摘要：We propose an automatic model order selection procedure for k-factor GARMA pro- cesses. The procedure is based on sequential tests of the maximum of the periodogram and semiparametric estimators of the model parameters. As a byproduct, we introduce a generalized version of Walker's large sample g-test that allows to test for persistent periodicity in stationary ARMA processes. Our simulation studies show that the proce- dure performs well in identifying the correct model order under various circumstances. An application to Californian electricity load data illustrates its value in empirical anal- yses and allows new insights into the periodicity of this process that has been subject of several forecasting exercises
关键词：Seasonal Long Memory · k-factor GARMA processes · Model selection ; Electricity loads ; We are grateful to Liudas Giraitis and Uwe Hassler for their remarks on earlier versions of this paper ; and the participants of the NSVCM 2014 Workshop in Pader
