Abstract
We consider the problem of testing hypotheses on the regression function from n observations on the regular grid on [0,1]. We wish to test the null hypothesis that the regression function belongs to a given functional class (parametric or even nonparametric) against a composite nonparametric alternative. The functions under the alternative are separated in the L2-norm from any function in the null hypothesis. We assume that the regression function belongs to a wide range of Hölder classes but as the smoothness parameter of the regression function is unknown, an adaptive approach is considered. It leads to an optimal and unavoidable loss of order in the minimax rate of testing compared with the non-adaptive setting. We propose a smoothness-free test that achieves the optimal rate, and finally we prove the lower bound showing that no test can be consistent if in the distance between the functions under the null hypothesis and those in the alternative, the loss is of order smaller than the optimal loss.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Baraud, Y., Huet, S., Laurent, B.: Adaptive tests of linear hypothesis by model selection. Ann. Stat., 31 (1), 225–251 (2003)
Clarke, F. H.: Optimization and Nonsmooth Analysis. Second edition. Classics in Applied Mathematics, 5. Society for Industrial and Applied Mathematics (SIAM), Philadelphia 1990
Ermakov, M.S.: Minimax detection of a signal in a white Gaussian noise. Theory Probab. Appl., 35, 667–679 (1990)
Fan, J.: On the estimation of quadratic functionals. Ann. Stat., 19 (3), 1273–1294 (1991)
Fan, J, Zhang, C., Zhang, J.: Generalized likelihood ratio statistics and Wilks phenomenon. Ann. Stat., 29 (1), 153–193 (2001)
Fan, J., Zhang, J.: Sieve empirical likelihood ratio tests for nonparametric functions. Ann. Stat., 32 (5), 1858–1907 (2004)
Fromont, M., Lévy-Leduc, C.: Adaptive tests for periodic signal detection with applications to laser vibrometry. Prépublication d'Orsay, 2003–76, 2003
Gayraud, G., Pouet, Ch.: Minimax Testing composite null hypotheses in the discrete regression scheme. Math. Methods Stat., 4, 375–394 (2001)
Guerre, E., Lavergne, P.: Optimal minimax rates for nonparametric specification testing in regression models. Econom. Theory, 18, 1139–1171 (2002)
Härdle, W., Kneip, A.: Testing a regression model when we have smooth alternatives in mind. Scand. J. Stat., 26 (2), 221–238 (1999)
Härdle, W., Mammen, E.: Comparing nonparametric versus parametric fits. Ann. Stat., 21(4), 1926–1947 (1993)
Hart, J.D.: Nonparametric Smoothing and Lack-of-fit Tests. Springer, N.Y. e.a. 1997
Hiriart-Urruty, J.-B., Lemaréchal, C.: Convex Analysis and Minimization Algorithms. I. Fundamentals. Grundlehren der Mathematischen Wissenschaften, 305. Springer-Verlag, Berlin 1993a
Hiriart-Urruty, J.-B., Lemaréchal, C.: Convex Analysis and Minimization Algorithms. II. Advanced Theory and Bundle Methods. Grundlehren der Mathematischen Wissenschaften, 306. Springer-Verlag, Berlin 1993b
Horowitz, J.L., Spokoiny, V.G.: An adaptive, rate-optimal test of a parametric mean-regression model against a nonparametric alternative. Econometrica, 69, 599–631 (2001)
Ingster, Yu.I.: On minimax nonparametric detection of a signal in Gaussian white noise. Probl. Inf. Trans., 18 (2), 61–73 (1982)
Ingster, Yu.I.: Minimax detection of signals in L p –metrics. Zap. Nauchn. Semin. LOMI, 184, 152–168 (1990)
Ingster, Yu.I.: Asymptotically minimax hypothesis testing for nonparametric alternatives. I, II, III., Math. Methods Stat., 2, 85–114; 1710-189; 249–268 (1993)
Le Cam, L.M.: Asymptotic Methods in Statistical Decision theory, Springer Series in Statistics. Springer, New–York 1986
Lemaréchal, C.: Nondifferentiable optimisation subgradient and ɛ-subgradient methods. Optimization and operations research. Proc. Conf., Oberwolfach, (1975), pp. 191–199. Lecture Notes in Econom. Math. Systems, Vol. 117, Springer, Berlin, 1976
Lepskii, O.V.: On asymptotically exact testing of nonparametric hypotheses. Discussion paper, Université de Louvain 1993
Lepskii, O.V., Nemirovski, A., Spokoiny, V.G.: On estimation of the L r norm of a regression function. Probab. Theory Relat. Fields, 113, 221–253 (1999)
Lepskii, O.V., Spokoiny, V.G.: Minimax nonparametric hypothesis testing: the case of an inhomogeneous alternative. Bernoulli, 5, 333–358 (1999)
Lepskii, O.V., Tsybakov, A.B.: Asymptotically exact nonparametric hypothesis testing in sup-norm and at a fixed point. Probab. Theory Relat. Fields, 117, 17–48 (2000)
Lorentz, G.G., Golitschek, M.V., Makovoz, Y.: Constructive Approximation : advanced problems. Springer Verlag, Berlin 1996
Petrov, V.V.: Limit Theorems of Probability Theory. Oxford University Press, New-York 1996
Spokoiny, V.G.: Adaptive hypothesis testing using wavelets. Ann. Stat., 24 (6), 2477–2498 (1996)
Spokoiny, V.G.: Adaptive and spatially adaptive testing of a nonparametric hypothesis. Math. Methods Stat., 7 (3), 245–273 (1998)
Suslina, I.A.: Minimax detection of a signal for l p –ball. Zap. Nauchn. Semin. POMI, 207, 127–137 (1993)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Gayraud, G., Pouet, C. Adaptive minimax testing in the discrete regression scheme. Probab. Theory Relat. Fields 133, 531–558 (2005). https://doi.org/10.1007/s00440-005-0445-4
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00440-005-0445-4