Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!
Get Started for Free

calibrate

Calculate fitted environmental attributes in an ordination


Description

Fits a Generalized Additive Model (GAM) for each environmental variable in a data.frame against an ordination.

Usage

## S3 method for class 'dsvord'
calibrate(dsvord,site,dims=1:ncol(dsvord$points),
           family='gaussian',gamma=1,keep.models=FALSE)

Arguments

dsvord

an ordination object of class dsvord

site

a matrix or data.frame with sample units as rows and environmental variables as columns

dims

the specific dimensions of the ordination to consider

family

the error distribution specifier for the GAM function

gamma

the gamma parameter to control fitting GAM models

keep.models

a switch to control saving the individual GAM models

Details

The calibrate function sequentially and independently fits a GAM model for each environmental variable as a function of ordination coordinates, using the family and gamma specifiers supplied in the function call, or their defaults. The model fits two or three dimensional models; if the length of dims is greater than three the dimensions are truncated to the first three chosen.

Value

A list object with vector elements aic, dev.expl, adj.rsq, and fitted value matrix. Optionally, if keep.models is TRUE, a list with all of the GAM models fitted. List element aic gives the model AICs for each variable, dev.expl gives the deviance explained, adj.rsq gives the adjusted r-Squared, and fitted gives the expected value of each variable in each sample unit.

Author(s)

See Also

predict for the complementary function that fits GAM models for species

Examples

data(bryceveg)
dis.man <- dist(bryceveg,method="manhattan")
demo.nmds <- nmds(dis.man,k=4)
## Not run: res <- calibrate(demo.nmds,brycesite[,c(2,4,7,12)],minocc=10)

labdsv

Ordination and Multivariate Analysis for Ecology

v2.0-1
GPL (>= 2)
Authors
David W. Roberts <droberts@montana.edu>
Initial release

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.