Development of Multivariate Analysis for Mesh Data with Preliminary Information and its Application
Project/Area Number |
05680246
|
Research Category |
Grant-in-Aid for General Scientific Research (C)
|
Allocation Type | Single-year Grants |
Research Field |
Statistical science
|
Research Institution | Hokkaido University |
Principal Investigator |
SAITO Takayuki Hokkaido University, Faculty of letters Professor, 文学部, 教授 (70113561)
|
Co-Investigator(Kenkyū-buntansha) |
IKEDA Tohru Hokkaido University, Faculty of letters Assistant, 文学部, 助手 (50202891)
OTSU Tatsuo Hokkaido University, Faculty of letters Associate Professor, 文学部, 助教授 (10203829)
|
Project Period (FY) |
1993 – 1994
|
Project Status |
Completed (Fiscal Year 1994)
|
Budget Amount *help |
¥1,400,000 (Direct Cost: ¥1,400,000)
Fiscal Year 1994: ¥700,000 (Direct Cost: ¥700,000)
Fiscal Year 1993: ¥700,000 (Direct Cost: ¥700,000)
|
Keywords | Mesh Data / Multivariate Analysis / Prior Information / Redundancy Analysis / Bays Estimation / Canonical Regression Analysis / 行動圏 |
Research Abstract |
When an environmental or ecological survey is conducted in a region, observations are often taken at each mesh cell in the region and recorded as multivariate data. In certain situations, there may be prior information about the variates or the cells, which is provided independently of the survey. In this study, we developed two procedures to analyze the multivariate data, incorporationg the prior infromation in the analyzes. One procedure deals with asymmetrical relationship among cells and performs analysis on the basis of least squares criterion. The otherdeals with the information about the variates or the cells and performs analysis accoding to Bays estimation. Both procedures have been found to work successfully. For possible application of the procedures, ecological data files were constructed for investigatation of home ranges of raccoons and other animals.
|
Report
(3 results)
Research Products
(20 results)