Statistical modeling for large scale missing in spatial and time-series data

2016 Fiscal Year Final Research Report

• Project/Area Number: 25330040
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Statistical science
• Research Institution: Sapporo Gakuin University
• Principal Investigator: NAKAMURA Nagatomo 札幌学院大学, 経済学部, 教授 (70207900)
• Co-Investigator(Renkei-kenkyūsha): TSUCHIYA Takahiro 城西大学, 理学部, 准教授 (60316677) ; UENO Genta 情報・システム研究機構, 統計数理研究所・モデリング研究系, 准教授 (40370093)
• Project Period (FY): 2013-04-01 – 2017-03-31
• Keywords: 混合分布モデル / 時空間データ / 欠測データ / 超大量データ / 一様乱数 / 疑似乱数

Outline of Final Research Achievements

The purpose of this research is to solve various problems for integrated analysis of magnetospheric plasma velocity data observed by artificial satellites. The format of the data is "discrete × unequal interval × direction data × pseudo frequency × asymmetric distribution × presence of noise-like data × multiple components × large scale × time series". It is complicated data in which data statements handled separately by the statistical sciences so far are mixed. While combining several elements, it is the final goal to remove obstacles in the integrated analysis as much as possible. In the research period, we performed spatial modeling on fundamental missing data and presented a proposition that is the root of this research and refined the random number generation method　according to the continuous probability distribution through the discrete probability distribution.

Free Research Field

統計科学