bmksensitive {bmk}R Documentation

Hellinger distance between two MCMC chains for sensitivity studies

Description

Determine if two identically dimensioned sets of chains match. This is good for conducting sensitivity studies.

Usage

  bmksensitive(inputlist1, inputlist2)

Arguments

inputlist1

A list of the combined MCMC chains for all samples from one scenario.

inputlist2

A list of the combined MCMC chains for all samples from another scenario.

References

Boone EL, Merrick JR and Krachey MJ. A Hellinger distance approach to MCMC diagnostics. Journal of Statistical Computation and Simulation, DOI:10.1080/00949655.2012.729588.

Examples

data(MCMCsamples)
 bmksensitive(MCMC.one.mean0, MCMC.one.mean1)
 ## Not run: 
 library(dismo); library(MCMCpack)
 data(Anguilla_train)
 b0mean0 <- 0
 b0mean1 <- 1
 b0precision <- (1/5)^2
 mcmclen = 1000
 burn=10000
 MCMC.one.mean0 <- MCMClogit(Angaus ~ SegSumT+DSDist+USNative+as.factor(Method)+DSMaxSlope+USSlope,
                  data=Anguilla_train,burnin=burn, mcmc=mcmclen, beta.start=-1,
                  b0=b0mean0, B0=b0precision)
 MCMC.one.mean1 <- MCMClogit(Angaus ~ SegSumT+DSDist+USNative+as.factor(Method)+DSMaxSlope+USSlope,
                  data=Anguilla_train,burnin=burn, mcmc=mcmclen, beta.start=-.5,
                  b0=b0mean1, B0=b0precision)
 bmksensitive(one, two)
 
## End(Not run)

[Package bmk version 1.0 Index]