On the basis of the results of the simple linear models by métier, Generalized Linear Models (GLM, [18]) are applied for each fleet segment to test the significance of the métier categorical variable on the variable costs and to derive the coefficients for the disaggregation process. [...] The variable costs associated with each observed vessel were then adjusted proportionally to the percentage of activity of the observations: if the prevalent métier represents the 75% for the total activity monitored for a vessel, all the type of variable costs associated to that métier for that vessel were estimated as the 75% of the variable costs collected for the vessel. [...] Table 4, representing the outcome of the disaggregation function in the SECFISH R package, reports the comparison between the original costs by fleet segments and the sum of the disag- gregated costs. [...] It should be noticed that, on one hand, the methodology facilitates the disaggregation of the variable costs in the presence of dependency both on the métier and on the transversal vari- ables; on the other hand, it helps identifying the relationship between costs and transversal var- iables in the case of a unique prevalent métier or non-dependence on the métier. [...] A necessary disclaimer for the proper use of the method presented here is related to the completeness of the input data: in order to allow a reliable analysis, the individual vessel data- set used for deriving the regression coefficients needs to be large enough and properly repre- sent the distribution of the effort by métier within the whole fleet segment.
Authors
- Pages
- 18
- Published in
- Germany