Asymmetric smooth transition autoregressive model in forecasting finance rate on consumer installment loans at commercial banks

Economic and finance time series are typically asymmetric and are expected to be modeled using asymmetric nonlinear time series models. The logistic smooth transition autoregressive, LSTAR, model which is an asymmetric type of the smooth transition autoregressive, is becoming popular in modeling economic and financial time series. In this paper, we have considered the logistic smooth transition autoregressive model and have estimated unknown parameters based on the method of moment and modified maximum likelihood method. The performance of the proposed estimation methods are studied by simulation and are compared with the performance of maximum likelihood estimators. It shown that for large sample sizes, the modified maximum likelihood estimators usually have the lowest mean square error and bias. We proposed a LSTAR model to finance rate on consumer installment loans at commercial banks and conclude that the estimated LSTAR model based on the modified maximum likelihood method has the lowest value of MSE. ‎