| Nationalekonomiska
institutionen Department of Economics School of Economics and Management Lund University |
||
Predictable non-linearities in U.S. inflation
[Back]
Published in Economics Letters, 2006, vol. 93, 223-228.
Abstract: This paper compares the out-of-sample inflation forecasting performance of two non-linear models; a neural network and a Markov switching autoregressive (MS-AR) model. We find that predictable non-linearities in inflation is best accounted for by the MS-AR model.
Keywords: inflation
forecasting; Markov switching models; recurrent neural networks