boolean3 (version 3.1.6)

boolprof: Calculate estimated likelihood-profiles.

Description

This function calculates log-likelihood profiles for the selected variables. Despite the function name, these are not true profile likelihoods as they hold all other coefficients fixed at their MLE.

Usage

boolprof(obj, method = names(obj$model.fit)[1], vars = 1:obj$k, k = 50, as.table = TRUE, scales = list(x = list(relation = "free")), between = list(x = 1, y = 1), main = "Estimated likelihood profiles", xlab = "beta", ylab = "Log-likelihood", ...)

Arguments

obj

object of boolean-class containing a fit boolean model.

method

estimation method to use

vars

numeric vector selecting a set of covariates from the fitted model

k

integer indicating the number of points at which the log-likelihood should be calculated.

as.table

logical (default TRUE), to be passed to xyplot.

scales

list of settings for the scales argument passed to xyplot.

between

numeric specifying the space between panels.

main

string, plot title

xlab

string, the x-axis label.

ylab

string, the y-axis label.

...

Additional arguments to pass to xyplot. See that cumentation for details.

Value

Returns an object of boolprof-class, the default action being to present the default plot.

Examples

## Not run: 
# 
# ## Note: This example assumes a boolean model has already been fit.
# 
# ## Display the contours of the likelihood given a change the value of
# ## the coefficients.
# (prof <- boolprof(fit))
# 
# ## Extract the plots for x1_a and x4_b.
# plot(prof, y = c("x1_a", "x4_b"))
# plot(prof, y = c(1, 3), scales = list(y = list(relation = "free")))
# 
# ## You can also use variable or index matching with boolprof to select
# ## particular covariates of interest.
# boolprof(fit, vars = c(1, 3))
# boolprof(fit, vars = c("x1_a", "x4_b"))
# ## End(Not run)