Main Article Content
Forecasting with nonlinear time series model: A Monte-Carlo bootstrap approach
Abstract
In this paper, we propose a new method of forecasting with nonlinear time series model using Monte-Carlo Bootstrap method. This new method gives better result in terms of forecast root mean squared error (RMSE) when compared with the traditional Bootstrap method and Monte-Carlo method of forecasting using a special nonlinear time series model, called logistic smooth transition autoregressive (LSTAR) model. We illustrate this new method using some simulation experiments.
Keywords: Bootstrap, Forecasting, LSTAR, Monte-Carlo, Monte-Carlo Bootstrap