CMStatistics 2017: Start Registration
View Submission - CMStatistics
Title: On estimating finite mixtures of sine-skewed wrapped Cauchy distributions Authors:  Toshihiro Abe - Nanzan University (Japan)
Yoichi Miyata - Takasaki City University of Economics (Japan) [presenting]
Takayuki Shiohama - Tokyo University of Science (Japan)
Abstract: Mixtures of the wrapped Cauchy distributions provide the most popular framework for modelling a population with circular and continuous outcomes arising in a variety of subclasses. In contrast, several circular data are not only multimodal, but also locally asymmetric around one or more modes. We consider an algorithm for estimating a mixture of sine-skewed wrapped Cauchy distributions from a likelihood perspective. Furthermore, we use a real data set to show that our proposed model has a better fit than the other models. Consistency of the maximum likelihood estimator is also shown under the topology of the quotient space obtained by collapsing the true parameter set into a single point.