modEvA (version 2.0)

getModEqn: Get model equation

Description

This function retrieves the equation of a model, to print or apply elsewhere.

Usage

getModEqn(model, type = "Y", digits = NULL, prefix = NULL, 
suffix = NULL)

Arguments

model

a model object of class 'lm' or glm'.

type

the type of equation to get; can be either "Y" (the default, for the linear model equation), "P" (for probabiity) or "F" (for favourability).

digits

the number of digits to which to round the coefficient estimates in the equation.

prefix

the prefix to add to each variable name in the equation.

suffix

the suffix to add to each variable name in the equation.

Value

A charachter string of model the equation.

Details

The summary of a model in R gives you a table of the coefficient estimates and other parameters. Sometimes it may be useful to have a string of text with the model's equation, so that you can present it in an article (e.g. Real et al. 2005) or apply it in a (raster map) calculation, either in R (although here you can usually use the 'predict' function for this) or in a GIS software (e.g. Barbosa et al. 2010). The getModEqn function gets this equation for linear or generalized linear models.

By default it prints the "Y" linear equation, but for generalized linear models you can also set type = "P" (for the equation of probability) or type = "F" (for favourability, which corrects the intercept to eliminate the effect of prevalence - see Real et al. 2006).

If the variables to which you want to apply the model have a prefix or suffix (e.g. prefix = "raster.stack$" for the R raster package, or prefix = "mydata$" for a data frame, or suffix = "@1" in Quantum GIS, or suffix = "@mapset" in GRASS), you can get these in the equation too, using the prefix and/or the suffix argument.

References

Barbosa A.M., Real R. & Vargas J.M. (2010) Use of coarse-resolution models of species' distributions to guide local conservation inferences. Conservation Biology 24: 1378-87

Real R., Barbosa A.M., Martinez-Solano I. & Garcia-Paris, M. (2005) Distinguishing the distributions of two cryptic frogs (Anura: Discoglossidae) using molecular data and environmental modeling. Canadian Journal of Zoology 83: 536-545

Real R., Barbosa A.M. & Vargas J.M. (2006) Obtaining environmental favourability functions from logistic regression. Environmental and Ecological Statistics 13: 237-245

Examples

# NOT RUN {
# load sample models:
data(rotif.mods)

# choose a particular model to play with:
mod <- rotif.mods$models[[1]]

getModEqn(mod)

getModEqn(mod, type = "P", digits = 3, suffix = "@mapset")

getModEqn(mod, type = "F", digits = 2)
# }