Statistical analysis of heterogeneous data, hidden Markov chain models, applications to biology and psychology
Research Fields:
Mathematics
Previous and Current Research
 Theoretical statistics: nonparametric analysis of mixtures with varying concentrations, a posteriori changepoint detection, estimation of parameters of nonstationary diffusion processes, correlation analysis of nonstationary Gaussian processes, hidden Markov chain models
 Mathematical models in biology: population dynamics, mitochondrial genetics
 Applied statistics: psychometrics, statistical analysis of repertoire grids (Kelly grids), randomized response technique, statistics of sociologic data
Our research is concentrated on the development of new methods of nonparametric statistical analysis for multidimentional and censored data.
The team consists of 2 researchers: 1PhD candidate and 1 PhD student.
We have developed a number of approaches to statistical analysis of nonparametric models of finite mixtures and applied them to data analysis in genetics, sociology and biostatistics.
Now we develop modified and new algorithms of regression and survival analyses for estimation of statistical characteristics and testing of hypotheses in nonparametric mixture models. We consider application of these algorithms to real medical and sociologic data.
Future Projects and Goals
 Algorithms of regression and survival analyses based on nonparametric models of finite mixtures
 Asymptotical analysis of efficiency of developed algorithms for statistics of mixtures
 Simulation techniques for analysis of algorithms for statistics of mixtures
Selected Publications
Maiboroda R., Sugakova O.
Jackknife covariance matrix estimation for observations from mixture.
Modern Stochastics: Theory and Applications Pub. online: 7 November 2019
Maiboroda R., Miroshnichenko V.
Confidence ellipsoids for regression coefficients by observations from a mixture.
Modern Stochastics: Theory and Applications, Vol.5, Iss.2 pp. 225  245,  2018
Maiboroda R., Navara H., Sugakova O.
Orthogonal regression for observations from mixtures.
Teoriya imovirnostey ta matematychna statystyka, Vol.99, Iss. pp. 152  167,  2018
Maiboroda R.E., Khizanov V.G.
A modified KaplanMeier estimator for a model of mixtures with varying concentrations.
Theory of Probability and Mathematical Statistics. 2016. Vol. 92. P. 109116.
Maiboroda R.,Sugakova O.
Sampling bias correction in the model of mixtures with varying concentrations.
Methodology and Computing in Applied Probability. 2015. Vol. 17 (1). P. 223234.
Liubashenko D., Maiboroda R.
Linear regression by observations from mixture with varying concentrations.
Modern Stochastics: Theory and Applications. 2015. Vol. 2 (4). P. 343353.
Doronin A., Maiboroda R.
Testing hypotheses on moments by observations from a mixture with varying concentrations.
Modern Stochastics: Theory and Applications. 2014. Vol. 1 (2). P. 195209.
Maiboroda R.,Sugakova O., Doronin A.
Generalized estimating equations for mixtures with varying concentrations.
Canadian Journal of Statistics. 2013. Vol. 41 (2). P. 217236.
Maiboroda R.,Sugakova O.
Statistics of mixtures with varying concentrations with application to DNA microarray data analysis.
Journal of Nonparametric Statistics. 2012.
Maiboroda R.,Sugakova O.
Nonparametric density estimation for symmetric distributions by contaminated data.
Metrika. 2012. Vol. 75 (1). P. 109126.
Maiboroda R., Sugakova O.
Generalized estimating equations for symmetric distributions observed with admixture.
Communications in Statistics  Theory and Methods. 2011. Vol. 40 (1). P. 96116.
Maiboroda R.,Shcherbina A.
Finite mixtures model approach to sensitive questions in surveys.
Statistics in Transition. 2011. Vol. 12 (2). P. 331344.
Contacts
Homepage: http://probability.univ.kiev.ua/index.php?page=userinfo&person=mre&lan=en
mre@univ.kiev.ua
