B0907
Title: A hidden Markov model whose components are the Weibull-extended sine skewed von Mises distributions
Authors: Yoichi Miyata - Takasaki City University of Economics (Japan) [presenting]
Takayuki Shiohama - Nanzan University (Japan)
Toshihiro Abe - Hosei University (Japan)
Abstract: Statistical analysis based on hidden Markov models is a useful method for estimating the timing of structural change and the structure of each population simultaneously for time series data. Cylindrical data consist of a pair of a non-negative observation and an angular observation identified with a vector on the unit circle. If angular parts in cylindrical data show significant asymmetric patterns, it is required to model a circular marginal distribution to have a higher degree of skewness. To model such cylindrical time series data, a hidden Markov model is proposed whose components are cylindrical distributions in which a circular random variable (representing the angle) has an extended sine-skewed circular distribution. As an example of real data analysis, we apply the proposed models for wind direction and speed data, which are measured in Japan, and provide an interpretation for the estimated states.
