Software reproduction of correlations in small samples in the statistical analysis of biometric data and market data in the space of values of the empirical Hurst indicator.
Аuthors
1*, 2**, 2***1. 1Penza Scientific Research Electrotechnical Institute, Penza, Russia
2. Penza State Univercity, 40, Krasnaya street, Penza, 400026, Russia
*e-mail: ivan@pniei.penza.ru
**e-mail: tarasovdv@mail.ru
***e-mail: vuc@pnzgu.ru
Abstract
The purpose of the study consists in describing the software modeling of correlations specifics when simulating small samplings with a computer. The classic Hurst indicator is widely used in practice, as it allows evaluating the fractal components of the biometric data model. The alike models may be used in the identification systems elaboration based on biometric data, such as airport biometric systems to increase security and speed up the process of passenger control. No doubt, the need for collecting, processing and storing a large amount of biometric information forces researchers to search for the ways for the data volume reducing of the samplings. The Hurst indicator is widely used as well in the models describing price fluctuations on the market. It is usually employed herewith for retrospective market analysis, since it requires large samplings of initial data. It is possible to reduce the sampling volume by employing the model of the market prices variation nonstationarity and biometric data. The article demonstrates that the weighting index of the summarized data does not depend on the volume of the reproduced computed sampling of experimental data over wide range. The author presents a functional relationship of the mathematical expectation of the correlation coefficient of data cohesion within artificial small samplings of the volume of 13 to 35 experiments. The error of the hypothesis of the correlation coupling indicator stability of the data of the two independent software generators was estimated.
Keywords:
correlation coefficient, small samples, statistical Hurst criterion, linking by summation of data of two software generators of pseudorandom numbersReferences
1.Kalush Yu.A., Loginov V.M. Sibirskii zhurnal industrial'noi matematiki, 2002, vol. 5, no. 4, pp. 29–37.
2. Peters E. Khaos i poryadok na rynkakh kapitala. Novyi analiticheskii vzglyad na tsikly, tseny i izmenchivost' rynka (Chaos and order in capital markets. A new analytical look at cycles, prices and market volatility), Moscow, MIR, 2000, 333 p.
3. Mandel'brot B., Khadson Z.L. (NE)poslushnye rynki. Fraktal'naya revolyutsiya v finansakh ((NOT)obedient markets. Fractal revolution in finance), Moscow, Izdatel'skii dom Vil'yams, 2006, 408 p.
4. Naiman E. Kak pokupat' deshevo i prodavat' dorogo: posobie dlya razumnogo investor (How to buy low and sell high: guidance for the smart investor), Moscow, Al'pina Pablisherz, 2011, 552 p.
5. Ivanov A.I. Vysokorazmernaya kollektivnaya biometriya podsoznatel'nogo povedeniya lyudei na rynke i proizvodstve (High-dimensional collective biometrics of subconscious behavior of people in the market and production), Penza, Iz-vo PGU, 2021, 60 p.
6. Ivanov A.I., Egorova Yu.Yu. Neirokomp'yutery: razrabotka, primenenie, 2012, no. 3, pp. 26–27.
7. Feder E. Fraktaly (Fractals), Moscow, Mir, 1991, 254 p.
8. Nekrasova I.V. Mezhdunarodnyi nauchno-issledovatel'skii zhurnal, 2015, no. 7 (38). URL: https://research-journal.org/archive/7-38-2015-august/pokazatel-xersta-kak-mera-fraktalnoj-struktury...
9. Orlov Yu.N., Osminin K.P. Nestatsionarnye vremennye ryady: Metody prognozirovaniya s primerami analiza finansovykh i syr'evykh rynkov (Non-stationary time series: Forecasting methods with examples of analysis of financial and commodity markets), Moscow, Knizhnyi dom «Librokom», 2011, 384 p.
10. Tarasov D.V. V Vserossiiskaya nauchno-tekhnicheskaya konferentsiya «Bezopasnost' informatsionnykh tekhnologii», posvyashchennaya 70-letnemu yubileyu AO "NPP "Rubin": sbornik statei. Penza, Penzenskii gosudarstvennyi universitet, 2023, pp. 147–151.
11. Kuznetsov V.E., Ivanov A.I., Gerasin V.Yu. V Vserossiiskaya nauchno-tekhnicheskaya konferentsiya «Bezopasnost' informatsionnykh tekhnologii», posvyashchennaya 70-letnemu yubileyu AO "NPP "Rubin": sbornik statei. Penza, Penzenskii gosudarstvennyi universitet, 2023, pp. 74–78.
12. R 50.1.037–2002. Rekomendatsii po standartizatsii. Prikladnaya statistika. Pravila proverki soglasiya opytnogo raspredeleniya s teoreticheskim. Ch. I. Kriterii tipa χ2 (P 50.1.037-2002. Recommendations for standardization. Applied statistics. Rules for checking the agreement of the experimental distribution with the theoretical one. Part I. Criteria of the χ2 type), Moscow, Gosstandart Rossii, 2001, 140 p.
13. Ivanov A.I. Neirosetevoi mnogokriterial'nyi statisticheskii analiz malykh vyborok. Proverka gipotezy nezavisimosti: spravochnik. (Neural network multicriteria statistical analysis of small samples. Testing the independence hypothesis: reference book), Penza: Izd-vo PGU, 2023, 218 p.
14. Osipov N.A., Musienko A.S., Merkushev O.A. Trudy MAI, 2023, no. 132. URL: https://trudymai.ru/eng/published.php?ID=176857
15. Mal'shakov G.V. Trudy MAI, 2020, no. 115. URL: https://trudymai.ru/eng/published.php?ID=119946. DOI: 10.34759/trd-2020-115-16
16. Solomatin M.S., Mitrofanov D.V. Trudy MAI, 2020, no. 114. URL: https://trudymai.ru/eng/published.php?ID=119013. DOI: 10.34759/trd-2020-114-18
17. Eliseev S.O., Kryukov D.A. Trudy MAI, 2018, no. 101. URL: https://trudymai.ru/eng/published.php?ID=97041
18. GOST R 52633.5–2011. Zashchita informatsii. Tekhnika zashchity informatsii. Avtomaticheskoe obuchenie neirosetevykh preobrazovatelei biometriya-kod dostupa (Information protection. Information protection technology. The neural net biometry-code converter automatic training), Moscow, Standarty, 2011.
19. Ivanov A.I. Malye vyborki, neiromorfnye vychisleniya: bystrye algoritmy otsenki entropii Shennona-Pirsona kvadratichnoi slozhnosti: spravochnik (Small samples, neuromorphic calculations: fast algorithms for estimating Shannon – Pearson entropy of quadratic complexity: reference book), Penza, Izd-vo PGU, 2023, 32 p.
20. Khaikin S. Neironnye seti: polnyi kurs (Neural networks: a comprehensive foundation), Moscow, Izdatel'skii dom Vil'yams, 2006, 1104 p.
21. Serikova N.I., Ivanov A.I., Kulikov C.V., Malygin A.Yu. V Vserossiiskaya nauchno-tekhnicheskaya konferentsiya «Bezopasnost' informatsionnykh tekhnologii», posvyashchennaya 70-letnemu yubileyu AO "NPP "Rubin": sbornik statei. Penza, Penzenskii gosudarstvennyi universitet, 2023, pp. 79–83.
Download