rmunorm
(Package: mcsm) :
Random generator for the multivariate normal distribution
This function produces one random vector distributed from the multivariate normal distribution N(mu,sig).
● Data Source:
CranContrib
● Keywords: distribution
● Alias: rmunorm
●
0 images

pimamh
(Package: mcsm) :
Langevin MCMC algorithm for the probit posterior
This function implements a Langevin version of the MetropolisHastings algorithm on the posterior of a probit model, applied to the Pima.tr dataset.
● Data Source:
CranContrib
● Keywords: datagen, hplot, optimize
● Alias: pimamh
●
0 images

mhmix
(Package: mcsm) :
Implement two MetropolisHastings algorithms on a mixture posterior
This function runs a MetropolisHastings algorithm on a posterior distribution associated with a mixture model and 500 datapoints. Depending on the value of the boolean indicator lange , the function uses a regular Gaussian randomwalk proposal or a Langevin alternative.
● Data Source:
CranContrib
● Keywords: datagen, hplot
● Alias: mhmix
●
0 images

dyadic
(Package: mcsm) :
A dyadic antithetic improvement for a toy problem
Using dyadic replicas of a uniform sample, when evaluating the mean of h(x)=(cos(50*x) +sin(20*x))^2, this function shows the corresponding improvement in variance. The parameter q is used to break the unit interval into 2^q blocks where a transform of the original uniform sample is duplicated.
● Data Source:
CranContrib
● Keywords: distribution
● Alias: dyadic
●
0 images

test2
(Package: mcsm) :
Generic chisquare generator
This function is a frontend for rchisq , designed for comparison with test1 .
● Data Source:
CranContrib
● Keywords: datagen, distribution
● Alias: test2
●
0 images

sqar
(Package: mcsm) :
Illustration of some of coda's criterions on the noisy squared AR model
This function illustrates some of coda 's criterions on the noisy squared AR model, using a MetropolisHastings algorithm based on a random walk. Depending on the value of the boolean multies , those criterions are either the geweke.diag and heidel.diag diagnostics, along with a KolmogorovSmirnov test of our own, or plot(mcmc.list()) if several parallel chains are produced together.
● Data Source:
CranContrib
● Keywords: hplot
● Alias: sqar
●
0 images

betagen
(Package: mcsm) :
Plot explaining acceptreject on a Beta(2.7,6.3) target
This function of Nsim represents Nsim points simulated from either a uniform or a Beta(2,6) proposal in terms of their location above versus below the density of the Beta(2.7,6.3) target in order to explain acceptreject methods.
● Data Source:
CranContrib
● Keywords: datagen, distribution, hplot
● Alias: betagen, rbeta
●
0 images

normbyde
(Package: mcsm) :
Compare two doubleexponentials approximations to a normal distribution
This simple program compares a doubleexponential distribution with parameter a=1 and a doubleexponential distribution with parameter a!=1 in their approximation to the standard normal distribution. Quite obviously, this function is not to be used when compared when rnorm .
● Data Source:
CranContrib
● Keywords: distribution
● Alias: normbyde
●
0 images

maximple
(Package: mcsm) :
Graphical representation of a toy example of simulated annealing
For the toy function h(x)=(cos(50*x)+sin(20*x))^2, this function represents simulated annealing sequences converging to a local or global maxima as paths on top of the function h itself. The simulated annealing parameters ratemp and powemp can be changed, as well as the stopping rule tolerance.
● Data Source:
CranContrib
● Keywords: optimize
● Alias: maximple
●
0 images

sqaradap
(Package: mcsm) :
Illustration of the dangers of doing adaptive MCMC on a noisy squared AR model
This function constructs a nonparametric proposal after each iteration of the MCMC algorithm, based on the earlier simulations. It shows how poorly this "natural" solution fares.
● Data Source:
CranContrib
● Keywords: hplot
● Alias: sqaradap
●
0 images
