Estimation of Parameters from Discrete Random Nonstationary Time Series
Hideki Takayasu, Tomomichi Nakamura · Progress of Theoretical Physics Supplement · 2009
For the analysis of nonstationary stochastic time series we introduce a formulation to estimate the underlying time-dependent parameters. This method is designed for random events with small numbers that are out of the applicability range of the normal distribution. The method is demonstrated for numerical data generated by a known system, and applied to time series of traffic accidents, batting average of a baseball player and sales volume of home electronics.