Title: Asymptotic properties of the gauge of step-indicator saturation
Authors: Matthias Qian - Oxford University (United Kingdom) [presenting]
Bent Nielsen - University of Oxford (United Kingdom)
Abstract: The aim is investigated the asymptotic properties of the gauge of Step-indicator Saturation which is an algorithm to handle unmodelled location shifts in time series. The gauge is the frequency of falsely retained step-indicators when the data generating process has no shifts. We present asymptotic convergence and distribution results of the gauge of the algorithm. The proofs rely on empirical process results of temporal differences of residuals. Our results offer an asymptotic justification to use the gauge in choosing the only tuning parameter of this statistical procedure.