Global power functions of goodness of fit tests. (English) Zbl 1106.62329

Janssen, Arnold

Ann. Stat. 28, No. 1, 239-253 (2000).

Summary: It is shown that the global power function of any nonparametric test is flat on balls of alternatives except for alternatives coming from a finite dimensional subspace. The present benchmark is here the upper one-sided (or two-sided) envelope power function. Every choice of a test fixes a priori a finite dimensional region with high power. It turns out that also the level points are far away from the corresponding Neyman-Pearson test level points except for a finite number of orthogonal directions of alternatives. For certain submodels the result is independent of the underlying sample size. In the last section the statistical consequences and special goodness of fit tests are discussed.

MSC:

62G10	Nonparametric hypothesis testing
62G20	Asymptotic properties of nonparametric inference

Keywords:

Goodness of fit test; Kolmogorov-Smirnov test; power function; envelope power function; curvature of power functions; level points; data driven Neyman’s smooth test,; Pitman efficiency; Bahadur efficiency; intermediate efficiency.

References:

[1]	And el, J. (1967). Local asymptotic power and efficiency of tests of Kolmogorov-Smirnov type. Ann. Math. Statist. 38 1705-1725. · Zbl 0153.48001 · doi:10.1214/aoms/1177698605
[2]	Anderson, T. W. and Darling, D. A. (1952). Asymptotic theory of certain ”Goodness of fit” criteria based on stochastic processes. Ann. Math. Statist. 23 193-212. · Zbl 0048.11301 · doi:10.1214/aoms/1177729437
[3]	Behnen, K. and Neuhaus, G. (1989). Rank Tests with Estimated Scores and Their Application. Teubner, Stuttgart. · Zbl 0692.62041
[4]	Bickel, P. J. and Ritov, Y. (1992). Testing for goodness of fit: a new approach. In Nonparametric Statistics and Related Topics (A. K. Md. E. Saleh, ed.) 51-57. North-Holland, Amsterdam.
[5]	Bouleau, N. and Hirsch, F. (1991). Dirichlet Forms and Analysis on Wiener Spaces. de Gruyter, Berlin. · Zbl 0748.60046 · doi:10.1515/9783110858389
[6]	Burnashev, M. V. (1979). On the minimax detection of an inaccurately known signal in a white Gaussian noise background. Theory Probab. Appl. 24 107-119. · Zbl 0433.60043 · doi:10.1137/1124008
[7]	Drees, H. and Milbrodt, H. (1991). Components of the two-sided Kolmogorov-Smirnov test in signal detection problems with Gaussian white noise. J. Statist. Plann. Inference 29 325-335. · Zbl 0747.62041 · doi:10.1016/0378-3758(91)90007-2
[8]	Drees, H. and Milbrodt, H. (1994). The one-sided Kolmogorov-Smirnov test in signal detection problems with Gaussian white noise. Statist. Neerlandica 28 103-116. · Zbl 0829.62053 · doi:10.1111/j.1467-9574.1994.tb01436.x
[9]	Durbin, J. and Knott, M. (1972). Components of Cramér-von Mises statistics I. J. Roy. Statist. Soc. Ser. B 34 290-307. JSTOR: · Zbl 0238.62052
[10]	Eubank, R. L., Hart, J. D. and LaRiccia, V.N. (1993). Testing goodness of fit via nonparametric function estimation techniques. Comm. Statist. Theory Methods 22 3327-3354. · Zbl 0830.62044 · doi:10.1080/03610929308831219
[11]	Hájek, J. and Sidák, Z. (1967). Theory of Rank Tests. Academic Press, New York. · Zbl 0161.38102
[12]	Inglot, T., Kallenberg, W. C. M. and Ledwina, T. (1998). Vanishing shortcoming of data driven Neyman’s tests. In Asymptotic Methods in probability and Statistics (B. Szyszkowicz, ed.) 811-829. North-Holland, Amsterdam. · Zbl 0956.62040 · doi:10.1016/B978-044450083-0/50054-X
[13]	Inglot, T. and Ledwina, T. (1996). Asymptotic optimality of data-driven Neyman’s tests for uniformity. Ann. Statist. 24 1982-2019. · Zbl 0905.62044 · doi:10.1214/aos/1069362306
[14]	Ingster, Y. I. (1993). Asymptotically minimax hypothesis testing for nonparametric alternatives. · Zbl 0798.62057
[15]	I, II, III. Math. Methods Statist. 2 85-114, 171-189, 249-268.
[16]	Janssen, A. (1995). Principal component decomposition of non-parametric tests. Probab. Theory Related Fields 101 193-209. · Zbl 0814.62026 · doi:10.1007/BF01375824
[17]	Janssen, A. and Milbrodt, H. (1993). Rényi type goodness of fit tests with adjusted principal direction of alternatives. Scand. J. Statist. 20 177-194. · Zbl 0798.62060
[18]	Kallenberg, W. C. M. and Ledwina, T. (1995). Consistency and Monte Carlo simulation of data driven version of smooth goodness-of-fit tests. Ann. Statist. 23 1594-1608. · Zbl 0847.62035 · doi:10.1214/aos/1176324315
[19]	Lepski, O. V. and Spokoiny, V. G. (1999). Minimax nonparametric hypothesis testing: the case of an inhomogenous alternative. Bernoulli 5 333-358. · Zbl 0946.62050 · doi:10.2307/3318439
[20]	Milbrodt, H. and Strasser, H. (1990). On the asymptotic power of the two-sided Kolmogorov- Smirnov test. J. Statist. Plann. Inference 26 1-23. · Zbl 0728.62049 · doi:10.1016/0378-3758(90)90091-8
[21]	Neuhaus, G. (1976). Asymptotic power properties of the Cramér-von Mises test under contiguous alternatives. J. Multivariate Anal. 6 95-110. · Zbl 0339.62035 · doi:10.1016/0047-259X(76)90022-1
[22]	Neuhaus, G. (1988). Addendumto Local asymptotics for linear rank statistics with estimated score functions. Ann. Statist. 16 1342-1343. · Zbl 0664.62015 · doi:10.1214/aos/1176350967
[23]	Neyman, J. (1937). ”Smooth test” for goodness of fit. Skand. Aktuarie Tidskv. 20 150-199. · Zbl 0018.03403
[24]	Nikitin, Y. (1995). Asymptotic Efficiency of Nonparametric Tests. Cambridge Univ. Press. · Zbl 0879.62044
[25]	Parthasarathy, K. R. (1967). Probability Measures on Metric Spaces. Academic Press, New York. · Zbl 0153.19101
[26]	Shorack, G. R. and Wellner, J. A. (1986). Empirical Processes with Applications to Statistics. Wiley, New York. · Zbl 1170.62365
[27]	Strasser, H. (1985). Mathematical Theory of Statistics. de Gruyter, Berlin. · Zbl 0594.62017 · doi:10.1515/9783110850826
[28]	Strasser, H. (1990). Global extrapolations of local efficiency. Statist. Decisions 8 11-26. · Zbl 0749.62032