summariseChains: Summarise the output of the BMEA MCMC process
In steveped/BMEA: Bayesian Modelling for Exon Arrays

Description Usage Arguments Details Value References

Takes the kept simulations from a BMEA MCMC process and provides the summary statistics.

1	summariseChains(data, transform = TRUE)

`data`	an object of class BMEA.MCMC
`transform`	logical. If `transform = TRUE`, the S & phi simulations will be transformed to the log & logit scales respectively when calculating the convergence statistics.

Provides summary statistics, quantiles & convergence statistics for a BMEA.MCMC object.

To approximate normality, sigma_mu, sigma_p & sigma_S are log transformed when calculating rHat. If transform = TRUE, all S simulations are log transformed & phi simulations are logit transformed. If the mixture prior for phi has been used, this should be set to FALSE as values of zero or one will be possible & will not be suitable for transformation.

A matrix with columns containing the mean, sd, quantiles (0.025, 0.25, 0.50, 0.75, 0.975), rHat & nEff for each BMEA model parameter.

Brooks, S.P. and Gelman, A. (1998) General Methods for Monitoring Convergence of Iterative Simulations Journal of Computational and Graphical Statistics, Vol. 7, No. 4 (Dec), pp. 434-455

steveped/BMEA documentation built on May 30, 2019, 5:38 p.m.