Given a matrix extracts an index of the extents at which the AUC (or other test statistic) overcomes the Vm coefficient obtained from the non-linear model fitting. Non-linear asymptotic functions are tested: Michaelis-Menten, 3-parameter asymptotic exponential (exponential 3) and 2-parameter asymptotic exponential (exponential 2). For details about these functions, see the "non-linear regression" section of THE R BOOK by Michael J. Crawley.
AUCextentFit(testmat, extents, diagrams = FALSE)Matrix. Data in each row is fitted separatelly.
Vector of increasing values that is fitted to each row in testmat.
Logical (default is FALSE). If TRUE diagrams of the fitted models are returned.
Named integer. Index of the minimum value in extents at which the data in testmat
is above the asymptote. The residual sum of squares is printed in the console and
the index corresponding to the best nls fit is returned.
This function is internally used by function mopaTrain, to fit AUC
scores to the background extents at which were obtained (see reference below).
Iturbide, M., Bedia, J., Herrera, S., del Hierro, O., Pinto, M., Gutierrez, J.M., 2015. A framework for species distribution modelling with improved pseudo-absence generation. Ecological Modelling. DOI:10.1016/j.ecolmodel.2015.05.018.