Winter 2005
Autumn 2004
Spring 2004
Winter 2004
Spring 2003
Winter 2003




























































































Forecasting with judgement

Simone Manganelli (European Central Bank)

This paper argues that forecasts should maximise the objective function in a stochastic, rather than deterministic, way. We explicitly incorporate two elements into the estimation framework: a subjective guess on the variable to be forecast and a probability reflecting the confidence associated with it. Starting from the subjective guess, the judgmental forecast increases the objective function only as long as its first derivatives are statistically different from zero. We show that the new estimator includes as a special case the classical estimator and discuss its relationship with Bayesian estimators. We study the properties of this new estimator with a detailed risk analysis and a Monte Carlo simulation. Finally, we illustrate the performance of the estimator with applications to mean-variance portfolio selection and to GDP forecast.

Contact  | Sitemap  | Directories  | Maps  & Directions  | Giving to Stanford
Copyright 2004Stanford University. All Rights Reserved. Stanford, CA 94305, (650) 723-2300
Terms of Use Copyright Complaints