Assessing point forecast accuracy by stochastic loss distance

Francis X. Diebold; Minchul Shin

doi:10.1016/j.econlet.2015.02.018

Assessing point forecast accuracy by stochastic loss distance

Francis X. Diebold, Minchul Shin

Research output: Contribution to journal › Article › peer-review

Abstract

We explore the evaluation (ranking) of point forecasts by a "stochastic loss distance" (SLD) criterion, under which we prefer forecasts with loss distributions F(L(e)) "close" to the unit step function at 0. We show that, surprisingly, ranking by SLD corresponds to ranking by expected loss.

Original language	English (US)
Pages (from-to)	37-38
Number of pages	2
Journal	Economics Letters
Volume	130
DOIs	https://doi.org/10.1016/j.econlet.2015.02.018
State	Published - May 1 2015
Externally published	Yes

Keywords

Absolute-error loss
Expected loss
Forecast evaluation
Forecast ranking
Quadratic loss
Squared-error loss

ASJC Scopus subject areas

Finance
Economics and Econometrics

Online availability

10.1016/j.econlet.2015.02.018

Library availability

Discover UIUC Full Text

Cite this

@article{4af709f46a5747a8b8128deb25302ef6,

title = "Assessing point forecast accuracy by stochastic loss distance",

abstract = "We explore the evaluation (ranking) of point forecasts by a {"}stochastic loss distance{"} (SLD) criterion, under which we prefer forecasts with loss distributions F(L(e)) {"}close{"} to the unit step function at 0. We show that, surprisingly, ranking by SLD corresponds to ranking by expected loss.",

keywords = "Absolute-error loss, Expected loss, Forecast evaluation, Forecast ranking, Quadratic loss, Squared-error loss",

author = "Diebold, {Francis X.} and Minchul Shin",

note = "Publisher Copyright: {\textcopyright} 2015 Elsevier B.V.",

year = "2015",

month = may,

day = "1",

doi = "10.1016/j.econlet.2015.02.018",

language = "English (US)",

volume = "130",

pages = "37--38",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Assessing point forecast accuracy by stochastic loss distance

AU - Diebold, Francis X.

AU - Shin, Minchul

PY - 2015/5/1

Y1 - 2015/5/1

N2 - We explore the evaluation (ranking) of point forecasts by a "stochastic loss distance" (SLD) criterion, under which we prefer forecasts with loss distributions F(L(e)) "close" to the unit step function at 0. We show that, surprisingly, ranking by SLD corresponds to ranking by expected loss.

AB - We explore the evaluation (ranking) of point forecasts by a "stochastic loss distance" (SLD) criterion, under which we prefer forecasts with loss distributions F(L(e)) "close" to the unit step function at 0. We show that, surprisingly, ranking by SLD corresponds to ranking by expected loss.

KW - Absolute-error loss

KW - Expected loss

KW - Forecast evaluation

KW - Forecast ranking

KW - Quadratic loss

KW - Squared-error loss

UR - http://www.scopus.com/inward/record.url?scp=84925011186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925011186&partnerID=8YFLogxK

U2 - 10.1016/j.econlet.2015.02.018

DO - 10.1016/j.econlet.2015.02.018

M3 - Article

AN - SCOPUS:84925011186

SN - 0165-1765

VL - 130

SP - 37

EP - 38

JO - Economics Letters

JF - Economics Letters

ER -

Assessing point forecast accuracy by stochastic loss distance

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this