Change detection in parametric multivariate dynamic data streams using the ARMAX-GARCH model

Dynamic data detection is one of the main concerns in statistical process control (SPC) field. Here we focus on monitoring parametric multivariate dynamic streams using ARMAX-GARCH model, which reflects both influence exogenous variables mean vector and heterogeneity covariance matrix. A quasi maximum likelihood estimator used to estimate parameter a process, top-r scheme proposed monitor parameters multi-dimensional streams. Finally, real-data example landslide illustrates superiorities scheme.