Forecasting Inflation with Thick Models and Neural Networks

35 Pages Posted: 14 Oct 2004

See all articles by Paul D. McNelis

Paul D. McNelis

Georgetown University - Department of Economics

Peter McAdam

European Central Bank (ECB); University of Surrey, Economics

Date Written: April 2004

Abstract

This paper applies linear and neural network-based "thick" models for forecasting inflation based on Phillips-curve formulations in the USA, Japan and the euro area. Thick models represent "trimmed mean" forecasts from several neural network models. They outperform the best performing linear models for "real-time" and "bootstrap" forecasts for service indices for the euro area, and do well, sometimes better, for the more general consumer and producer price indices across a variety of countries.

Keywords: Neural Networks, Thick Models, Phillips curves, real-time

JEL Classification: C12, E31

Suggested Citation

McNelis, Paul D. and McAdam, Peter, Forecasting Inflation with Thick Models and Neural Networks (April 2004). ECB Working Paper No. 352. Available at SSRN: https://ssrn.com/abstract=533014

Paul D. McNelis (Contact Author)

Georgetown University - Department of Economics ( email )

Washington, DC 20057
United States
202-687 5573 (Phone)
202-687 6102 (Fax)

Peter McAdam

European Central Bank (ECB) ( email )

Kaiserstrasse 29
Eurotower
D-60311 Frankfurt am Main
Germany
0049 69 13440 (Phone)
0044 69 1344 6000 (Fax)

University of Surrey, Economics ( email )

Guildford
Guildford, Surrey GU2 5XH
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Downloads
364
Abstract Views
3,898
rank
81,898
PlumX Metrics