Application of Data Compression Methods to Nonparametric Estimation of Characteristics of Discrete-Time Stochastic Processes

Discrete-time stochastic processes generating elements of either a finite set (alphabet) or a real line interval are considered. Problems of estimating limiting (or stationary) probabilities and densities are considered, as well as classification and prediction problems. We show that universal coding (or data compression) methods can be used to solve these problems.