Statistical methods for multivariate data which include angular observations

2016 Fiscal Year Final Research Report

• Project/Area Number: 25400218
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Foundations of mathematics/Applied mathematics
• Research Institution: The Institute of Statistical Mathematics
• Principal Investigator: Kato Shogo 統計数理研究所, 数理・推論研究系, 准教授 (60468535)
• Project Period (FY): 2013-04-01 – 2017-03-31
• Keywords: 統計数学 / 方向統計学 / 多変量解析

Outline of Final Research Achievements

In various academic fields, it is often required to handle measurements which can be expressed as angles. Examples of such measurements include wind directions in meteorology and torsional angles in molecular biology. In practice, it is common that angular measurements are recorded with other linear and/or circular measurements. In our study, we have studied statistical methods for multivariate data which include angular observations. Specifically, we have proposed the following three models, among others, and obtained their statistical properties: families of distributions on the general-dimensional torus, a random effect model for circular data, and a Bayesian network model for linear-circular data.

Free Research Field

統計数学