Another look at measures of forecast accuracy
International Journal of ForecastingPublished 26 May 2006
Rob J. Hyndman, Anne B. Koehler
Citations5,343
SJR quartileQ1
SJR score2.43
SNIP3.36
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
We discuss and compare measures of accuracy of univariate time series forecasts. The methods used in the M-competition as well as the M3-competition, and many of the measures recommended by previous authors on this topic, are found to be degenerate in commonly occurring situations. Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
Keywords
Decision SciencesEconomics, Econometrics and Finance
International Journal of ForecastingThe M3-Competition: results, conclusions and implications
1,701 Citations2000Spyros Makridakis, Michèle Hibon
Journal of ForecastingThe accuracy of extrapolation (time series) methods: Results of a forecasting competition
1,469 Citations1982Spyros Makridakis, A. Andersen +7 more
The results of a forecasting competition are presented to provide empirical evidence about differences found to exist among the various extrapolative (time series) methods used in the competition.
Principles of forecasting : a handbook for researchers and practitioners
1,061 Citations2001J. Scott Armstrong
A review of the evidence showed that role playing was effective in matching results for seven of eight experiments and was correct for 56 percent of 143 predictions, while unaided expert opinions were correct for 16 percent of 172 predictions.
International Journal of ForecastingA state space framework for automatic forecasting using exponential smoothing methods
1,004 Citations2002Rob J. Hyndman, Anne B. Koehler +2 more
A new approach to automatic business forecasting based on an extended range of exponential smoothing methods that allows the easy calculation of the likelihood, the AIC and other model selection criteria, and the computation of prediction intervals for each method.
International Journal of ForecastingAccuracy measures: theoretical and practical concerns
816 Citations1993Spyros Makridakis
This paper describes such as system which allows the user to do preliminary analysis of his data to identify the forecasting technique or class of techniques most appropriate for his situation and to apply those in developing a forecast.
International Journal of ForecastingThe theta model: a decomposition approach to forecasting
461 Citations2000Vassilios Assimakopoulos, Κωνσταντίνος Νικολόπουλος
Elements of Forecasting
422 Citations1997Francis X. Diebold
Journal of ForecastingEconomic and statistical measures of forecast accuracy
403 Citations2000Clive W. J. Granger, M. Hashem Pesaran
An empirical application to the problem of stock market predictability is provided, and the conditions under which such predictability could be exploited in the presence of transaction costs are discussed.
Journal of ForecastingOn the limitations of comparing mean square forecast errors
398 Citations1993Michael P. Clements, David F. Hendry
International Journal of ForecastingOn the asymmetry of the symmetric MAPE
316 Citations1999Paul Goodwin, Richard Lawton
International Journal of ForecastingExponential smoothing model selection for forecasting
266 Citations2005Baki Billah, Maxwell L. King +2 more
The results indicate that the information criterion approach appears to provide the best basis for an automated approach to method selection, provided that it is based on Akaike's information criterion.
International Journal of ForecastingThe evaluation of extrapolative forecasting methods
266 Citations1992Robert Fildes
Examining how a forecasting method should be chosen based on analyzing alternative loss functions concludes that exponential smoothing and ‘naive’ models, previously thought to be ‘robust’ performers, forecast poorly for the particular set of time series under analysis, whatever error measure is used.
Forecasting, time series, and regression : an applied approach
265 Citations2005Bruce L. Bowerman, Richard T. O'Connell +1 more
International Journal of ForecastingThe M3 competition: Statistical tests of the results
180 Citations2004Alex Koning, Philip Hans Franses +2 more
A new methodology that has not previously been used to evaluate economic forecasts: multiple comparisons is introduced, which concludes that the accuracy of the various methods does differ significantly, and that some methods are significantly better than others.
International Journal of ForecastingUnmasking the Theta method
149 Citations2002Rob J. Hyndman, Baki Billah
The Theta method of forecasting performed particularly well in the M3-competition and is therefore of interest to forecast practitioners and it is shown that the forecasts obtained are equivalent to simple exponential smoothing with drift.
Management ScienceEvaluating Forecast Performance in an Inventory Control System
130 Citations1990Everette S. Gardner
DemographyA note on the measurement of accuracy for subnational demographic estimates
48 Citations2000David A. Swanson, Jeff Tayman +1 more
It is argued thatMAPE-R is a more appropriate summary measure of average absolute percentage error when the guidelines indicate that MAPE is not valid, and a transformed MAPE (MAPET) is calculated using a modified Box-Cox method.
International Journal of ForecastingAn MSE statistic for comparing forecast accuracy across series
46 Citations1990Patrick A. Thompson
International Journal of ForecastingA model selection strategy for time series with increasing seasonal variation
44 Citations1998Philip Hans Franses, Anne B. Koehler
International Journal of ForecastingJudgmental forecasting in the presence of loss functions
32 Citations2004Michael Lawrence, Marcus O’Connor