2020/04/06 by Idris A. Eckley, Eckley, Idris, Claudia Kirch +3
Chemistry · Economics, Econometrics and Finance · Environmental Science · #62G20 #62H12 #62M10 #Air Quality and Health Impacts #Applications (stat.AP) #Chemical Thermodynamics and Molecular Structure #Economics of Agriculture and Food Markets #FOS: Computer and information sciences #Methodology (stat.ME)
paper · pdf · doi:10.48550/arxiv.2004.02692
openalex publication_date 2020/04/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Motivated by an example from remote sensing of gas emission sources, we\nderive two novel change point procedures for multivariate time series where, in\ncontrast to classical change point literature, the changes are not required to\nbe aligned in the different components of the time series. Instead the change\npoints are described by a functional relationship where the precise shape\ndepends on unknown parameters of interest such as the source of the gas\nemission in the above example. Two different types of tests and the\ncorresponding estimators for the unknown parameters describing the change\nlocations are proposed. We derive the null asymptotics for both tests under\nweak assumptions on the error time series and show asymptotic consistency under\nalternatives. Furthermore, we prove consistency for the corresponding\nestimators of the parameters of interest. The small sample behavior of the\nmethodology is assessed by means of a simulation study and the above remote\nsensing example analyzed in detail.\n