Inference Theory in the frequency domain of spatio-temporal statistical analysis
| Project/Area Number |
15K11994
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2015: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 時空間統計解析 / 周波数領域解析 / 時空間データ / 不規則間隔データ / 大規模時空間データ / 統計的検定 / 不等間隔データ |
|---|
| Outline of Final Research Achievements |
We proposed a new test statistic based on discrete Fourier transformas of spatio-temporal data for parametrics models of stationary random fields.
It is constructed by smoothing periodograms of different frequencies by a kernel function. Under the null hypothesis in that a supposed parametric model is true, the test statistic has simple asymptotic expectation and variance, and hence it can be implemented easily to analyze acutual data. Furthermore it is expected that it is asymptotically normally distributed.
|
Report
(2 results)
Research Products
(3 results)
