In the present work, eight forecasting techniques are evaluated on the basis of their efficiency to model and provide accurate operational forecasts of the annual commercial landings of 16 species or groups of species in the Hellenic (Greek) marine waters. The development of operational forecasts was based on the following four general categories of forecasting techniques: (a) deterministic simple or multiple regression models incorporating different exogenous variables (time-varying regression, TV; multiple regression models incorporating time, fishing effort, wholesale value of catch and climatic variables, MREG); (b) univariate time series models (Brown's one parameter exponential smoothing, BES; Holt's two parameter exponential smoothing, HES; and AutoRegressive Integrated Moving Average (ARIMA)); (c) multivariate time series techniques (harmonic regression, HREG; dynamic regression, DREG; and vector autoregressions, VAR); and (d) the ‘biological’ exponential surplus-yield model, FOX. Fits (for 1964–1987) and forecasts (for 1988–1989) obtained by the different models were compared with each other and with those of a naive method (NM) and an empirical one (i.e. combination of forecasts, EMP) using 32 different measures of accuracy. The results revealed that HREG and MREG models outperformed, in terms of fitting accuracy, the remaining eight models (NM, TV, BES, HES, FOX, ARIMA, VAR and EMP). They were both characterised by: (a) higher accuracy in terms of all, or most, standard and relative statistical measures; (b) unbiased fits; (c) much better performance than NM; (d) transformed errors which were essentially white noise. In addition, HREG and MREG models: (e) explained from 79% to 97% of the variability of 13 transformed annual catches and from 31% to 61% for the remaining ones; (f) produced fits with MAPE values ranging from 3.4% to 21.2%; (g) in all, or most cases, predicted the between year variations during the fitting period, 1964–1987. In terms of forecasting performance, however, not a single best approach was found for the 16 annual catches. In general, BES and, to a lesser extent, HES, NM (which actually is an ARIMA (0,1,0)), EMP and HREG models were among the best performers more often, produced the worst forecasts more rarely and were generally characterised by the higher number of stable forecasts and of forecasts with MAPE <20% and <10%. TV was also efficient for some annual series. Conversely, the poorest performers (FOX, MREG and ARIMA) rarely did better than average. The biological FOX models produced the least accurate and biased fits, bad forecasts (> 34.1%) in two out of four cases, and were characterised by transformed errors that were significantly ( P < 0.05) autocorrelated. Some of the empirical models also had interesting explanations. Hence, the univariate ARIMA and multivariate VAR time series models predicted persistence of catches. The multivariate VAR and HREG time series models also predicted cycles in the variability of the catches with periods of 2–3 years. Moreover, FOX and MREG models indicated that fishing effort, wholesale value of catch and climate may, in a synergetic fashion, affect long-term trends and short-term variation in the catches of, at least, some species (or groups of species). Finally, MREG and VAR models predicted that variability and replacement of anchovy by sardine catches are not due to chance, and wind activity over the northern Aegean Sea may act as a forcing function.
Read full abstract
Jan 10, 2022
Erwan Sulistianto 
Open Access
