Portfolio optimization problem for high dimensional data
Project/Area Number |
24730193
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Economic statistics
|
Research Institution | Keio University (2014-2016) Jikei University School of Medicine (2012-2013) |
Principal Investigator |
|
Project Period (FY) |
2012-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2014: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2013: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
Keywords | 最適ポートフォリオ / 統計的推定 / 漸近理論 / 高次元データ / 縮小推定量 / ランダム行列 / ファクターモデル / 主成分分析 / 国際研究者交流 / イギリス / PCA / 国際情報交換 / 多国籍 |
Outline of Final Research Achievements |
In this research, we propose two types of optimal portfolio estimators when an investor aims to invest a huge number of assets. Suppose that high dimensional data with respect to the past asset return is available. Then we propose (1)Optimal portfolio estimator by using an unbiased estimator for the inverse of the covariance matrix, (2)Shrinkage type estimator for the plug-in portfolio weights estimator. First, we derive the theoretical properties and confirm numerical validity of these estimators. Then, we compare the performance (in terms of the sharp ration and the utility function) with existing portfolios based on the Japanese stock price data (200 issues) and realized the superiority of the proposed method.
|
Report
(6 results)
Research Products
(18 results)