Combining density forecasts

By Stephen G. Hall, James Mitchell. 2007

317 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/95c336847e20a0cc8224f593cafaa99f128f55dc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Management Science and Operations Research

Citations in the corpus

Bayesian Nonparametric Calibration and Combination of Predictive Distributions (2015, background): “Moreover, the traditional linear pool (Stone, 1961; Hall and Mitchell, 2007) has been generalized to nonlinear aggregation schemes (Fawcett et al.”
Electricity price forecasting: A review of the state-of-the-art with a look into the future (2014, background): “Hall and Mitchell (2007) propose a data-driven approach to the direct combination of density forecasts by taking a weighted linear combination of the competing density forecasts. The combination weights are chosen to minimize the ‘distance’, as measured by the Kullback–Leibler information criterion,”
Using Entropic Tilting to Combine BVAR Forecasts With External Nowcasts (2014, background): “In particular, merging a multi-step BVAR forecast density with an external nowcast is not a traditional density combination problem in the spirit of Stone (1961), Hall and Mitchell (2007), Geweke and Amisano (2011), and Gneiting and Ranjan (2013).”
The Evolution of Forecast Density Combinations in Economics (2018, background): “Applications by Mitchell and Hall (2005) and Hall and Mitchell (2007) indicated that the density forecasts of inflation from the Bank of England (as published in their fan charts) and the National Institute of Economic and Social Research in the UK could be improved if combined in real-time with…”
Using Stacking to Average Bayesian Predictive Distributions (with Discussion) (2017, methodology): “…also parallels the historical development of Bayesian density combination methods following the literature on combination of point forecasts (e.g. Hall and Mitchell, 2007; Geweke and Amisano, 2011; Billio et al., 2013; Aastveit et al., 2014; Kapetanios et al., 2015; Aastveit et al., 2018; Del…”
A MIDAS Approach to Modeling First and Second Moment Dynamics (2016, unknown): “To measure the importance of such differences, we follow Amisano and Giacomini (2007), Geweke and Amisano (2010), and Hall and Mitchell (2007) and compute the average log-score differential (LSD) LSD i = t τ =t (LS i,τ − LS RW,τ ) , (38) where LS i,τ (LS RW,τ ) denotes the log-score of model i…”
Combining inflation density forecasts (2010, background): “(2) Thus, when ElnS1 > ElnS2 then KLIC1 KLIC2.”
Quantile aggregation of density forecasts (2014, unknown): “Some examples are Wallis (2005, 2011), Hall and Mitchell (2007), Mitchell and Wallis (2010), Geweke and Amisano (2011), Fawcett et al. (2013).”
Advances in Forecasting Under Instability (2012, unknown): “Hall and Mitchell (2007) discuss techniques to combine density forecasts.”
Reliability, sufficiency, and the decomposition of proper scores (2009, background): “res or simply opinions from a number of disagreeing experts. A simple and widely practised way to combine these forecasts is by convex mixture (Winkler, 1989; Clemen, 1989; Doblas-Reyes et al., 2005; Hall and Mitchell, 2007). For the discussion in this paper, it is unimportant how the weights are ob”
Combining forecast densities from VARs with uncertain instabilities (2010, methodology): “Following Amisano & Giacomini (2007) and Hall & Mitchell (2007), we use the logarithmic score to measure density fit for each model through the evaluation period.”
Dynamic Prediction Pools: An Investigation of Financial Frictions and Forecasting Performance (2016, unknown): “Hall and Mitchell (2007) and Geweke and Amisano (2011) use the sequence of predictive densities, which measure the likelihood of ex-post outcomes from the perspective of a model’s ex-ante forecast distribution, to construct optimal linear pools.1 These pools are optimal in the sense that the…”
Generalised Density Forecast Combinations (2015, unknown): “…Bayesian model averaging with linear combinations of predictive densities, so-called “opinion pools”, where the weights on the component density forecasts are optimised to maximise the score, typically the logarithmic score, of the density combination as suggested in Hall & Mitchell (2007).”
Combining forecasts – forty years later (2011, background): “It seems to be agreed to base the weights on past forecast performance as measured by the average logarithmic score, possibly allowing for time variation in the weights (Hall and Mitchell, 2007; Geweke and Amisano, 2009; Jore et al., 2010; Kascha and Ravazzolo, 2010).”
Combining density forecasts using focused scoring rules (2017, unknown): “(1) As discussed in detail in Hall and Mitchell (2007), the log scoring rule is closely related to information-theoretic goodness-of-fit measures such as the Kullback–Leibler information criterion (KLIC).”