It is shown that price changes of the shares $\textrm{РАО ЕЭС}$ upon different delay times $\tau$ can be regarded as a stochastic Marcovian process. The evolution of the probability distributions is described by means of the Fokker–Plank equation. It is written in terms of a drift and a diffusion coefficients that are directly estimated from financial data. The drift and diffusion coefficients allow to separate the deterministic and noisy influence on a dynamic of the share quotations. It is also shown that for small $\tau$ the asymptotical behavior of the probability distributions is determined by power-law tail. In the case of large $\tau$ the prices change have Gaussian distribution.