Your Cart

Your cart is empty

Home  >  Volume 22 (2012)

An Interval forecast for stationary Autoregressive process using Bootstrap method by Ekhosuehi N. and 2Omosigho S. E. Volume 22 (November, 2012), pp 219 – 224
Sale price: $5.00


In this paper, we propose a new interval forecast for stationary Autoregressive, AR(p), process using bootstrap method. The bootstrap method which we call Akaike information criterion (AIC) bootstrap employs resampling of the residuals generated from the fitted AR(p) model to compute various AIC. The standard error obtained from the AIC statistic is then used to construct forecast interval for an AR(p) model. In our study, this AIC bootstrap forecast interval compares favourably with the theoretical forecast interval in an out of sample forecast performance. A simulation study was used to demonstrate the procedure.

Keywords: AR(p); AIC; Interval forecast