Model Confidence Sets and forecast combination

B-Tier
Journal: International Journal of Forecasting
Year: 2017
Volume: 33
Issue: 1
Pages: 48-60

Authors (2)

Samuels, Jon D. (not in RePEc) Sekkel, Rodrigo M. (Bank of Canada)

Score contribution per author:

1.005 = (α=2.01 / 2 authors) × 1.0x B-tier

α: calibrated so average coauthorship-adjusted count equals average raw count

Abstract

A longstanding finding in the forecasting literature is that averaging the forecasts from a range of models often improves upon forecasts based on a single model, with equal weight averaging working particularly well. This paper analyzes the effects of trimming the set of models prior to averaging. We compare different trimming schemes and propose a new approach based on Model Confidence Sets that takes into account the statistical significance of the out-of-sample forecasting performance. In an empirical application to the forecasting of U.S. macroeconomic indicators, we find significant gains in out-of-sample forecast accuracy from using the proposed trimming method.

Technical Details

RePEc Handle
repec:eee:intfor:v:33:y:2017:i:1:p:48-60
Journal Field
Econometrics
Author Count
2
Added to Database
2026-01-29