logMargDenNR {bayesm}R Documentation

Compute Log Marginal Density Using Newton-Raftery Approx

Description

logMargDenNR computes log marginal density using the Newton-Raftery approximation.
Note: this approximation can be influenced by outliers in the vector of log-likelihoods. Use with care .

Usage

logMargDenNR(ll)

Arguments

ll vector of log-likelihoods evaluated at length(ll) MCMC draws

Value

approximation to log marginal density value.

Warning

This routine is a utility routine that does not check the input arguments for proper dimensions and type.

Author(s)

Peter Rossi, Graduate School of Business, University of Chicago, Peter.Rossi@ChicagoGsb.edu.

References

For further discussion, see Bayesian Statistics and Marketing by Allenby, McCulloch, and Rossi, Chapter 6.
http://gsbwww.uchicago.edu/fac/peter.rossi/research/bsm.html


[Package bayesm version 1.1-1 Index]