DOI:https://doi.org/10.15407/kvt182.02.066
Kibern. vyčisl. teh., 2015, Issue 182, pp.
State Institution “O.N. Marzeev Institute for Hygiene and Medical Ecology
of NAMS of Ukraine” (Kiev)
THE METHOD OF DETERMINATION OF ENVIRONMENTAL FACTORS JOINT IMPACT IN EPIDEMIOLOGICAL STUDIES FOR BINARY DATA
Introduction. Modern approaches for data analysis combine classical methods and focused on their practical application. Sometimes the information is presented in the form of qualitative characteristics that are characterize the contamination of the research object. Such binary variables are easily transformed into a probability (in percent), so the task description of results performed using probability theory.
The purpose of the article is to develop such a common method forcalculation joint action of the factors that would allow to operate with qualitative (binary) information and would use techniques and formulas of probability theory
Results. A careful analysis was carried out for the existing approaches in the medical and environmental studies for calculating the effect of the joint action of the factors. It was evaluated disadvantages of these approaches that implemented in the theory of probability and mathematical statistics. The article proposes an original method of calculating the combined effect of the factors that allows you to work with the information expressed in binary form. The final expression was designed by using approach of formal logic and probability theory.
Conclusions. It is shown that the known methods of probability theory cannot be adequately used to evaluate the combined effect of the factors. The original method of calculating the probability of the joint action of factors that take into account their possible connection is described.
Keywords: qualitative data, binary variables, joint effect of the factors, the probability of independent and interdependent events.
References
1 Duke V. A. Samoilenko A. P. Data Mining. Training — SPb, 2001. — 368p.
2 David W. Hosmer, Stanley Lemeshow Applied Logistic Regression, 2nd ed. — New York, Chichester, Wiley. 2002. — 383p.
3 Nasledov A. N. SPSS 19: Professional statistical analysis. — SPb, 2011. — 400 p.
4 Greenacre M. Correspondence Analysis in Practice, 2nd ed. — London: Chapman & Hall / CRC — 2007. — 280 p.
5 Ritchie M. D., Hahn L. W., Roodi N., Bailey L. R., Dupont W. D., Parl F. F., Moore J. H. Multifactor-dimensionality reduction reveals high-order interactions among estrogenmetabolism genes in sporadic breast cancer. Am. J. Hum. Genet. 2001 Jul; 69 (1): 138-47. https://doi.org/10.1086/321276
6 Hahn L. W., Ritchie M. D., Moore J. H. Multifactor dimensionality reduction software for detecting gene-gene and gene-environment interactions//Bioinformatics. 2003 Feb 12; 19 (3): 376-82 https://doi.org/10.1093/bioinformatics/btf869
7 Orlov A. I. Applied Statistics — M .: Publisher “Exam”, 2004. — 656 p.
8 Antomonov M. Y. Mathematical processing and analysis of medical-biological data. — Kiev: Publishing house “Malii Druk”, 2006. — 558p.
9 Gaydyshev I. Analysis and data processing — St. Petersburg, 2001. — 750p.
10 Wentzel E. S. Probability 10th ed., Sr — M.: “Academy”, 2005. — 576 p.
11 Gnedenko B. V., Khinchin A. Y. An elementary introduction to the theory of probability, 1970. — 168p.
12 Novikov P. S. Elements of mathematical logic. 2nd ed. — M .: Nauka, 1973 — 400 p.
Received 02.06.2015