Penguin island closure feasibility study analysis results update: random effects models applied to both Western and Eastern Cape islands

Working Paper

2014

Permanent link to this Item
Authors
Journal Title
Link to Journal
Journal ISSN
Volume Title
Publisher
Publisher

University of Cape Town

License
Series
Abstract
This Addendum updates results from previous papers using random effects instead of fixed effects models for the year factors. Results are now given for Bird and St Croix islands in addition to those for Dassen and Robben islands. The results from random effects models are qualitatively unchanged from those given earlier from the fixed effects models, except that the periods required to obtain statistically significant results are extended somewhat as a result of the removal of the negative bias in the residual variance estimates for the earlier fixed effects models.
Description

Reference:

Collections