A0796
Title: Test for volatility parameter change in linear parabolic SPDEs
Authors: Yozo Tonaki - The University of Osaka (Japan) [presenting]
Yusuke Kaino - Kobe University (Japan)
Masayuki Uchida - The University of Osaka (Japan)
Abstract: The purpose is to consider change point detection for the volatility parameter in second-order linear parabolic stochastic partial differential equations (SPDEs) based on high-frequency spatiotemporal data. Ornstein-Uhlenbeck processes are obtained from the inner product of the solution of the SPDE and an orthonormal basis, and these processes can be approximated through statistical inference for SPDEs based on high-frequency spatiotemporal data. A test statistic is therefore proposed to detect changes of the volatility parameter in the linear parabolic SPDE based on change point analysis for diffusion processes. The asymptotic null distribution of the proposed test statistic is derived, and the test statistic is shown to be consistent. Additionally, the asymptotic properties of the test statistic are validated through numerical simulations.
