Nmix (version 2.0.5)

Nmix-package: tools:::Rd_package_title("Nmix")

Description

A program for Bayesian analysis of univariate normal mixtures, implementing the approach of Richardson and Green (1997) <doi:10.1111/1467-9868.00095>

Author

Maintainer: tools:::Rd_package_maintainer("Nmix")

Details

A program for Bayesian analysis of univariate normal mixtures with an unknown number of components, implementing the approach of Richardson and Green, Journal of the Royal Statistical Society, B, 59, 731-792 (1997); see also the correction in J. R. Statist. Soc. B, 1998, 60, 661). Computation is by reversible jump Markov chain Monte Carlo; this package is essentially an R interface to the Fortran program originally written in 1996 for the MCMC sampling, together with some facilities for displaying and summarising the resulting posterior distribution, and reporting the sampler performance.

References

Richardson and Green (1997) <doi:10.1111/1467-9868.00095> (J. R. Statist. Soc. B, 59, 731-792; see also the correction in <doi:10.1111/1467-9868.00146>, J. R. Statist. Soc. B, 1998, 60, 661).

The author is grateful to Peter Soerensen for providing the interface to the C i/o routines used here.

Examples

data(galx)
z<-Nmix('galx',nsweep=10000,nburnin=1000)
print(z)
summary(z)