Changepoint in Error-Prone Relations

Linear relations, containing measurement errors in input and output data, are considered. Parameters of these so-called errors-in-variables models can change at some unknown moment. The aim is to test whether such an has occurred or not. For instance, detecting a trend for randomly spaced time series special case the investigated framework. designed changepoint tests shown be consistent involve neither nuisance parameters nor tuning constants, which makes testing procedures effortlessly applicable. A estimator also introduced its consistency proved. boundary issue avoided, meaning that detected when being close extremities observation regime. As theoretical basis developed methods, weak invariance principle smallest singular value data matrix provided, assuming weakly dependent non-stationary errors. results presented simulation study, demonstrates computational efficiency techniques. completely data-driven illustrated through problems coming from calibration insurance; however, methodology applied other areas as clinical measurements, dietary assessment, psychometrics, environmental toxicology manifested paper.