On conistent hypothesis testing

M. S. Ermakov

Zapiski Nauchnykh Seminarov POMI, Probability and statistics. Part 23, Tome 442 (2015), pp. 48-74

Résumé

We explore natural links between different types of consistency: consistency, uniform consistency and pointwise consistency. On the base of these results we provide both sufficient conditions and necessary conditions for existence of different types of consistent tests for the problems of hypothesis testing on a probability measure of independent sample, on a mean measure of Poisson process, on a solution of linear ill-posed problem in Gaussian noise, on a solution of deconvolution problem and for a signal detection in Gaussian white noise. In the last three cases we show that necessary conditions and sufficient conditions coincide.

Bibliographie

[1] M. Arcones, “The large deviation principle for stochastic processes. II”, Teoriya veroyatn. i ee primen., 48:1 (2004), 122–150 | DOI | MR | Zbl

[2] R. R. Bahadur, R. G. Savage, “The nonexistence of certain statistical procedures in nonparametric problems”, Ann. Math. Statist., 27 (1956), 1115–1122 | DOI | MR | Zbl

[3] N. Balakrishnan, M. S. Nikulin, V. Voinov, Chi-squared Goodness of Fit Tests with Applications, Elsevier, Oxford, 2013 | Zbl

[4] A. R. Barron, “Uniformly powerful goodness of fit tests”, Ann. Statist., 17 (1989), 107–124 | DOI | MR | Zbl

[5] A. Berger, “On uniformly consistent tests”, Ann. Math. Statist., 18 (1951), 289–293 | DOI | MR

[6] V. I. Bogachev, Measure Theory, v. 2, Springer, NY., 2000

[7] V. I. Bogachev, Gaussovskie mery, Nauka, M., 1997 | MR

[8] M. V. Burnashev, “O minimaksnom obnaruzhenii netochno izvestnogo signala na fone belogo gaussovskogo shuma”, Teoriya veroyatn. i ee primen., 24:1 (1979), 106–118 | MR | Zbl

[9] L. Comminges, A. S. Dalalyan, “Minimax testing of a composite null hypothesis defined via a quadratic functional in the model of regression”, Electronic J. Statist., 7 (2013), 146–190 | DOI | MR | Zbl

[10] T. M. Cover, “On determing irrationality of the mean of a random variable”, Ann. Statist., 1 (1973), 862–871 | DOI | MR | Zbl

[11] A. Dembo, Y. Peres, “A topological criterion for hypothesis testing”, Ann. Statist., 22 (1994), 106–117 | DOI | MR | Zbl

[12] A. Dembo, O. Zeitouni, Large Deviations Techniques and Applications, Jones and Bartlett, Boston, 1993 | MR | Zbl

[13] L. Devroye, G. Lugosi, “Almost sure classification of densities”, J. Nonpar. Statist., 14 (2002), 675–698 | DOI | MR | Zbl

[14] D. L. Donoho, “One-sided inference about functionals of a density”, Ann. Statist., 16 (1988), 1390–1420 | DOI | MR | Zbl

[15] H. Danford, Dzh. Shvarts, Lineinye operatory, v. I, Izd-vo “Inostrannoi literatury”, M., 1962

[16] M. S. Ermakov, “Bolshie ukloneniya empiricheski mer i statisticheskie kriterii”, Zap. nauchn. semin. POMI, 207, 1993, 37–59 | MR | Zbl

[17] M. S. Ermakov, “On distinguishability of two nonparametric sets of hypothesis”, Statist. Probab. Letters, 48 (2000), 275–282 | DOI | MR | Zbl

[18] M. S. Ermakov, “Nonparametric signal detection with small type I and type II error probabilities”, Statist. Inference Stoch. Processes, 14 (2011), 1–19 | DOI | MR | Zbl

[19] P. Ganssler, “Compactness and sequential compactness on the space of measures”, Z. Wahrsch. Verw. Gebiete, 17 (1971), 124–146 | DOI | MR | Zbl

[20] P. Groeneboom, J. Oosterhoff, F. H. Ruymgaart, “Large deviation theorems for empirical probability measures”, Ann. Probab., 7 (1979), 553–586 | DOI | MR | Zbl

[21] W. Hoeffding, J. Wolfowitz, “Distinguishability of sets of distributions”, Ann. Math. Statist., 29 (1958), 700–718 | DOI | MR | Zbl

[22] J. L. Horowitz, V. S. Spokoiny, “An adaptive, rate optimal test of a parametric model against a nonparametric alternative”, Econometrica, 69 (2001), 599–631 | DOI | MR | Zbl

[23] I. A. Ibragimov, R. Z. Khasminskii, “Ob otsenivanii beskonechnomernogo signala v gaussovskom belom shume”, Dokl. AN SSSR, 236 (1977), 1053–1055 | Zbl

[24] Yu. I. Ingster, “Asymptotically minimax hypothesis testing for nonparametric alternatives. I”, Math. Methods Statist., 2 (1993), 85–114 | MR | Zbl

[25] Yu. I. Ingster, Yu. A. Kutoyants, “Nonparametric hypothesis testing for intensity of the Poisson process”, Math. Methods Statist., 16 (2007), 218–246 | MR

[26] Yu. I. Ingster, I. A. Suslina, Nonparametric Goodness-of-fit Testing under Gaussian Models, Lecture Notes in Statistics, 169, Springer, N.Y., 2002 | MR

[27] K. Iosida, Funktsionalnyi analiz, Mir, M., 1967 | MR

[28] A. Janssen, “Global power function of goodness of fit tests”, Ann. Statist., 28 (2000), 239–253 | DOI | MR | Zbl

[29] C. Kraft, “Some conditions for consistency and uniform consistency of statistical procedures”, Iniv. Californ. Publ. Stat., 2 (1955), 125–142 | MR | Zbl

[30] S. R. Kulkarni, O. Zeitouni, “A general classification rule for probability measures”, Ann. Statist., 23 (1995), 1393–1407 | DOI | MR | Zbl

[31] L. Le Cam, “Convergence of estimates under dimensionality restrictions”, Ann. Statist., 1 (1973), 38–53 | DOI | MR | Zbl

[32] L. Le Cam, L. Schwartz, “A necessary and sufficient conditions for the existence of consistent estimates”, Ann. Math. Statist., 31 (1960), 140–150 | DOI | MR | Zbl

[33] E. L. Lehmann, J. P. Romano, Testing Statistical Hypothesis, Springer Verlag, NY, 2005, 784 pp. | MR

[34] A. B. Nobel, “Hypothesis testing for families of ergodic processes”, Bernoulli, 12 (2006), 251–269 | DOI | MR | Zbl

[35] L. Schwartz, “On Bayes procedures”, Z. Wahrsch. Verw. Gebiete, 4 (1965), 10–26 | DOI | MR | Zbl

[36] J. Pfanzagl, “On the existence of consistent estimates and tests”, Z. Wahrscheinlichkeitstheor. verw. Geb., 10 (1968), 43–62 | DOI | MR | Zbl

[37] A. Shapiro, “On concepts of directional differentiability”, J. Optimization Theor. Appl., 66 (1990), 477–487 | DOI | MR | Zbl

[38] A. W. van der Vaart, Asymptotic Statistics, Cambridge University Press, Cambridge, 1998 | MR | Zbl