plot.maxnet {maxnet}

Response plots for maxnet models

Description

Create response plots for each predictor in a maxnet model

Usage

## S3 method for class 'maxnet'
plot(x, vars = names(x$samplemeans), common.scale = T, 
   type = c("link", "exponential", "cloglog", "logistic"), ylab = NULL, ...)

response.plot(mod, v, type, mm=mod$samplemeans, min=mod$varmin[v], max=mod$varmax[v], 
   levels=unlist(mod$levels[v]), plot=T, xlab=v, ylab=tools::toTitleCase(type), ...)

Arguments

x

an object of class maxnet, i.e., a fitted model.

vars

vector of predictors for which response plots are desired.

common.scale

if true, all plots use the same scale on the y-axis.

type

type of response to plot on y-axis.

xlab

label for x-axis.

ylab

label for y-axis.

mod

a fitted model, must be of type maxnet if default values used for other arguments.

v

name of variable to be plotted.

mm

sample means (or majorities for factors) for predictors; predictors other than v are given these values.

min

minimum value of v; determines range of x-axis

max

maximum value of v; determines range of x-axis

levels

if v is a factor, determines levels to be plotted

plot

if false, don't draw the plot

...

passed to plot or barplot

Value

If plot is false, return a vector of y values, one for each factor or 100 ranging from min - 0.1*(max-min) to max + 0.1*(max-min).

Author(s)

Steven Phillips