NATIONAL BUREAU OF ECONOMIC RESEARCH
NATIONAL BUREAU OF ECONOMIC RESEARCH
loading...

Assessing Point Forecast Accuracy by Stochastic Error Distance

Francis X. Diebold, Minchul Shin

NBER Working Paper No. 22516
Issued in August 2016
NBER Program(s):Asset Pricing, Economic Fluctuations and Growth

We propose point forecast accuracy measures based directly on distance of the forecast-error c.d.f. from the unit step function at 0 ("stochastic error distance," or SED). We provide a precise characterization of the relationship between SED and standard predictive loss functions, and we show that all such loss functions can be written as weighted SED's. The leading case is absolute-error loss. Among other things, this suggests shifting attention away from conditional-mean forecasts and toward conditional-median forecasts.

download in pdf format
   (349 K)

email paper

Machine-readable bibliographic record - MARC, RIS, BibTeX

Document Object Identifier (DOI): 10.3386/w22516

Published: Francis X. Diebold & Minchul Shin, 2017. "Assessing point forecast accuracy by stochastic error distance," Econometric Reviews, vol 36(6-9), pages 588-598. citation courtesy of

Users who downloaded this paper also downloaded* these:
Diebold, Schorfheide, and Shin w22615 Real-Time Forecast Evaluation of DSGE Models with Stochastic Volatility
Stock and Watson w21282 Core Inflation and Trend Inflation
Solon, Haider, and Wooldridge w18859 What Are We Weighting For?
Baumeister and Hamilton w20741 Sign Restrictions, Structural Vector Autoregressions, and Useful Prior Information
Bajari, Nekipelov, Ryan, and Yang w20955 Demand Estimation with Machine Learning and Model Combination
 
Publications
Activities
Meetings
NBER Videos
Themes
Data
People
About

National Bureau of Economic Research, 1050 Massachusetts Ave., Cambridge, MA 02138; 617-868-3900; email: info@nber.org

Contact Us