Another look at measures of forecast accuracy

Hyndman, Rob J.; Koehler, Ann B

doi:10.1016/j.ijforecast.2006.03.001

Cited by 3,787 publications

(2,174 citation statements)

References 19 publications

Supporting

Mentioning

1,912

Contrasting

Unclassified

Order By: Relevance

“…As percentage measures such as the MAPE and the MDPV are heavily skewed when the series have values close to zero (see e.g. Hyndman and Koehler (2006); this is also confirmed in unreported preliminary experiments), for each series we subtract the overall minimum (calculated over all series) from all values to obtain a series of non-negative values, and then we increment all values by 1, to achieve a series which only contains values greater 1. In this way, new coefficients are estimated and a new series is generated for each iteration.…”

Section: Univariate Casementioning

confidence: 68%

“…This paper aims to investigate the usefulness of a blocked cross-validation (BCV) scheme along with directional accuracy measures for forecast evaluation. Several forecast error measures such as scale-dependent, percentage and relative measures have been used largely for forecast evaluation (see Hyndman and Koehler (2006); Costantini and Pappalardo (2010), Costantini and Kunst (2011) among others).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the usefulness of cross-validation for directional forecast evaluation

Bergmeir

Costantini

Benítez

2014

Computational Statistics & Data Analysis

View full text Add to dashboard Cite

The usefulness of a predictor evaluation framework which combines a blocked cross-validation scheme with directional accuracy measures is investigated. The advantage of using a blocked cross-validation scheme with respect to the standard out-of-sample procedure is that cross-validation yields more precise error estimates of the prediction error since it makes full use of the data. In order to quantify the gain in precision when directional accuracy measures are considered, a Monte Carlo analysis using univariate and multivariate models is provided. The experiments indicate that more precise estimates are obtained with the blocked cross-validation procedure. An application is carried out on forecasting UK interest rate for illustration purposes. The results show that in such a situation with small samples the crossvalidation scheme may have considerable advantages over the standard out-of-sample evaluation procedure as it may help to overcome problems induced by the limited information the directional accuracy measures contain due to their binary nature.

show abstract

Section: Univariate Casementioning

confidence: 68%

Section: Introductionmentioning

confidence: 99%

On the usefulness of cross-validation for directional forecast evaluation

Bergmeir

Costantini

Benítez

2014

Computational Statistics & Data Analysis

View full text Add to dashboard Cite

show abstract

“…The forecasts are evaluated using the Relative Mean Absolute Error (RMAE) (see Davydenko and Fildes, 2013) and the Mean Absolute Scaled Error (MASE) (see Hyndman and Koehler, 2006). Both these measures permit calculating forecasting accuracy across time series of different scales.…”

Section: Methodsmentioning

confidence: 99%

Forecasting with temporal hierarchies

Athanasopoulos

Kourentzes

Petropoulos

2017

European Journal of Operational Research

Self Cite

196

167

View full text Add to dashboard Cite

This paper introduces the concept of Temporal Hierarchies for time series forecasting. A temporal hierarchy can be constructed for any time series by means of non-overlapping temporal aggregation. Predictions constructed at all aggregation levels are combined with the proposed framework to result in temporally reconciled, accurate and robust forecasts. The implied combination mitigates modelling uncertainty, while the reconciled nature of the forecasts results in a unified prediction that supports aligned decisions at different planning horizons: from shortterm operational up to long-term strategic planning. The proposed methodology is independent of forecasting models. It can embed high level managerial forecasts that incorporate complex and unstructured information with lower level statistical forecasts. Our results show that forecasting with temporal hierarchies increases accuracy over conventional forecasting, particularly under increased modelling uncertainty. We discuss organisational implications of the temporally reconciled forecasts using a case study of Accident & Emergency departments.

show abstract

“…MAPE is commonly used to evaluate cross-sectional forecasts [54]. MAPE values for the main variables of the model are shown in table 4.6.…”

Section: Model Validation and Verificationmentioning

confidence: 99%

Studying the relationship between economic growth, CO2 emissions, and the environmental Kuznets curve in Venezuela (1980–2025)

Robalino-López

Nieto

García‐Ramos

et al. 2015

Renewable and Sustainable Energy Reviews

144

View full text Add to dashboard Cite

This work tries to determine whether it is possible to stabilize CO 2 emissions under a rapid increase of Gross Domestic Product in a medium term. The paper is an effort to study in detail how changes in the driving forces of the economy affect CO 2 emissions. We study the case of Venezuela for the period 1980-2025, using the methodology proposed by Robalino-López et al. [1,2], which is based on an extension of the Kaya identity and on a GDP formation approach that includes the effect of renewable energies. We test the environmental Kuznets curve (EKC) [3] hypothesis in a coming future under different economic scenarios considering, therefore, not only past data but also projections for the coming years. We use cointegration techniques [4] and the Jaunky [5] specification to test the fulfillment of the EKC hypothesis in Venezuela. Our predictions show that Venezuela does not fulfill the EKC hypothesis, but however, the country could be on the way to achieve environmental stabilization in the medium term. This stabilization could be accomplished combining economic growth with increasing use of renewable energy, appropriated changes in the energy matrix, and in the productive sectoral structure.

show abstract

Another look at measures of forecast accuracy

Cited by 3,787 publications

References 19 publications

On the usefulness of cross-validation for directional forecast evaluation

On the usefulness of cross-validation for directional forecast evaluation

Forecasting with temporal hierarchies

Studying the relationship between economic growth, CO2 emissions, and the environmental Kuznets curve in Venezuela (1980–2025)

Contact Info

Product

Resources

About