How can the functional reponse best be determined?

Abstract

We evaluated three methods for the analysis of functional response data by asking whether a given method could discriminate among functional responses and whether it could accurately identify regions of positive density-dependent predation. We evaluated comparative curve fitting with foraging models, linear least-squares analysis using the angular transformation, and logit analysis. Using data from nature and simulations, we found that the analyses of predation rates with the angular transformation and logit analysis were best at consistently determining the "true" functional response, i.e. the model used to generate simulated data. These methods also produced the most accurate estimates of the "true" regions of density dependence. Of these two methods, functional response data best fulfill the assumptions of logit analysis. Angularly transformed predation rates only approximate the assumptions of linear leastsquares analysis for predation rates between 0.1 and 0.9. Lack-of-fit statistics can reveal inadequate fit of a model to a data set where simple regression statistics might erroneously suggest a good match.

Keywords: Curve fitting; Density dependence; Functional response; Logit; Predation.