Control variate method for financial time series models and optimal portfolio

2017 Fiscal Year Final Research Report

• Project/Area Number: 26730018
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Statistical science
• Research Institution: The University of Electro-Communications (2015-2017); Wakayama University (2014)
• Principal Investigator: Amano Tomoyuki 電気通信大学, 大学院情報理工学研究科, 准教授 (40514451)
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: 制御変数法 / 時系列 / 最適ポートフォリオ

Outline of Final Research Achievements

Control variate method was investigated by Lavenberg etc. and widely used to improve estimators. However this method has been developed mainly in i.i.d. cases.We　proposed control variate estimator for stationary processes　and derived the asymptotics.　However this proposed estimator is constructed for scalar-valued processes and many data are vector-valued statinary processes.　Hence in this research, we proposed control variate estimator for vector-valued stationary processes and derived the asymptotics.　Furthermore we applied control variate method to optimal portfolio and derived asymptotics.

Free Research Field

統計科学