dsm (version 2.2.17)

vis.concurvity: Visualise concurvity between terms in a GAM

Description

Plot measures of how much one term in the model could be explained by another. When values are high, one should consider re-running variable selection with one of the offending variables removed to check for stability in term selection.

Usage

vis.concurvity(model, type = "estimate")

Arguments

model

fitted model

type

concurvity measure to plot, see concurvity

Details

These methods are considered somewhat experimental at this time. Consult concurvity for more information on how concurvity measures are calculated.

Examples

# NOT RUN {
library(Distance)
library(dsm)

# load the Gulf of Mexico dolphin data (see ?mexdolphins)
data(mexdolphins)

# fit a detection function and look at the summary
hr.model <- ds(distdata, max(distdata$distance),
               key = "hr", adjustment = NULL)

# fit a simple smooth of x and y to counts
mod1 <- dsm(count~s(x,y)+s(depth), hr.model, segdata, obsdata)

# visualise concurvity using the "estimate" metric
vis.concurvity(mod1)
# }