R Graphical Manual

Browse All

Last data update: 2014.03.03

R: Compute the log likelihood of input data given a parameter...

mix.loglik

R Documentation

Compute the log likelihood of input data given a parameter vector and a list of 2 distribution functions.

Description

This is the main function to compute the negative 2 x log likelihood function of parameters given data.

This function is not intended to be called directly by users, but can be useful to test user-specified mixture distributions passed to mix.mle.

Usage

mix.loglik(.pars, .input, .distlist, do.sum = TRUE)

Arguments

`.pars`	A list of the following 5 parameters: mix.prob Probability of second distribution dist1.par1 Lower distribution: mean for normal, shape for gamma dist1.par2 Lower distribution: SD for normal, scale for gamma dist2.par1 Upper distribution: mean for normal, shape for gamma dist2.par2 Upper distribution: SD for normal, scale for gamma
`.input`	Vector of (numeric) trait observations.
`.distlist`	List of 2 distribution density functions. The first is the lower or leftmost distribution; the second is the upper or rightmost.
`do.sum`	By default, return sum of likelihoods. Set to `FALSE` for testing.

Details

Computes maximum likelihood function for either the normal mixture distribution or the facing gamma distribution model for a dimorphic trait.

Value

Numeric: the negative 2 x log likelihood of trait measurement.

References

Rowland JM, Qualls CR. 2005. Likelihood models for discriminating alternative phenotypes in morphologically dimorphic species.
Evolutionary Ecology Research 7: 421-434.