On the asymmetry of the symmetric MAPE

Goodwin, Paul; Lawton, Richard

doi:10.1016/s0169-2070(99)00007-2

Cited by 240 publications

(100 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, we performed additional supplementary analyses on the aggregated level to investigate collective decisionmaking outcomes. To increase the robustness of our results, we performed the analyses using three separate measures: the decision quality score as applied on the user level, as well as the Mean Absolute Percent Error (MAPE) and Haessel R 2 , which are commonly used in prediction market research to evaluate forecasting errors (Goodwin andLawton 1999, King et al 1993). 8 For rating scales, we aggregated all user ratings for each idea by geometric mean, which is the recommended aggregation in collective intelligence tasks (Lorenz et al 2011).…”

Section: Supplementary Mechanism-level Resultsmentioning

confidence: 99%

Rate or Trade? Identifying Winning Ideas in Open Idea Sourcing

Blohm

Riedl

Füller

et al. 2016

Information Systems Research

View full text Add to dashboard Cite

I nformation technology (IT) has created new patterns of digitally-mediated collaboration that allow opensourcing of ideas for new products and services. These novel sociotechnical arrangements afford finely-grained manipulation of how tasks can be represented and have changed the way organizations ideate. In this paper, we investigate differences in behavioral decision-making resulting from IT-based support of open idea evaluation. We report results from a randomized experiment of 120 participants comparing IT-based decision-making support using a rating scale (representing a judgment task) and a preference market (representing a choice task). We find that the rating scale-based task invokes significantly higher perceived ease of use than the preference market-based task and that perceived ease of use mediates the effect of the task representation treatment on the users' decision quality. Furthermore, we find that the understandability of ideas being evaluated, which we assess through the ideas' readability, and the perception of the task's variability moderate the strength of this mediation effect, which becomes stronger with increasing perceived task variability and decreasing understandability of the ideas. We contribute to the literature by explaining how perceptual differences of task representations for open idea evaluation affect the decision quality of users and translate into differences in mechanism accuracy. These results enhance our understanding of how crowdsourcing as a novel mode of value creation may effectively complement traditional work structures.

show abstract

Section: Supplementary Mechanism-level Resultsmentioning

confidence: 99%

Rate or Trade? Identifying Winning Ideas in Open Idea Sourcing

Blohm

Riedl

Füller

et al. 2016

Information Systems Research

View full text Add to dashboard Cite

show abstract

“…Thus, the measure still involves division by a number close to zero. and Lawton (1999) and Koehler (2001) for further discussion on this point.…”

Section: Measures Based On Percentage Errorsmentioning

confidence: 99%

“…The relative measures are all computed relative to a naïve (random walk) method. Corporation, 1990-1999. Data source: Tsay (2002 Makridakis, Wheelwright and Hyndman (1998) Hanke andReitsch, 1995, p.120, andBowerman, O'Connell &Koehler, 2004, p.18) and it was the primary measure in the M-competition (Makridakis, et al, 1982).…”

Section: Introductionmentioning

confidence: 99%

Another look at measures of forecast accuracy

Hyndman

Koehler

2006

International Journal of Forecasting

3,912

1,912

View full text Add to dashboard Cite

“…For the same value of Y t , the value of 2|Y t − F t |/(Y t + F t ) has a heavier penalty when forecasts are high compared to when forecasts are low. See Goodwin & Lawton (1999) and Koehler (2001) for further discussion on this point.…”

Section: Forecast Evaluation and Accuracy Measuresmentioning

confidence: 99%

25 years of time series forecasting

Gooijer

Hyndman

2006

International Journal of Forecasting

1,295

632

View full text Add to dashboard Cite

During this period, over one third of all papers published in these journals concerned time series forecasting. We also review highly influential works on time series forecasting that have been published elsewhere during this period. Enormous progress has been made in many areas, but we find that there are a large number of topics in need of further development. We conclude with comments on possible future research directions in this field.

show abstract

On the asymmetry of the symmetric MAPE

Cited by 240 publications

References 6 publications

Rate or Trade? Identifying Winning Ideas in Open Idea Sourcing

Rate or Trade? Identifying Winning Ideas in Open Idea Sourcing

Another look at measures of forecast accuracy

25 years of time series forecasting

Contact Info

Product

Resources

About