Intermediate efficiency in nonparametric testing problems with an application to some weighted statistics

Inglot, Tadeusz; Ledwina, Teresa; Ćmiel, Bogdan

ESAIM: Probability and Statistics, Tome 23 (2019), pp. 697-738.

Suite au passage du modèle économique de la revue en S20, le texte intégral des articles des années 2019 et 2020 est accessible uniquement sur le site de l'éditeur et est réservé aux abonnés.

The basic motivation and primary goal of this paper is a qualitative evaluation of the performance of a new weighted statistic for a nonparametric test for stochastic dominance based on two samples, which was introduced in Ledwina and Wyłupek [TEST 21 (2012) 730–756]. For this purpose, we elaborate a useful variant of Kallenberg’s notion of intermediate efficiency. This variant is general enough to be applicable to other nonparametric problems. We provide a formal definition of the proposed variant of intermediate efficiency, describe the technical tools used in its calculation, and provide proofs of related asymptotic results. Next, we apply this approach to calculating the intermediate efficiency of the new test with respect to the classical one-sided Kolmogorov–Smirnov test, which is a recognized standard for this problem. It turns out that for a very large class of convergent alternatives the new test is more efficient than the classical one. We also report the results of an extensive simulation study on the powers of the tests considered, which shows that the new variant of intermediate efficiency reflects the exact behavior of the power well.

[1] R.R. Bahadur, Rates of convergence of estimates and test statistics. Ann. Math. Statist. 38 (1967) 303–324. | DOI | MR | Zbl

[2] G.F. Barrett and S.G. Donald, Consistent tests for stochastic dominance. Econometrica 71 (2003) 71–104. | DOI | MR | Zbl

[3] K. Behnen, A characterization of certain rank-order tests with bounds for the asymptotic relative efficiency. Ann. Math. Statist. 43 (1972) 1839–1851. | DOI | MR | Zbl

[4] K. Behnen, Nichtparametrische Statistik: Zweistichproben Rangtests. Z. Angew. Math. Mech. 61 (1981) T203–T212. | MR | Zbl

[5] K. Behnen and G. Neuhaus, Galton’s test as a linear rank test with estimated scores and its local asymptotic efficiency. Ann. Statist. 11 (1983) 588–599. | DOI | MR | Zbl

[6] K. Behnen and G. Neuhaus, Rank Tests with Estimated Scores and Their Application. Teubner, Stuttgart (1989). | DOI | MR | Zbl

[7] A.A. Borovkov and A.A. Mogulskii, Large deviations and statistical invariance principle. Theory Probab. Appl. 37 (1993) 7–13. | DOI | MR | Zbl

[8] M. Csörgő, S. Csörgő, L. Horváth and D.M. Mason, Weighted empirical and quantile processes. Ann. Probab. 14 (1986) 31–85. | DOI | MR | Zbl

[9] G.R. Ducharme and T. Ledwina, Efficient and adaptive nonparametric test for the two-sample problem. Ann. Statist. 31 (2003) 2036–2058. | DOI | MR | Zbl

[10] M.S. Ermakov, Large deviations for empirical probability measures and statistical tests. J. Math. Sci. 81 (1996) 2379–2393. | DOI | MR | Zbl

[11] M.S. Ermakov, On asymptotically efficient statistical inference for moderate deviation probabilities. Theory Probab. Appl. 48 (2004) 622–641. | DOI | MR | Zbl

[12] J. Fan, Test of significance based on wavelet thresholding and Neyman’s truncation. J. Am. Statist. Assoc. 96 (1996) 674–688. | DOI | MR | Zbl

[13] J.-D. Fermanian, D. Radulović and M. Wegkamp, Weak convergence of empirical copula process. Bernoulli 10 (2004) 847–860. | MR | Zbl

[14] P. Groeneboom and G.R. Shorack, Large deviations of goodness of fit statistics and linear combinations of order statistics. Ann. Probab. 9 (1981) 971–987. | DOI | MR | Zbl

[15] M.S. Handcock and M. Morris, Relative Distribution Methods in the Social Sciences. Springer, New York (1999). | MR | Zbl

[16] T. Inglot, Generalized intermediate efficiency of goodness of fit tests. Math. Methods Statist. 8 (1999) 487–509. | MR | Zbl

[17] T. Inglot, On large deviation theorem for data-driven Neyman’s statistic. Statist. Probab. Lett. 47 (2000) 411–419. | DOI | MR | Zbl

[18] T. Inglot, Intermediate efficiency by shifting alternatives and evaluation of power. J. Statist. Plan. Inference 140 (2010) 3263–3281. | DOI | MR | Zbl

[19] T. Inglot, Asymptotic behaviour of linear rank statistics for the two-sample problem. Probab. Math. Statist. 32 (2012) 93–116. | MR | Zbl

[20] T. Inglot and T. Ledwina, On probabilities of excessive deviations for Kolmogorov-Smirnov, Cramér-von Mises and chi-square statistics. Ann. Statist. 18 (1990) 1491–1495. | DOI | MR | Zbl

[21] T. Inglot and T. Ledwina, Moderately large deviations and expansions of large deviations for some functionals of weighted empirical process. Ann. Probab. 21 (1993) 1691–1705. | DOI | MR | Zbl

[22] T. Inglot and T. Ledwina, Asymptotic optimality of data driven Neyman’s tests for uniformity. Ann. Statist. 24 (1996) 1982–2019. | DOI | MR | Zbl

[23] T. Inglot and T. Ledwina, Intermediate approach to comparison of some goodness-of-fit tests. Ann. Inst. Statist. Math. 53 (2001) 810–834. | DOI | MR | Zbl

[24] T. Inglot and T. Ledwina, Intermediate efficiency of some max-type statistics. J. Statist. Plan. Inference 136 (2006) 2918–2935. | DOI | MR | Zbl

[25] L. Jager and J.A. Wellner, On the “Poisson boundaries” of the family of weighted Kolmogorov statistics, in Festschrift for Herman Rubin, edited by A. Dasgupta. IMS, Beachwood, OH (2004) 319–331. | DOI | MR | Zbl

[26] L. Jager and J.A. Wellner, Goodness-of-fit tests via phi-divergences. Ann. Statist. 35 (2007) 2018–2053. | DOI | MR | Zbl

[27] G. Kalish and P.W. Mikulski, The asymptotic behavior of the Smirnov test compared to standard “optimal procedures”. Ann. Math. Statist. 42 (1971) 1742–1747. | DOI | MR | Zbl

[28] W.C.M. Kallenberg, Intermediate efficiency, theory and examples. Ann. Statist. 11 (1983) 1401–1420. | MR | Zbl

[29] W.C.M. Kallenberg, Efficiency, intermediate or Kallenberg, in Encyclopedia of Statistical Sciences, edited by S. Kotz et al., Wiley, New York (1999) 1876–1881.

[30] W.C.M. Kallenberg and A.J. Koning, On Wieand’s theorem. Statist. Probab. Lett. 25 (1995) 113–132. | MR | Zbl

[31] Y. Kitamura, Asymptotic optimality of empirical likelihood for testing moment restrictions. Econometrica 69 (2001) 1661–1672. | DOI | MR | Zbl

[32] S. Klonner, The first-order stochastic dominance ordering of the Singh-Maddala distribution. Econ. Lett. 69 (2000) 123–128. | DOI | MR | Zbl

[33] A.J. Koning, Approximation of stochastic integrals with applications to goodness-of-fit. Ann. Statist. 20 (1992) 428–454. | DOI | MR | Zbl

[34] T. Ledwina, On the limiting Pitman efficiency of some rank tests of independence. J. Multivar. Anal. 20 (1986) 265–271. | DOI | MR | Zbl

[35] T. Ledwina and G. Wyłupek, Nonparametric tests for first order stochastic dominance. TEST 21 (2012) 730–756. | DOI | MR | Zbl

[36] T. Ledwina and G. Wyłupek, Two-sample test against one-sided alternative. Scand. J. Statist. 39 (2012) 358–381. | DOI | MR | Zbl

[37] T. Ledwina and G. Wyłupek, Tests for first-order stochastic dominance. Preprint IM PAN (2013) 746.

[38] D.M. Mason and R.L. Eubank, Moderate deviations and intermediate efficiency for lack-of-fit tests. Statist. Risk Model. 29 (2012) 175–187. | DOI | MR | Zbl

[39] S.M. Mirakhmedov, Asymptotic intermediate efficiency of the chi-square and likelihood ratio goodness of fit tests. Preprint (2016). | arXiv

[40] G. Neuhaus, H₀-contiguity in nonparametric testing problems and sample Pitman efficiency. Ann. Statist. 10 (1982) 575–582. | DOI | MR | Zbl

[41] G. Neuhaus, Local asymptotics for linear rank statistics with estimated score functions. Ann. Statist. 15 (1987) 491–512. | DOI | MR | Zbl

[42] Y. Nikitin, Asymptotic Efficiency of Nonparametric Tests. Cambridge University Press, Cambridge (1995). | DOI | MR | Zbl

[43] E.J.G. Pitman, Notes on Nonparametric Statistical Inference. Institute of Statistics, University of North Carolina, Chapel Hill (1948).

[44] E.J.G. Pitman, Some Basic Theory for Statistical Inference. Wiley, NY (1979). | MR | Zbl

[45] F. Schmid and M. Trede, Testing for first order stochastic dominance: a new distribution-free test. Statistician 45 (1996) 371–380. | DOI

[46] R.J. Serfling, Approximation Theorems of Mathematical Statistics. Wiley, New York (1980). | DOI | MR | Zbl

[47] G.R. Shorack, Probability for Statisticians. Springer, New York (2000). | MR | Zbl

[48] B.K. Sinha and H.S. Wieand, Bounds on the efficiencies of four commonly used nonparametric tests of location. Sankhyā, Ser. B 39 (1977) 121–129. | MR | Zbl

[49] V.S. Tsirel’Son, The density of the distribution of the maximum of a Gaussian process. Theory Probab. Appl. 20 (1975) 847–856. | DOI | Zbl

[50] H.S. Wieand, A condition under which the Pitman and Bahadur approaches to efficiency coincide. Ann. Statist. 4 (1976) 1003–1011. | DOI | MR | Zbl

[51] C.S. Yu, Pitman efficiencies of Kolmogorov-Smirnov tests. Ann. Math. Statist. 42 (1971) 1595–1605. | DOI | MR | Zbl

[52] S. Zacks, Pitman efficiency, in Encyclopedia of Statistical Sciences. Edited by S. Kotz et al. Wiley, New York (2006) 6136–6140.