A smooth transition long-memory model
Abstract
This paper proposes a new fractional model with a time-varying long-memory parameter. The latter evolves nonlinearly according to a transition variable through a logistic function. We present an LR-Based test that allows to discriminate between the standard fractional model and our model. We further apply a nonlinear least squares estimation method to estimate the long-memory parameter. We present an application to the unemployment rate in the United States from 1948 to 2012.