Journal #J-04/1999
Forecasting weekly salmon prices: risk management in fish farming
Atle Guttormsen
Department of Economics & Social Sciences Agricultural University of Norway PO Box 5033, N-1432 Ås, Norway http://www.nlh.no/ior/ e-mail: atle.guttormsen@ior.nlh.no

Guttormsen, A. (1999): "Forecasting weekly salmon prices: risk management in fish farming", Aquacultural Economics and Management, 3(2):159-166.

Abstract:
Production of farmed salmon has increased substantially during the last decade. Most of the salmon production is sold spot, resulting in large price fluctuations, both for the producer and for the exporter. No derivative markets exist; consequently, no one can hedge prices. If prices could be forecasted within reasonable confidence bounds, risk would be reduced. This study use six easy applicable, procedures to forecast weekly producer prices for salmon. The procedures tested were Classical Additive Decomposition, Holt Winters Exponential Smoothing, ARIMA, VAR and two different naive models: post-sample predictive accuracy was evaluated. Results indicated that the CAD model forecasted the direction of price movements best, whereas the VAR model performed best according to accuracy measures.

Key words: Forecasting models, risk management, salmon prices

To order: fax (+47) 6494 3012 or e-mail: ior@ior.nlh.no