2022 Fiscal Year Final Research Report
Sequential analysis for economic time series and its applications - Detection of financial bubbles
| Project/Area Number |
19K21691
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 7:Economics, business administration, and related fields
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
人見 光太郎 京都工芸繊維大学, 基盤科学系, 教授 (00283680)
永井 圭二 横浜国立大学, 大学院国際社会科学研究院, 教授 (50311866)
|
|---|
| Project Period (FY) |
2019-06-28 – 2023-03-31
|
| Keywords | 逐次検定 / 単位根 / criticality / DDSブラウン運動 / ベッセル過程 |
|---|
| Outline of Final Research Achievements |
A theoretical study of sequential tests in autoregressive models commonly used in economic time series analysis and Galton-Watson branching processes used to describe populations in epidemiology was conducted for the AR(1) and AR(p) models, with stop times based on observed Fisher information. Simultaneous limits of the sequential test statistic and stopping time for the unit root test in the sampling scheme were derived and characterised using Bessel processes driven by DDS Brownian motion. The statistical properties of the estimators of variance were also clarified. Simultaneous Laplace transformations and simultaneous density functions in the limit were also obtained under the null and local alternative hypotheses.
|
| Free Research Field |
計量経済学
|
| Academic Significance and Societal Importance of the Research Achievements |
社会全体としては、提案されて手法をもちいることによって、リアルタイムにバブルの発生を検出することが可能になる。それにより、政府や金融機関がバブルの発生による社会的なコストや損失回避のための情報を得ることが可能である。学術的には、検定統計量と停止時の同時分布を解析的に求めることで、この分野の数理統計理論を大きく発展させた。それにより、期待値や分散を含めたモーメントの計算および分位点の導出が可能になった。
|
