The maximum and minimum of primary forecasts
Article Abstract:
The maximum and minimum of a set of forecasts may improve forecasting ability since they can have low correlation with the primary forecast allowing the data to be included in combinations. Empirical data illustrates the use of the maximum, minimum, mean and median of a set of forecasts included in a primary forecast. In addition, it enhances the accuracy of the primary forecast compared to the forecast made without the aforementioned data.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1992
User Contributions:
Comment about this article or add new information about this topic:
The uses and abuses of 'consensus' forecasts
Article Abstract:
A discussion on the uses and abuses of consensus forecasts which is a combination of individual forecasts is presented. A review of literature indicates the feasability of consensus forecasting, but tautological properties should not be confused with empirical results. One should not rely heavily on consensus forecasting since there may be a tendency to skew individual forecasts in light of the consensus.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1992
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: The method of simulated scores for the estimation of LDV models. An information-theoretic alternative to generalized method of moments estimation
- Abstracts: Two characterizations of bargaining sets. The core and the hedonic core: equivalence and comparative statics
- Abstracts: Nonuniform Bertrand competition. Stochastic monotonicity and stationary distributions for dynamic economies. Entry, exit, and firm dynamics in long run equilibrium
- Abstracts: A comment of Aumann's Bayesian view. Efficiency and immediate agreement: a reply to Hart and Levy. Asymptotic efficiency in large exchange economies with asymmetric information
- Abstracts: On trend extraction models: reply on comments by Harvey. Algorithms for explaining forecast revisions