Consensus Forecasting Using Relative Error Weights

Author: Lackman Conway   Brandon Charles  

Publisher: Emerald Group Publishing Ltd

ISSN: 0263-4503

Source: Marketing Intelligence & Planning, Vol.12, Iss.1, 1994-01, pp. : 37-41

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Employs weights based on relative errors produced by two or more models to formulate a consensus forecast. This method better captures changing patterns through time and sharply reduces size of forecast error.