Testing nonlinearity: decision rules for selecting between logistic and exponential star models

This paper introduces new LM specification procedures to choose between Logistic and Exponential Smooth Transition Autoregressive (ST AR) models and to improve testing for nonlinearities. The selection procedures introduced here are simpler and have better consistency and power properties than those previously available in the literature. These improvements result from analyzing the properties ofthe Taylor approximations to the transition function. Monte-CarIo and empirical evidence are provided in support of the new procedures