О равномерной состоятельности непараметрических критериев типа Неймана

Mikhail S. Ermakov; David Yu. Kapatsa

doi:10.21638/spbu01.2023.203

Authors

Mikhail S. Ermakov St Petersburg State University, 7-9, Universitetskaya nab., St Petersburg, 199034, Russian Federation
David Yu. Kapatsa Institute of Problems of Mechanical Engineering of the Russian Academy of Sciences, 61, Bolshoy pr., 61, V. O., St Petersburg, 199178, Russian Federation

DOI:

https://doi.org/10.21638/spbu01.2023.203

Abstract

The goodness-of-fit problem is explored, when the test statistic is a linear combination of squared Fourier coefficients’ estimates coming from the Fourier decomposition of a probability density. Common examples of such statistics include Neyman’s test statistics and test statistics, generated by L2-norms of kernel estimators. We prove the asymptotic normality of the test statistic for both the null and alternative hypothesis. Using these results we deduce conditions of uniform consistency for nonparametric sets of alternatives, which are defined in terms of distribution or density functions. Results on uniform consistency, related to the distribution functions, can be seen as a statement showing to what extent the distance method, based on a given test statistic, makes the hypothesis and alternatives distinguishable. In this case, the deduced conditions of uniform consistency are close to necessary. For sequences of alternatives - defined in terms of density functions - approaching the hypothesis in L2-metric, we find necessary and sufficient conditions for their consistency. This result is obtained in terms of the concept of maxisets, the description of which for given test statistics is found in this publication.

Keywords:

nonparametric hypothesis testing, goodness of fit tests, Neyman’s test, consistency, nonparametric set of alternatives, density hypothesis testing

Downloads

Download data is not yet available.

References

Литература

1. Lehmann E. L., Romano J. P., Casella G. Testing statistical hypotheses. Vol. 3. Springer (2005).

2. Ingster Y. I., Suslina I. A. Nonparametric goodness-of-fit testing under Gaussian models. Vol. 169. Springer Science and Business Media (2003).

3. Gin´e E., Nickl R. Mathematical foundations of infinite-dimensional statistical models. Cambridge University Press (2021).

4. Kendall M. G., Stuart A. The Advanced Theory of Statistics, Vol. 2. Inference and Relationship. The Annals of Mathematical Statistics 35 (3), 1371-1380 (1964).

5. Shorack G. R., Wellner J. A. Empirical processes with applications to statistics. New York, Wiley-Interscience (1986).

6. Durbin J. Distribution theory for tests based on the sample distribution function. Philadelphia, Society for Industrial and Applied Mathematics (1973).

7. Ermakov M. Minimax nonparametric testing of hypotheses on the distribution density. Theory of Probability and Its Applications 39 (3), 396-416 (1995).

8. Ermakov M. On uniform consistency of nonparametric tests I. Journal of Mathematical Sciences 258 (6), 802-837 (2021).

9. Bera A. K., Ghosh A. Neyman’s smooth test and its applications in Econometrics. Statistics Textbooks and Monographs 165, 177-230 (2002).

10. Neyman J. Smooth test for goodness of fit. Scandinavian Actuarial Journal 1937 (3/4), 149-199 (1937).

11. Ermakov M. Minimax detection of a signal in the heteroscedastic Gaussian white noise. Journal of Mathematical Sciences 137 (1), 4516-4524 (2006).

12. Rivoirard V. Maxisets for linear procedures. Statistics and probability letters 67 (3), 267-275 (2004).

13. Tsybakov A. B. Introduction to nonparametric estimation. Vol. 3. Springer (2009).

14. Ermakov M. On asymptotically minimax nonparametric detection of signal in Gaussian white noise. Journal of Mathematical Sciences 251 (1), 78-87 (2020).

15. Hall P. Central limit theorem for integrated square error of multivariate nonparametric density estimators. Journal of multivariate analysis 14 (1), 1-16 (1984).