Metropolis: generate Markov chains for specific distribution based on...

In Scopia/StatComp18053: generating and monitoring convergence of Markov chain and permutation test for equal distribution

Description

This function generates a Markov chain using a random walk Metropolis-Hastings algorithm.The user supplies target distribution, burn-in time, the length of the chain and the variance of proposal distribution. And a Markov chain after discarding burn-in samples is returned, which can be used for monitoring convengence.

Usage

Metropolis(burn_in=1000,dist=dcauchy,sigma,N=10000,print_acc=F)

Arguments

burn_in	the total length of discarding
dist	the target distribution
sigma	the variance of the normal proposal distribution
N	the length of Markov chain
print_acc	if print acceptance rate or not

Details

Metropolis generates a Markov chain using a Metropolis-Hastings algorithm. The aim is to generate random numbers from specific distribution based on Normal proposal distribution

References

Statistic computing with R. Maria L. Rizzo

Examples

## Not run: 
y=Metropolis(sigma=2,print_acc=T)
plot(density(Metropolis(sigma = 3,print_acc = T)))

## End(Not run)

Scopia/StatComp18053 documentation built on May 22, 2019, 2:44 p.m.