Premium
Bayesian Composite Qualitative Forecasting: Hog Prices Again
Author(s) -
Dorfman Jeffrey H.
Publication year - 1998
Publication title -
american journal of agricultural economics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.949
H-Index - 111
eISSN - 1467-8276
pISSN - 0002-9092
DOI - 10.2307/1244556
Subject(s) - consensus forecast , correctness , econometrics , bayesian probability , set (abstract data type) , logit , computer science , variety (cybernetics) , basis (linear algebra) , statistics , mathematics , artificial intelligence , algorithm , geometry , programming language
A new method for forming composite qualitative forecasts is presented. A set of qualitative forecasts is evaluated using auxiliary logit models to predict the probability of each forecast's correctness. Individual model forecasts are then combined on the basis of normalized values of these probabilities. This method is demonstrated with three sets of forecasts on the direction of change in hog prices (up or down). The application shows that without any information on the manner in which the individual forecasts are generated this method can form a composite forecast that is superior according to a variety of metrics for evaluating qualitative forecasts.