LLsurface {secr}

R Documentation

Plot Likelihood Surface

Description

LLsurface is a generic function to calculate log likelihood over a grid of values of two coefficients (beta parameters) from a fitted model and optionally make an approximate contour plot of the log likelihood surface.

A method is provided for secr objects.

Usage

LLsurface(object, ...)

## S3 method for class 'secr'
LLsurface(object, betapar = c("g0", "sigma"), xval = NULL,
    yval = NULL, centre = NULL, realscale = TRUE, plot = TRUE,
    plotfitted = TRUE, ncores = NULL, ...)

Arguments

object	fitted model, secr object output from secr.fit
betapar	character vector giving the names of two beta parameters
xval	vector of numeric values for x-dimension of grid
yval	vector of numeric values for y-dimension of grid
centre	vector of central values for all beta parameters
realscale	logical. If TRUE input and output of x and y is on the untransformed (inverse-link) scale.
plot	logical. If TRUE a contour plot is produced
plotfitted	logical. If TRUE the MLE from object is shown on the plot (+)
ncores	integer number of threads for parallel processing
...	other arguments passed to contour

Details

centre is set by default to the fitted values of the beta parameters in object. This has the effect of holding parameters other than those in betapar at their fitted values.

If xval or yval is not provided then 11 values are set at equal spacing between 0.8 and 1.2 times the values in centre (on the ‘real’ scale if realscale = TRUE and on the ‘beta’ scale otherwise).

Contour plots may be customized by passing graphical parameters through the ... argument.

Setting ncores = NULL uses the existing value from the environment variable RCPP_PARALLEL_NUM_THREADS (see setNumThreads).

Value

A matrix of the log likelihood evaluated at each grid point (rows x, columns y), invisibly if plot = TRUE. Failed evaluations return NA.

Note

LLsurface works for named ‘beta’ parameters rather than ‘real’ parameters. The default realscale = TRUE only works for beta parameters that share the name of the real parameter to which they relate i.e. the beta parameter for the base level of the real parameter. This is because link functions are defined for real parameters not beta parameters.

The contours are approximate because they rely on interpolation. See Examples for a more reliable way to compare the likelihood at the MLE with nearby points on the surface.

Examples

## Not run: 

LLsurface(secrdemo.CL, xval = seq(0.16,0.40,0.02),
    yval = 25:35, nlevels = 20)

## now verify MLE
## click on MLE and apparent `peak'
if (interactive()) {
    xy <- locator(2)
    LLsurface(secrdemo.CL, xval = xy$x, yval = xy$y, plot = FALSE)
}


## End(Not run)

---