A1241
Title: Autocorrelation test under frequent mean shifts
Authors: Han Xiao - Rutgers University (United States) [presenting]
Abstract: Testing for the presence of autocorrelation is a fundamental problem in time series analysis. Classical methods such as the Box-Pierce test rely on the assumption of stationarity, necessitating the removal of non-stationary components such as trends or shifts in the mean prior to application. However, this is not always practical, particularly when the mean structure is complex, such as being piecewise constant with frequent shifts. The aim is to propose a new inferential framework for autocorrelation in time series data under frequent mean shifts. In particular, a shift-immune portmanteau (SIP) test is introduced that reliably tests for autocorrelation and is robust against mean shifts. An application of the method is illustrated to nanopore sequencing data.
