diagnosticsJagsMix function

MCMC diagnostics for polyploid segregation ratio mixture models

Produce and/or plot various diagnostic measures from coda

package for Bayesian mixture models for assessing marker dosage in autopolyploids

diagnosticsJagsMix(mcmc.mixture, diagnostics = TRUE, plots = FALSE,
 index = -c( grep("T\\[",varnames(mcmc.mixture$mcmc.list)),
             grep("b\\[",varnames(mcmc.mixture$mcmc.list)) ),
 trace.plots = FALSE, auto.corrs = FALSE, density.plots = FALSE,
 xy.plots = FALSE, hpd.intervals = FALSE, hdp.prob = 0.95,
 return.results = FALSE)

Arguments

• mcmc.mixture: Object of class segratioMCMC or runJagsWrapper after JAGS run produced by coda
• diagnostics: if TRUE then print several coda dignostic tests
• plots: if TRUE then produce several coda dignostic plots
• index: index of parameters for disgnostic tests/plots (Default: mixture model (and random effects) parameters)
• trace.plots: if TRUE plot mcmc traces (default: FALSE)
• auto.corrs: if TRUE produce autocorrelations of mcmc's (default: FALSE)
• density.plots: if TRUE plot parameter densities (default: FALSE)
• xy.plots: if TRUE plot traces using 'lattice' (default: FALSE)
• hpd.intervals: if TRUE print and return highest posterior density intervals for parameters specified by index
• hdp.prob: probability for hpd.intervals
• return.results: if TRUE return results as list

Returns

If return.results is TRUE then a list is returned with components depending on various settings of arguments

Author(s)

Peter Baker p.baker1@uq.edu.au

See Also

mcmc autocorr.diag

raftery.diag geweke.diag

gelman.diag trellisplots

Examples

## simulate small autooctaploid data set
a1 <- sim.autoMarkers(8,c(0.7,0.2,0.1),n.markers=100,n.individuals=50)
##print(a1)
sr <-  segregationRatios(a1$markers)
x <- setModel(3,8)

## Not run:

## fit simple model in one hit

x.run <- runSegratioMM(sr, x, burn.in=200, sample=500)
print(x.run)
diagnosticsJagsMix(x.run)
diagnosticsJagsMix(x.run, plot=TRUE)
## End(Not run)