Loglikeli: Log likelihood

In baccione-eawag/EawagSchoolTools: Miscellaneous Tools for Eawag Summer School in Environmental Systems Analysis

Description

Function implementing a simple standard log likelihood function for a model provided by a deterministic function. This function provides the density of a multivariate normal distribution centered at the results of the deterministic model.

This likelihood implementation serves as a template for implementing more specific likelihood functions. It is called by the function Logposterior.

Usage

Loglikeli(par,model,L,y,error.sd=NA,error.cor.inv=NA,...)

Arguments

par	parameters
model	model function
L	observation layout
y	data
error.sd	used for variance-covariance structure
error.cor.inv	used for variance-covariance structure
...	additional arguments passed to model

Details

If there exists a component of the parameter vector labeled sd_rel instead of the provided standard deviations, error.sd, the standard deviations error.sd * par["sd_rel"] are used. This makes it possible to estimate a common factor of a given variance-covariance structure.

Value

Returns log likelihood.

Author(s)

Peter Reichert <[e-mail]>

See Also

Logposterior

baccione-eawag/EawagSchoolTools documentation built on Dec. 19, 2021, 6:38 a.m.