Abstract
In this paper, we study adaptive tests for the one-sample problem. The limit of the normalized difference between the power of a given adaptive test and that of the most powerful test is found. This limit directly yields the Hodges-Lehmann asymptotic deficiency of corresponding adaptive tests. Here adaptation means that the efficient score function of the test is estimated from the sample. A Fourier series estimator is used for the score function.
Similar content being viewed by others
References
V. E. Bening, “On asymptotic efficiency and deficiency of some adaptive tests in the one-sample problem”,J. Math. Sci.,81, No. 5, 2894–2899 (1996).
V. E. Bening, “A formula for deficiency: one sampleL- andR-tests 1”,Math. Meth. Statist.,4, 167–188 (1995).
J. L. Jr. Hodges and E. L. Lehmann, “Deficiency”,Ann. Math. Statist.,41, 783–801 (1970).
R. Beran, “Asymptotically efficient adaptive rank estimates in location models”,Ann. Statist.,2, 63–74 (1974).
J. Hájek and Z. Šidak,Theory of Rank Tests, Academia, Prague (1967).
A. N. Kolmogoroff, “Zur Grössenordnung des restgliedes Fourierschen Reihen differenzierbarer Funktionen”,Ann. Math.,36, 521–526 (1935).
V. V. Petrov,Sums of Independent Random Variables, Springer, Berlin (1975).
N. K. Bary,Treatise on Trigonometric Series, Vol. 1, 2, Pergamon Press, New York (1964).
P. Billingsley,Convergence of Probability Measures, Wiley, New York (1968).
A. N. Shirjayev,Wahrscheinlichkeit, Berlin (1988).
Author information
Authors and Affiliations
Additional information
Supported by the Russian Foundation for Fundamental Research (grant No. 93-011-1446).
Proceedings of the Seminar on Stability Problems for Stochastic Models, Moscow, Russia, 1996, Part I.
Rights and permissions
About this article
Cite this article
Bening, V.E. On the power of some adaptive tests in the one-sample problem. J Math Sci 89, 1468–1485 (1998). https://doi.org/10.1007/BF02362282
Issue Date:
DOI: https://doi.org/10.1007/BF02362282