of a location parameter”, Ann. Statist., 2 (1974), 1127–1137 | DOI | MR | Zbl

[18] Port S. C., Stone C. J., “Fisher information and the Pitman estimator of a location parameter”, Ann. Statist., 2 (1974), 225–247 | DOI | MR | Zbl

[19] Serfling R. J., Approximation Theorems of Mathematical Statistics, Wiley, New York, 1980, 371 pp. | MR | Zbl

[20] Hodges J. L., Lehmann E. L., “Estimates of location based on rank tests”, Ann. Math. Statist., 34 (1963), 598–611 | DOI | MR | Zbl

[21] Albers W., Bickel P. J., van Zwet W. R., “Asymptotic expansions for the power of distribution free tests in the one-sample problem”, Ann. Statist., 4:1 (1976), 108–156 | DOI | MR | Zbl

[22] Helmers R., Edgeworth Expansions for Linear Combinations of Order Statistics, Mathematisch Centrum, Amsterdam, 1984, 137 pp. | MR

[23] Huber P. J., “Robust estimation of a location parameter”, Ann. Math. Statist., 35:1 (1964), 73–101 | DOI | MR | Zbl

[24] Feller V., Vvedenie v teoriyu veroyatnostei i ee prilozheniya, v. 2, Mir, M., 1984, 746 pp.

[25] Dvait G. B., Tablitsy integralov i drugie matematicheskie formuly, Nauka, M., 1977, 224 pp.

[26] Kapur J. N., Maximum-Entropy Models in Science and Engineering, Wiley, New York, 1989, 635 pp. | MR | Zbl

[27] Tsallis C., de Souza A. M. C., Maynard R., “Derivation of Lévy-type anomalous superdiffusion from general statistical mechanics”, Lévy Flights and Related Topics in Physics, eds. M. F. Shlesinger, G. M. Zaslavsky, and U. Frisch, Springer-Verlag, Berlin, 1995, 269–289 | MR | Zbl

[28] Hill B. M., “A simple general approach to inference about the tail of a distribution”, Ann. Statist., 3 (1975), 1163–1174 | DOI | MR | Zbl

[29] Resnick S. I., “Heavy tail modeling and teletraffic data”, Ann. Statist., 25:5 (1997), 1805–1869 | DOI | MR | Zbl

[30] Embrechts P., Klüppelberg C., Mikosch T., Modeling Extremal Events for Insurance and Finance, Springer-Verlag, Berlin, 1997, 645 pp. | MR | Zbl

[31] Petrov V. V., Summy nezavisimykh sluchainykh velichin, Nauka, M., 1972 | MR

[32] Teicher H., “Identifiability of mixtures”, Ann. Math. Statist., 32 (1961), 244–248 | DOI | MR | Zbl