Abstract
In many applied cases of ecological and environmental modelling, there is a sizeable variation among the measured variables due to measurement- and sampling error. Such measurement- and sampling error among the independent variables may lead to regression dilution and biased prediction intervals in traditional empirical modelling. It is possible to avoid these shortcomings by subsampling and hierarchical modelling, but this is still not a common practice. Here, it is recommended to model the measurement- and sampling errors by integrating the stochastic modelling of the errors into hierarchical ecological and environmental models.
Footnotes
cfd{at}bios.au.dk
Copyright
The copyright holder for this preprint is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-ND 4.0 International license.