Arbeitspapier

Estimating Loss Functions of Experts

We propose a new and simple methodology to estimate the loss function associated with experts' forecasts. Under the assumption of conditional normality of the data and the forecast distribution, the asymmetry parameter of the lin-lin and linex loss function can easily be estimated using a linear regression. This regression also provides an estimate for potential systematic bias in the forecasts of the expert. The residuals of the regression are the input for a test for the validity of the normality assumption. We apply our approach to a large data set of SKU-level sales forecasts made by experts and we compare the outcomes with those for statistical model-based forecasts of the same sales data. We find substantial evidence for asymmetry in the loss functions of the experts, with underprediction penalized more than overprediction.

Sprache
Englisch

Erschienen in
Series: Tinbergen Institute Discussion Paper ; No. 11-177/4

Klassifikation
Wirtschaft
Econometric Modeling: General
Forecasting Models; Simulation Methods
Thema
model forecasts
expert forecasts
loss functions
asymmetry
econometric models
Absatz
Prognoseverfahren
Sachverständige
Vergleich
Ökonometrisches Modell

Ereignis
Geistige Schöpfung
(wer)
Franses, Philip Hans
Legerstee, Rianne
Paap, Richard
Ereignis
Veröffentlichung
(wer)
Tinbergen Institute
(wo)
Amsterdam and Rotterdam
(wann)
2011

Handle
Letzte Aktualisierung
20.09.2024, 08:20 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Objekttyp

  • Arbeitspapier

Beteiligte

  • Franses, Philip Hans
  • Legerstee, Rianne
  • Paap, Richard
  • Tinbergen Institute

Entstanden

  • 2011

Ähnliche Objekte (12)