Asymptotical problems of sequential interval and point estimation

The accuracy of interval estimation systems is usually measured using interval lengths for given covering probabilities. The confidence intervals are the intervals of a fixed width if the length of the interval is determined, i.e., not random, and tends to zero for a given covering probability. We consider two important directions of statistical analysis -sequential interval estimation with confidence intervals of fixed width and sequential point estimation with asymptotically minimum risk. Two statistical models are used to describe the basis problems of sequential interval estimation by confidence intervals of a fixed width and point estimation. A review of data on nonparametric sequential estimation is carried out and new original results obtained by the authors are presented. Sequential analysis is characterized by the fact that the moment of termination of observations (stopping time) is random and is determined depending on the values of the observed data and on the adopted measure of optimality of the constructed statistical estimate. Therefore, to solve the asymptotic problems of sequential estimation, the methods of summation of random variables are used. To prove the asymptotic consistency of the confidence intervals of a fixed width, we used a method based on application of limit theorems for randomly stopped random processes. General conditions of the consistency and efficiency of sequential interval estimation of a wide class of functionals of an unknown distribution function are obtained and verified by sequential interval estimation of an unknown probability density of asymptotically uncorrelated and linear processes. Conditions of the regularity are specified that provide the property of being an estimate with an asymptotically minimum risk for a wide class of estimates and loss functions. Those conditions are verified by sequential point estimation of an unknown distribution function.

1. Dantzig G. B. On the nonexistence of tests of «student’s» hypethesis having power functions independent of σ2 / Ann. Math. Statist. 1940. N 11. P. 186 – 192.

2. Lehmann E. L. Notes on the theory of estimation. — Berkeley: Univ. of Calif. Press, 1951.

3. Chow Y. S., Robbins H. On the asymptotic theory of fixed-width sequential confidence intervals for the mean / Ann. Math. Statist. 1965. N 36. P. 457 – 462.

4. Anscombe F. J. Large sample theory of sequential estimation / Proc. Cambridge Philos. Soc. 1952. N 48. P. 600 – 607.

5. Ghosh M., Mukhopadhyay N., Sen P. K. Sequential estimation. — New York: Wiley, 1996.

6. Silvestrov D. S. Limit Theorems for Randomly Stopped Stochastic Processes. — London: Springer-Verlag, 2004.

7. Shiohama T., Tanagushi M. Sequential estimation for a functional of the spectral density of a Gaussian stationary process / Ann. Inst. Statist. Math. 2001. Vol. 53. N 1. P. 142 – 158.

8. Mukhopadhyay N., De Silva B. M. Sequential methods and their applications. — London: Chapman and Hall, 2009.

9. Rakhimova G. G. Application of limit theorems for superposition of random functions to sequential estimation: In the book: Silvestrov S., Rancic M., Malyarenko A. (eds.) Stochastic Processes and Applications / Proceedings in Mathematics & Statistics. Springer, 2018. Chapter 7. P. 148 – 154.

10. Abdushukurov A. A., Rakhimova G. G. Asymptotic properties of sequential interval estimation of functionals of a distribution function / Statistical Methods of Estimating and Hypotheses Testing. Collection of Scientific Papers. 2018. Vol. 28. P. 4 – 14 [in Russian].

11. Rakhimova G. G. Asymptotic problems of sequential point estimation of functionals of an unknown distribution function / Proceedings of the Republican Scientific and Practical Conference «Statistics and its Applications», Tashkent, 2019. P. 232 – 238 [in Russian].

12. Takahata H. Limiting behavior of density estimates for stationary asymptotically uncorrelated processes / Bull. Tokyo Gak. Univ. Ser. VI. 1977. Vol. 29. P. 1 – 9.

13. Takahata H. On recursive density estimators for a class of stationary processes / Bull. Tokyo Gak. Univ. Ser. VI. 1977. Vol. 29. P. 10 – 18.

14. Tursunov G. T. Interval estimation of the probability density of an asymptotically uncorrelated process / Theor. Probability Math. Statist. 1984. N 29. P. 141 – 147.

15. Chanda K. C. Density estimation for linear processes / Ann. Inst. Statist. Math. 1983. Vol. 35. Part A. P. 439 – 446.

16. Mirzakhmedov M. A., Tursunov G. T. The sequential interval estimating of linear random processes / Sixth Int. Vilnius conference on probability theory and math. statist. Abstracts of comm. — Vilnius, 1993. P. 35 – 36.