Geodesic
Stability estimating in optimal sequential hypotheses testing
Kybernetika, Tome 45 (2009) no. 2, pp. 331-344 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

We study the stability of the classical optimal sequential probability ratio test based on independent identically distributed observations $X_1,X_2,\dots$ when testing two simple hypotheses about their common density $f$: $f=f_0$ versus $f=f_1$. As a functional to be minimized, it is used a weighted sum of the average (under $f_0$) sample number and the two types error probabilities. We prove that the problem is reduced to stopping time optimization for a ratio process generated by $X_1,X_2,\dots$ with the density $f_0$. For $\tau_*$ being the corresponding optimal stopping time we consider a situation when this rule is applied for testing between $f_0$ and an alternative $\tilde f_1$, where $\tilde f_1$ is some approximation to $f_1$. An inequality is obtained which gives an upper bound for the expected cost excess, when $\tau_*$ is used instead of the rule $\tilde\tau_*$ optimal for the pair $(f_0,\tilde f_1)$. The inequality found also estimates the difference between the minimal expected costs for optimal tests corresponding to the pairs $(f_0,f_1)$ and $(f_0,\tilde f_1)$.
We study the stability of the classical optimal sequential probability ratio test based on independent identically distributed observations $X_1,X_2,\dots$ when testing two simple hypotheses about their common density $f$: $f=f_0$ versus $f=f_1$. As a functional to be minimized, it is used a weighted sum of the average (under $f_0$) sample number and the two types error probabilities. We prove that the problem is reduced to stopping time optimization for a ratio process generated by $X_1,X_2,\dots$ with the density $f_0$. For $\tau_*$ being the corresponding optimal stopping time we consider a situation when this rule is applied for testing between $f_0$ and an alternative $\tilde f_1$, where $\tilde f_1$ is some approximation to $f_1$. An inequality is obtained which gives an upper bound for the expected cost excess, when $\tau_*$ is used instead of the rule $\tilde\tau_*$ optimal for the pair $(f_0,\tilde f_1)$. The inequality found also estimates the difference between the minimal expected costs for optimal tests corresponding to the pairs $(f_0,f_1)$ and $(f_0,\tilde f_1)$.
Classification : 62L10, 62L15
Keywords: sequential hypotheses test; simple hypothesis; optimal stopping; sequential probability ratio test; likelihood ratio statistic; stability inequality 
@article{KYB_2009_45_2_a8,
     author = {Gordienko, Evgueni and Novikov, Andrey and Zaitseva, Elena},
     title = {Stability estimating in optimal sequential hypotheses testing},
     journal = {Kybernetika},
     pages = {331--344},
     year = {2009},
     volume = {45},
     number = {2},
     mrnumber = {2518155},
     zbl = {1165.62052},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_2009_45_2_a8/}
}
TY  - JOUR
AU  - Gordienko, Evgueni
AU  - Novikov, Andrey
AU  - Zaitseva, Elena
TI  - Stability estimating in optimal sequential hypotheses testing
JO  - Kybernetika
PY  - 2009
SP  - 331
EP  - 344
VL  - 45
IS  - 2
UR  - http://geodesic.mathdoc.fr/item/KYB_2009_45_2_a8/
LA  - en
ID  - KYB_2009_45_2_a8
ER  - 
%0 Journal Article
%A Gordienko, Evgueni
%A Novikov, Andrey
%A Zaitseva, Elena
%T Stability estimating in optimal sequential hypotheses testing
%J Kybernetika
%D 2009
%P 331-344
%V 45
%N 2
%U http://geodesic.mathdoc.fr/item/KYB_2009_45_2_a8/
%G en
%F KYB_2009_45_2_a8
Gordienko, Evgueni; Novikov, Andrey; Zaitseva, Elena. Stability estimating in optimal sequential hypotheses testing. Kybernetika, Tome 45 (2009) no. 2, pp. 331-344. http://geodesic.mathdoc.fr/item/KYB_2009_45_2_a8/

[1] Y. S. Chow, H. Robbins, and D. Siegmund: Great Expectations: The Theory of Optimal Stopping. Houghton Mifflin Company, Boston 1971. | MR

[2] E. I. Gordienko and F. S. Salem: Estimates of stability of Markov control processes with unbounded costs. Kybernetika 36 (2000), 195–210. | MR

[3] E. I. Gordienko and A. A. Yushkevich: Stability estimates in the problem of average optimal switching of a Markov chain. Math. Methods Oper. Res. 57 (2003), 345–365. | MR

[4] P. J. Huber: A robust version of the probability ratio test. Ann. Math. Statist. 36 (1965), 1753–1758. | MR | Zbl

[5] A. Kharin: On robustifying of the sequential probability ratio test for a discrete model under “contaminations". Austrian J. Statist. 3 (2002), 4, 267–277.

[6] A. Kharin: Robust sequential testing of hypotheses on discrete probability distributions. Austrian J. Statist. 34 (2005), 2, 153–162.

[7] G. Lorden: Structure of sequential tests minimizing an expected sample size. Z. Wahrsch. Verw. Gebiete 51 (1980), 291–302. | MR | Zbl

[8] V. Mackevičius: Passage to the limit in problems of optimal stopping of Markov processes (in Russian). Litovsk. Mat. Sb. (Russian) 13 (1973), 1, 115–128, 236. | MR

[9] R. Montes-de-Oca, A. Sakhanenko, and F. Salem-Silva: Estimates for perturbations of general discounted Markov control chains. Appl. Math. 30 (2003), 287–304. | MR

[10] A. Novikov: Optimal sequential tests for two simple hypotheses. Sequential Analysis 28 (2009), No. 2. | MR | Zbl

[11] A. Novikov: Optimal sequential tests for two simple hypotheses based on independent observations. Internat. J. Pure Appl. Math. 45 (2008), 2, 291–314. | MR

[12] V. V. Petrov: Sums of Independent Random Variables. Springer, New York 1975. | MR | Zbl

[13] P. X. Quang: Robust sequential testing. Ann. Statist. 13 (1985), 638–649. | MR | Zbl

[14] A. N. Shiryayev: Statistical Sequential Analysis. Nauka, Moscow 1969. (In Russian.)

[15] A. Wald and J. Wolfowitz: Optimum character of the sequential probability ratio test. Ann. Math. Statist. 19 (1948), 326–339. | MR

[16] J. Whitehead: The Design and Analysis of Sequential Clinical Trials. Wiley, New York 1997. | MR | Zbl