Sequential statistical decision making in problems of data flows analysis
https://doi.org/10.37661/1816-0301-2Q21-18-3-36-47
Abstract
In the problems of data flows analysis, the problems of statistical decision making on parameters of observed data flows are important. For their solution it is proposed to use sequential statistical decision rules. The rules are constructed for three models of observation flows: sequence of independent homogeneous observations; sequence of observations forming a time series with a trend; sequence of dependent observations forming a homogeneous Markov chain. For each case the situation is considered, where the model describes the observed stochastic data with a distortion. "Outliers" ("contamination") are used as the admissible distortions that adequately describe the majority of situations appear in practice. For such situations the families of sequential decision rules are proposed, and robust decision rules are constructed that allow to reduce influence of distortion to the efficiency characteristics. The results of computer experiments are given to illustrate the constructed decision rules.
Keywords
sequential decision rule,
statistical test,
time series with trend,
homogeneous Markov chain,
distortion
Supporting agencies: The results of the paper are obtained within the Project "Procedures library for computer monitoring of data and decision making on the basis of sequential analysis methods" in frames of the State research program "Digital and space technologies, human and state safety", and with the support of the grant of the President of the Republic of Belarus of talented young researchers for the year 2021
About the Author
A. Y. Kharin
Belarusian State University
Belarus
Belarus
Alexey Y. Kharin - Dr. Sci. (Phys.-Math.), Associate Professor, Head of the Department of Probability Theory and Mathematical Statistics, Leading Researcher of the Research Laboratory of Statistical Analysis and Modeling of the Research Institute for Applied Problems of Mathematics and Informatics, BSU.
Av. Nezavisimosti, 4, Minsk, 220030
References
1. Mukhopadhyay N., Silva B. de. Sequential Methods and Their Applications. New York, Marcel Dekker, 2009, 504 р.
2. Wald A. Sequential Analysis. New York, John Wiley and Sons, 1947, 212 p.
3. Lai T. Sequential analysis: Some classical problems and new challenges. Statistica Sinica, 2001, vol. 11, рр. 303-408.
4. Kharin A. Y. Robastnost bajesovskih i posledovatelnyh statisticheskih reshayuschih pravil. Robustness of Bayesian and Sequential Statistical Decision Rules. Minsk, Belorusskij gosudarstvennyj universitet, 2013, 207 p. (In Russ.).
5. Huber P., Ronchetti E. Robust Statistics. New York, Wiley, 2009, 380 р.
6. Maevskii V. V., Kharin Y. S. Robust regressive forecasting under functional distortions in a model. Automation and Remote Control, 2002, vol. 63, iss. 11, рр. 1803-1820.
7. Weiss C. H. Discrete-valued Time Series. Oxford, John Wiley and Sons, 2018, 284 p.
8. Kharin A. Y., Kishylau D. V. Robust sequential test for hypotheses about discrete distributions in the presence of "outliers". Journal of Mathematical Sciences, 2015, vol. 205, iss. 1, рр. 68-73.
9. Kharin A., Tu T. T. Performance and robustness analysis of sequential hypotheses testing for time series with trend. Austrian Journal of Statistics, 2017, vol. 46, no. 3-4, рр. 23-36.
10. Kharin A. Y., Tu T. T. On error probabilities calculation for the truncated sequential probability ratio test. Zhurnal Belorusskogo gosudarstvennogo universiteta. Matematika. Informatika [Journal of the Belarusian State University. Mathematics and Informatics], 2018, no. 1, рр. 68-76.
11. Kemeny J. G., Snell J. L. Finite Markov Chains. New York, Springer, 1960, 238 р.
12. Kharin A. Y. An approach to asymptotic robustness analysis of sequential tests for composite parametric hypotheses. Journal of Mathematical Sciences, 2017, vol. 227, iss. 2, рр. 196-203.
13. Tu T. T., Kharin A. Y. Sequential probability ratio test for many simple hypotheses on parameters of time series with trend. Zhurnal Belorusskogo gosudarstvennogo universiteta. Matematika. Informatika [Journal of the Belarusian State University. Mathematics and Informatics], 2019, no. 1, рр. 35-45.
14. Siegmund D. Sequential Analysis. Tests and Confidence Intervals. New York, Springer-Verlag, 1985, 272 p.
15. Ghosh B. Sequential Tests of Statistical Hypotheses. Reading, Addison - Wesley, 1970, 454 p.
Review
For citations:
Kharin A.Y. Sequential statistical decision making in problems of data flows analysis. Informatics. 2021;18(3):36-47. (In Russ.) https://doi.org/10.37661/1816-0301-2Q21-18-3-36-47
Views: 549
Email this article 