期刊名称:Discussion Papers / Business School, University of Strathclyde
出版年度:2013
卷号:2013
出版社:University of Strathclyde
摘要:This paper investigates the usefulness of switching Gaussian state spacemodels as a tool for implementing dynamic model selecting (DMS) or averaging (DMA)in time-varying parameter regression models. DMS methods allow for model switching,where a di.erent model can be chosen at each point in time. Thus, they allow for theexplanatory variables in the time-varying parameter regression model to change over time.DMA will carry out model averaging in a time-varying manner. We compare our exactapproach to DMA/DMS to a popular existing procedure which relies on the use of forget-ting factor approximations. In an application, we use DMS to select di.erent predictorsin an in.ation forecasting application. We also compare di.erent ways of implementingDMA/DMS and investigate whether they lead to similar results
关键词:Model switching; forecast combination; switching state space model; in-;.ation forecasting