A Mixture Model for Estimating Discarded Bycatch from Data with Many Zero Observations: Tuna Discards in the Eastern Tropical Pacific Ocean
Fisheries discard data for unwanted species often show a smooth distribution of the per-set discards, but a large number of zero observations, a set which does not fit easily with a standard distribution. A proposed distribution mixture model would have one component showing the zero observations, a...
Gespeichert in:
Veröffentlicht in: | Fishery bulletin (Washington, D.C.) D.C.), 1996-04, Vol.94 (2), p.330-330 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Fisheries discard data for unwanted species often show a smooth distribution of the per-set discards, but a large number of zero observations, a set which does not fit easily with a standard distribution. A proposed distribution mixture model would have one component showing the zero observations, and the other showing the positive discards data. This representation of a mixture model works when the discard observations are rounded to integers, and can thus estimate the proportions of rounded zeros (small amounts of discards) and true zeros (no discards). The model is applied to data collected from the commercial tuna industry operating in the eastern tropical Pacific Ocean between 1989 92. The model parameters can vary as a function of fishing strategy and geographic location. |
---|---|
ISSN: | 0090-0656 |