Inference for a change-point problem under a generalised Ornstein-Uhlenbeck setting (Q1656864)

The subject of the paper is the investigation of estimation techniques in locating the change point under the framework of a generalized version of the one-dimensional Ornstein-Uhlenbeck process. The importance of the Ornstein-Uhlenbeck process in the modelling of certain economic indicator is known (see [\textit{O. Vasicek}, J. Financ. Econ. 5, No. 2, 177--188 (1977; Zbl 1372.91113)], [\textit{C. Erlwein}, \textit{F. Benth} and \textit{R. Mamon}, ``HMM filtering and parameter estimation of an electricity spot price model'', Energy Econ. 32, 1034--1043 (2010)]). To rectify the classical Ornstein-Uhlenbeck model's inability to capture the evolution of a process whose mean level varies with time, \textit{H. Dehling} et al. [Stat. Inference Stoch. Process. 13, No. 3, 175--192 (2010; Zbl 1209.60047)] introduced a generalised OU process in which a time-dependent function describes its mean-reverting level. Determining accurately when regime and structural changes occur in various time-series data is critical in many social and natural sciences. The equivalence of two consistent estimation techniques in locating the change point under the framework of the process considered is shown in this paper. The methods are based on the least sum of squared error and the maximum log-likelihood approaches. The case where both the existence and the location of the change point are unknown is investigated and an informational methodology is employed to address these issues. Numerical illustrations are presented to assess the methods' performance.