The problem of mathematical analysis of demographic data was investigated for data, where information on migration flows is taken into account implicitly. Regression techniques, neural networks and stochastic analysis were used for the mathematical analysis of demographic processes. Two age groups were considered: young (0 - 39 years) and elderly (40 - 70 years). While development of stochastic models the theory of Markov chains and transition matrix were used. The parameterization and model identification were conducted according to Rosstat data.