MODELING AND FORECASTING MONTHLY FISHERIES CATCHES - COMPARISON OF REGRESSION, UNIVARIATE AND MULTIVARIATE TIME-SERIES METHODS

In the present work, seven forecasting techniques were evaluated on th e basis of their efficiency to model and provide accurate operational forecasts of the monthly commercial landings of 16 species (or groups of species) in the Hellenic marine waters. The development of operatio nal forecasts was based on the following three general categories of f orecasting techniques: (a) deterministic simple or multiple regression models incorporating different exogenous variables (seasonal time-var ying regression, TVS; multiple regression models, MREG, incorporating time, number of fishers, wholesale value of catch and climatic variabl es); (b) univariate time series models (Winter's three parameter expon ential smoothing, WES; ARIMA); and (c) multivariate time series techni ques (harmonic regression, HREG; dynamic regression, DREG; vector auto regressions, VAR). Fits (for 1964-1987) and forecasts (for 1988-1989) obtained by the different models were compared with each other and wit h those of two naive methods (NM1 and NM12) and an empirical one (i.e. combination of forecasts, EMP) using 32 different measures of accurac y. The results revealed that the univariate ARIMA, closely followed by the multivariate DREG time series model, outperformed the others (NM1 , NM12, TVS, MREG, HREG, EMP, VAR and WES) in terms of both fitting an d forecasting accuracy. They were characterised by: (a) higher accurac y in terms of all, or most of the standard and relative statistical me asures that were usually tied together, (b) unbiased fits and forecast s; (c) much better performance than NM1 and NM12. In addition, ARIMA a nd DREG models: (d) explained over 80% of the variance of the transfor med catches; (e) had residuals that were essentially white noise; (f) in all cases predicted the amplitude and the start and end of the fish ing season; and (g) produced forecasts that had mean absolute percenta ge error values under 28.2% for 11 out of 16 monthly series. The diffe rent measures employed also indicated that EMP and WES models outperfo rmed NMI, NM12, TVS, MREG and HREG models. EMP produced forecasts with MAPE values under 23.2% for ten monthly series, whereas WES produced forecasts with MAPE values under 25.3% for eight monthly series. This suggests their potential use in short-term fisheries forecasting. The limitations of the different forecasting techniques, measures of accur acy and data used in the present study are also discussed. Some of the empirical models built also had interesting biological/oceanographic explanations. Hence, the univariate ARIMA and multivariate DREG and VA R time series models all predicted persistence of catches. The univari ate ARIMA and multivariate HREG, DREG and VAR time series models all p redicted cycles in the variability of the catches with periods of 1 an d 2-3 years. Moreover, MREG, DREG and VAR models indicated that the nu mber of fishers, wholesale value of catch and climate may, in a synerg istic fashion, affect long-term trends and short-term variation in the catches of at least some species (or groups of species). Finally, DRE G and VAR models predicted that variability and replacement of anchovy by sardine catches are not due to chance and wind activity over the n orthern Aegean Sea may act as a forcing function.