Basic requirements for mathematical methods of classification

Ordering of classification methods should increase their role in solving applied problems, in particular, in diagnostics of materials. Development of the requirements to be met by classification methods is the first concern. The initial formulation of the requirements is the main content of this work. Mathematical methods of classification are considered as a part of the applied statistics methods. The natural requirements to the considered methods of data analysis and presentation of the calculation results arising from the achievements and ideas accumulated by the national probabilistic and statistical scientific school are discussed. Specific recommendations are given on a number of issues, as well as criticism of individual errors. In particular, methods of data analysis must be invariant with respect to the permissible transformations of the scales in which the measured data are gained, i.e., the methods should be adequate in the terms of measurement theory. The basis of any statistical method of data analysis is always a particular probabilistic model which must be clearly described and the premises must be justified either from theoretical considerations, or experimentally. Data processing methods intended for use in real-world problems should be tested for robustness with respect to the acceptable deviations of the initial data and model assumptions. The accuracy of the solutions provided by the method should be determined. When publishing the results of statistical analysis of real data, it is necessary to indicate their accuracy (confidence intervals). As an estimate of the predictive power of the classification algorithm, it is recommended to use predictive power instead of the proportion of correct forecasts. Methods of mathematical research are divided into «exploratory analysis» and «evidence-based statistics». Specific requirements for data processing methods arise in connection with their «docking» during their sequential execution. The limits of applicability of probabilistic-statistical methods are discussed. Specific statements of the classification problems and typical errors in application of different methods of their solution are also considered.

1. Orlov A. I. Applied Statistics. — Moscow: Ékzamen, 2006. — 671 p. [in Russian].

2. Orlov A. I. Characterization of average values by means of measurement scales / Nauch. Zh. KubGAU. 2017. N 134. P. 877 – 907 [in Russian].

3. Enyukov I. S. Methods for digitizing non-quantitative attributes / Algorithmic and software for applied statistical analysis. — Moscow: Nauka, 1980. P. 309 – 316 [in Russian].

4. Aleksandrov V. V., Gorskii N. D. Algorithms and programs for the structural method of data processing. — Leningrad: Nauka, 1983. — 208 p. [in Russian].

5. Saati T. L. Decisionmaking. Hierarchy Analysis Method. — Moscow: Radio i svyaz’, 1993. — 278 p. [in Russian].

6. Hajek Ja., Sidak Zb. Theory of rank tests. — Prague: Academia. Publishing House of the Czechoslovak Academy of Sciences, 1967. — 376 p.

7. Hollander M., Wolfe D. A. Nonparametric statistical methods. — New York – London – Sydney – Toronto: John Wiley and Sons, 1973. — 503 p.

8. Alimov Yu. I. Alternative to the method of mathematical statistics. — Moscow: Znanie, 1980. — 64 p. [in Russian].

9. Malinovskii L. G. Analysis of statistical relationships: a model-constructive approach. — Moscow: Nauka, 2002. — 687 p. [in Russian].

10. Orlov A. I. On the methods of testing the homogeneity of two independent samples / Zavod. Lab. Diagn. Mater. 2020. Vol. 86. N 3. P. 67 – 76. DOI: 1026896/1028-6861-2020-86-3-67-76 [in Russian].

11. Bol’shev L. N., Smirnov N. V. Tables of mathematical statistics. 3rd edition. — Moscow: Nauka, 1983. — 416 p. [in Russian].

12. Orlov A. I. Structure of Nonparametric Statistics (generalizing paper) / Zavod. Lab. Diagn. Mater. 2015. Vol. 81. N 7. P. 62 – 72 [in Russian].

13. Zagoruiko N. G., Orlov A. I. Some unsolved mathematical problems of applied statistics / Modern problems of cybernetics (applied statistics). — Moscow: Znanie, 1981. P. 53 – 63 [in Russian].

14. Orlov A. I., Mironova N. G., Fomin V. N., Chernomordik O. M. Methodology. Testing of the homogeneity of two samples of product parameters in estimation its technical level and quality. — Moscow: VNIIStandartizatsii, 1987. — 116 p. [in Russian].

15. Orlov A. I. Real and nominal significance levels when testing statistical hypotheses / Nauch. Zh. KubGAU. 2015. N 114. P. 42 – 54 [in Russian].

16. Orlov A. I. Consistent Tests of Absolute Homogeneity of Independent Samplings / Zavod. Lab. Diagn. Mater. 2012. Vol. 78. N 11. P. 66 – 70 [in Russian].

17. Orlov A. I. Stability in socio-economic models. — Moscow: Nauka, 1979. — 296 p. [in Russian].

18. Orlov A. I. Stable economic and mathematical methods and models. Design and development of stable economic and mathematical methods and models for the modernization of enterprise management. — Saarbrücken (Germany), LAP (Lambert Academic Publishing), 2011. — 436 p. [in Russian].

19. Orlov A. I. Some probabilistic questions of classification theory / Applied statistics. — Moscow: Nauka, 1983. P. 166 – 179 [in Russian].

20. Tikhonov A. N., Arsenin V. Ya. Methods for solving incorrect problems. — Moscow: Nauka, 1986. — 288 p. [in Russian].

21. Kupershtokh V. L., Mirkin B. G., Trofimov V. A. The sum of internal relationships as an indicator of the quality of classification / Avtomat. Telemekh. 1976. N 3. P. 91 – 98 [in Russian].

22. Orlov A. I. Statistical simulations method in applied statistics / Zavod. Lab. Diagn. Mater. 2019. Vol. 85. N 5. P. 67 – 79 [in Russian].

23. Blekhman I. I., Myshkis A. D., Panovko Ya. G. Mechanics and Applied Mathematics: Logic and Features of Mathematics Applications. 2nd edition. — Moscow: Nauka, 1990. — 360 p. [in Russian].

24. Orlov A. I. Statistic Packages: Tools of the Researcher / Zavod. Lab. Diagn. Mater. 2008. Vol. 74. N 5. P. 76 – 78 [in Russian].

25. Orlov A. I. Certification and statistical methods (generalizing article) / Zavod. Lab. Diagn. Mater. 1997. Vol. 63. N 3. P. 55 – 62 [in Russian].

26. Orlov A. I. Predictive power — the best indicator of the quality of the diagnostic algorithm / Nauch. Zh. KubGAU. 2014. N 99. P. 33 – 49 [in Russian].

27. Tutubalin V. N. Probability Theory in Natural Science. — Moscow: Znanie, 1972. — 64 p. [in Russian].

28. Orlov A. I. Econometrics. 4th edition. — Rostov-on-Don: Feniks, 2009. — 572 p. [in Russian].

29. Chesnokov S. V. Determinative analysis of socio-economic data. 2nd edition. — Moscow: URSS, 2009. — 168 p. [in Russian].

30. Lbov G. S. Methods for processing heterogeneous experimental data. — Novosibirsk: Nauka, 1981. 160 p. [in Russian].

31. Khaitun S. D. Scientometrics: Status and Prospects. — Moscow: Nauka, 1983. — 344 p. [in Russian].

32. Orlov A. I. Nonparametric goodness-of-fit Kolmogorov, Smirnov, omega-square tests and the errors in their application / Nauch. Zh. KubGAU. 2014. N 97. P. 32 – 45 [in Russian].

33. Gini C. Logic in statistics. — Moscow: Statistika, 1973. — 128 p. [Russian translation].

34. Ventsel’ E. S. Methodological features of applied mathematics at the present stage / Mathematicians about mathematics. — Moscow: Znanie, 1982. P. 37 – 55 [in Russian].

35. Mirkin B. G. Analysis of quality attributes and structures. — Moscow: Statistika, 1980. — 319 p. [in Russian].

36. Orlov A. I. The limit theory of the solutions of extremal statistical problems / Nauch. Zh. KubGAU. 2017. N 133. P. 579 – 600 [in Russian].

37. Orlov A. I. Estimation of the dimensionality of a model in regression / Algorithmic and software for applied statistical analysis. — Moscow: Nauka, 1980. P. 92 – 99 [in Russian].

38. Rabukhin A. E., Sil’vestrov V. P., Orlov A. I., et al. The results of treatment of patients with acute pneumonia / Current issues of clinical and experimental medicine. — Moscow: 4 GU MZ SSSR, 1978. P. 132 – 138 [in Russian].

39. Orlov A. I., Mironova N. G., Fomin V. N., Cherchintsev A. N. Recommendations. Applied statistics. Data processing methods. Basic requirements and characteristics. — Moscow: VNIIStandartizatsii, 1987. — 62 p. [in Russian].

40. Kuptsov V. I. Determinism and probability. — Moscow: Politizdat, 1976. — 256 p. [in Russian].

41. Sachkov Yu. V. Probabilistic revolution in science (Probability, chance, independence, hierarchy)]. — Moscow: Nauchnyi mir, 1999. — 144 p. [in Russian].

42. Sachkov Yu. V. Introduction to the Probabilistic World. — Moscow: Nauka, 1971. — 208 p. [in Russian].

43. Tutubalin V. N. Boundaries of applicability (probabilistic-statistical methods and their capabilities). — Moscow: Znanie, 1977. — 64 p. [in Russian].

44. Orlov A. I. On the development of applied statistics / Modern problems of cybernetics (applied statistics). — Moscow: Znanie, 1981. P. 3 – 14 [in Russian].

45. Orlov A. I. Mathematics of fuzziness / Nauka i zhizn’. 1982. N 7. P. 60 – 67 [in Russian].

46. Kolmogorov A. N. Basic concepts of probability theory. 2nd edition. — Moscow: Nauka, 1974. — 120 p. [in Russian].

47. Morgenshtern O. On the accuracy of economic and statistical observations. — Moscow: Statistika, 1968. — 293 p. [in Russian].

48. Kendall M. G., Stuart A. Multivariate Statistical Analysis and Time Series. — Moscow: Nauka, 1976. — 736 p. [in Russian].

49. Adler Yu. P. Quality Management: A Statistical Approach. — Moscow: Znanie, 1979. — 51 p. [in Russian].

50. Orlov A. I., Guseinov G. A. Mathematical methods in the study of mathematics-capable schoolchilds / Research on probabilistic and statistical modeling of real systems. — Moscow: TsÉMI AN SSSR, 1977. P. 80 – 93 [in Russian].

51. Tyurin Yu. N. About mathematical problems in expert estimators / Expert assessments. Cybernetics. Issue 58. — Moscow: Nauchnyi sovet AN SSSR po kompleksnoi probleme «Kibernetika», 1979. P. 7 – 16 [in Russian].

52. Orlov A. I. Theory of lusians / Nauch. Zh. KubGAU. 2014. N 101. P. 275 – 304 [in Russian].

53. Burbaki N. Essays on the History of Mathematics. — Moscow: IL, 1963. — 292 p. [Russian translation].

54. Orlov A. I. The role of methodology in mathematical methods of research / Zavod. Lab. Diagn. Mater. 2019. Vol. 85. N 7. P. 5 – 6 [in Russian].