Statistical inference for stochastic processes and application to high-frequency financial data

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K21598
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Foundations of mathematics/Applied mathematics; Economic statistics
• Research Institution: The Institute of Statistical Mathematics
• Principal Investigator: Teppei Ogihara 統計数理研究所, 数理・推論研究系, 助教 (40746426)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 非同期観測 / マイクロストラクチャー・ノイズ / 高頻度データ解析 / 最尤型推定量 / 拡散過程 / 漸近有効性 / 疑似尤度解析 / 積分観測モデル

Outline of Final Research Achievements

Statistical inference for diffusion processes with noisy, nonsynchronous observations was studied. This model is applied to high-frequency data in a stock market. A maximum-likelihood- and a Bayes-type estimators were constructed by using a quasi-likelihood function. Asymptotic mixed normality of the estimators were shown. Local asymptotic normality of the statistical model was proved in the case that the diffusion coefficients were deterministic, and consequently, asymptotic optimality of the estimators were shown.

Free Research Field

数理統計学