Bahadur efficiency of EDF based normality tests when parameters are estimated

B. Milošević   ; Ya. Yu. Nikitin   ; M. Obradović

Zapiski Nauchnykh Seminarov POMI, Probability and statistics. Part 30, Tome 501 (2021), pp. 203-217

Résumé

In this paper some well-known tests based on empirical distribution functions (EDF) with estimated parameters for testing composite normality hypothesis are revisited, and some new results on asymptotic properties are provided. In particular, the approximate Bahadur slopes are obtained – in the case of close alternatives — for the EDF-based tests as well as the likelihood ratio test. The local approximate efficiencies are calculated for several close alternatives. The obtained results could serve as a benchmark for evaluation of the quality of recent and future normality tests.

Bibliographie

[1] T. W. Anderson, D. A. Darling, “Asymptotic theory of certain “goodness of fit” criteria based on stochastic processes”, Ann. Math. Stat., 23:2 (1952), 193–212 | DOI | Zbl

[2] M. A. Arcones, “On the Bahadur slope of the Lilliefors and the Cramér-von Mises tests of normality”, Lecture Notes-Monograph Series, 51, 2006, 196–206 | DOI | MR | Zbl

[3] R. R. Bahadur, “Stochastic comparison of tests”, Ann. Math. Stat., 31:2 (1960), 276–295 | DOI | Zbl

[4] R. R. Bahadur, “Rates of convergence of estimates and test statistics”, Ann. Math. Stat., 38:2 (1967), 303–324 | DOI | Zbl

[5] P. Billingsley, Convergence of probability measures, John Wiley Sons, 1999

[6] V. Božin, B. Milošević, Ya. Yu. Nikitin, M. Obradović, “New characterization-based symmetry tests”, Bull. Malaysian Math. Sci. Soc., 43:1 (2020), 297–320 | DOI | MR | Zbl

[7] M. Cuparić, B. Milošević, Ya. Yu. Nikitin, M. Obradović, “Some consistent exponentiality tests based on Puri–Rubin and Desu characterizations”, Appl. Math. Prague, 65:3 (2020), 245–255 | DOI | Zbl

[8] D. A. Darling, “The Cramer-Smirnov test in the parametric case”, Ann. Math. Stat., 26:1 (1955), 1–20 | DOI | MR | Zbl

[9] D. A. Darling, “The Kolmogorov-Smirnov, Cramer-von Mises tests”, Ann. Math. Stat., 28:4 (1957), 823–838 | DOI | MR | Zbl

[10] D. A. Darling, “On the asymptotic distribution of Watson's statistic”, Ann. Stat., 11:4 (1983), 1263–1266 | DOI | Zbl

[11] D. A. Darling, “On the supremum of a certain Gaussian process”, Ann. Probab., 11:3 (1983), 803–806 | DOI | MR | Zbl

[12] J. Durbin, “Weak convergence of the sample distribution function when parameters are estimated”, Ann. Stat., 1:2 (1973), 279–290 | DOI | Zbl

[13] N. Henze and T. Wagner, “A new approach to the {BHEP} tests for multivariate normality”, J. Multivar. Annal., 62:1 (1997), 1–23 | DOI | Zbl

[14] H. K. Iverson, R. H. Randles, “The effects on convergence of substituting parameter estimates into U-statistics and other families of statistics”, Probab. Theory Relat. Fields, 81:3 (1989), 453–471 | DOI | Zbl

[15] M. Kac, J. Kiefer, J. Wolfowitz, “On tests of normality and other tests of goodness of fit based on distance methods”, Ann. Math. Stat., 26:2 (1955), 189–211 | DOI | Zbl

[16] E. V. Khmaladze, “Martingale approach in the theory of goodness-of-fit tests”, Theory Probab. its Appl., 26:2 (1982), 240–257 | DOI | Zbl

[17] A. N. Kolmogorov, “Sulla determinazione empirica di una legge di distribuzione”, Giorn. Ist. Ital. Attuari, 4:1 (1933), 83–91

[18] N. H. Kuiper, “Tests concerning random points on a circle”, Proc. Sect. Sci. K. Ned. Akad. Wet. Amst. Series A, 63:1 (1960), 38–47 | Zbl

[19] H. W. Lilliefors, “On the Kolmogorov-Smirnov test for normality with mean and variance unknown”, J. Am. Stat. Assoc., 62:318 (1967), 399–402 | DOI

[20] H. W. Lilliefors, “On the Kolmogorov-Smirnov test for the exponential distribution with mean unknown”, J. Am. Stat. Assoc., 64:325 (1969), 387–389 | DOI

[21] M. B. Marcus, L. A. Shepp, “Sample behavior of Gaussian processes”, Proc. of the Sixth Berkeley Symposium on Mathematical Statistics and Probability, v. 2, 1972, 423–441 | Zbl

[22] B. Milošević, M. Obradović, “Two-dimensional Kolmogorov-type goodness-of-fit tests based on characterisations and their asymptotic efficiencies”, J. Nonparametr. Stat., 28:2 (2016), 413–427 | DOI | MR | Zbl

[23] Ya. Yu. Nikitin, Asymptotic efficiency of nonparametric tests, Cambridge University Press, 1995 | Zbl

[24] Ya. Yu. Nikitin, “Large deviations of U-empirical Kolmogorov–Smirnov tests and their efficiency”, J. Nonparametr. Stat., 22:5 (2010), 649–668 | DOI | MR | Zbl

[25] Ya. Yu. Nikitin and I. Peaucelle, “Efficiency and local optimality of nonparametric tests based on U- and V-statistics”, Metron, LXII:2 (2004), 185–200 | Zbl

[26] Ya. Yu. Nikitin, E. V. Ponikarov, “Large deviations of Chernoff type for U-and V-statistics”, Dokl. Math., 60:3 (1999), 316–318 | Zbl

[27] Ya. Yu. Nikitin, A. V. Tchirina, “Lilliefors test for exponentiality: large deviations, asymptotic efficiency, and conditions of local optimality”, Math. Methods Stat., 16:1 (2007), 16–24 | DOI | Zbl

[28] R. H. Randles, “On the asymptotic normality of statistics with estimated parameters”, Ann. Stat., 10:2 (1982), 462–474 | DOI | Zbl

[29] F. Rublík, “On optimality of the LR tests in the sense of exact slopes. I. General case”, Kybernetika, 25:1 (1989), 13–14 | MR

[30] M. A. Stephens, “Asymptotic results for goodness-of-fit statistics with unknown parameters”, Ann. Stat., 4:2 (1976), 357–369 | DOI | Zbl

[31] S. Sukhatme, “Fredholm determinant of a positive definite kernel of a special type and its application”, Ann. Math. Stat., 43:6 (1972), 1914–1926 | DOI | MR | Zbl

[32] A. W. Van der Vaart, Asymptotic statistics, v. 3, Cambridge University Press, 2000 | Zbl

[33] G. S. Watson, “Goodness-of-fit tests on a circle”, Biometrika, 48:1/2 (1961), 109–114 | DOI | MR | Zbl

[34] G. S. Watson, “Optimal invariant tests for uniformity”, Studies in Probability and Statistics, Papers in honour of E.J.G. Pitman, ed. E. J. Williams, North-Holland, Amsterdam, 1976, 121–127

[35] V. M. Zolotarev, “Concerning a certain probability problem”, Theory Probab. its Appl., 6:2 (1961), 201–204 | DOI