Ekologiya cheloveka (Human Ecology)Ekologiya cheloveka (Human Ecology)1728-08692949-1444Eco-Vector1691710.33396/1728-0869-2016-5-50-64Research ArticlePROPENSITY SCORE MATCHING AS A MODERN STATISTICAL METHOD FOR BIAS CONTROL IN OBSERVATIONAL STUDIES WITH BINARY OUTCOMEGrjibovskiA MAndrej.Grjibovski@gmail.comIvanovS V-GorbatovaM A-DyussupovA A-Norwegian Institute of Public HealthNorthern State Medical UniversityNorth-Eastern Federal UniversityInternational Kazakh - Turkish UniversityNorth-Western State Medical UniversitySemey State Medical University15052016235506423102019Copyright © 2016, Human Ecology2016This article presents propensity score matching (PSM) - modern statistical method to control for confounding, which threatens the validity of associations in observational studies. The efficiency of PSM has been demonstrated in several international studies. The increasing use of PSM by the research community is reflected by steady growth of the number of publications with this method in the PubMed database over time. This article presents the theoretical basis of PSM and its practical application using Stata software. In the practical part of the article, detailed step by step algorithms of various PSM methods are presented allowing researchers to conduct statistical analysis of their own data and interpret results.propensity scorestatistical analysisobservational studiespseudo-randomizationpropensity scorematchingweightingconfounderbiasselection biasстатистический анализобсервационные исследованияпсевдорандомизацияподбор парвзвешиваниеканфаундерсмещение результатовошибка отборабинарный исходотношение шансов[Гржибовский А. М., Иванов С. В. Когортные исследования в здравоохранении // Наука и Здравоохранение. 2015. № 3. С. 5-16.][Гржибовский А. М., Иванов С. В. Поперечные (одномоментные) исследования в здравоохранении // Наука и Здравоохранение. 2015. № 2. С. 5-18.][Унгуряну Т. Н., Гржибовский А. М. Программное обеспечение для статистической обработки данных STATA: введение // Экология человека. 2014. № 1. C. 60-63.][Флетчер Р., Флетчер С., Вагнер Э. Клиническая эпидемиология. Основы доказательной медицины. М. : Медиа Сфера, 1998. 352 с.][Acock A. C. Gentle Introduction to Stata. USA, Texas : Stata Press, 2006. 289 p.][Austin P. C. An introduction to propensity score methods for reducing the effects of confounding in observational studies // Multivariate Behavioral Research. 2011. Vol. 46. P. 399-424.][Austin P. C. Optimal caliper widths for propensity-score matching when estimating differences in means and differences in proportions in observational studies // Pharmaceutical statistics. 2011. Vol. 10 (2). P. 150-161.][Becker S.O., Ichino A. Estimation of average treatment effects based on propensity scores // The Stata Journal. 2002. Vol. 2 (4). P. 358-377.][Cepeda M. S., Boston R., Farrar J. T., Strom B. L. Comparison of logistic regression versus propensity score when the number of events is low and there are multiple confounders // American Journal of Epidemiology. 2003. Vol. 158 (3). P. 280-287.][D'Agostino R. B. Propensity score methods for bias reduction in the comparison of a treatment to a nonrandomized control group // Statistics in Medicine. 1998. Vol. 17 (19). P. 2265-2281.][Garrido M. M., Kelley A. S., Paris J., Roza K., Meier D. E., Morrison R. S., Aldridge M. D. Methods for constructing and assessing propensity scores // Health Services Research. 2014. Vol. 49 (5). P. 1701-1720.][Guo Sh. Y., Mark W. Fraser. Propensity Score Analysis: Statistical Methods and Applications, 2nd ed. USA. SAGE Publications, 2015. 448 p.][Hernan M. A., Hernandez-Diaz S., Robins J. M. A structural approach to selection bias // Epidemiology. 2004. Vol. 15 (5). P. 615-625.][Patorno E., Grotta A., Bellocco R., Schneeweiss S. Propensity score methodology for confounding control in health care utilization databases // Epidemiology Biostatistics and Public Health. 2013. Vol. 10 (3). P. e8940.][Rosenbaum P. R., Rubin D. B. The central role of the propensity score in observational studies for causal effects // Biometrika. 1983. Vol. 70 (1). P. 41-55.][Sturmer T., Joshi M., Glynn R. J., Avorn J., Rothman K. J., Schneeweiss S. A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariable methods // Journal of Clinical Epidemiology. 2006. Vol. 59 (5). P. 437-447.]