MixtureInf (version 1.1)

pmle.pois: compute the PMLE or MLE of the parameters under a mixture of Possions

Description

Compute the PMLE or MLE of the parameters under a mixture of Possions. When the level of penalty is 0, PMLE reduces to MLE.

Usage

pmle.pois(x, m0 = 1, lambda = 0, 
	  inival = NULL, len = 10, niter = 50, tol = 1e-06, rformat = FALSE)

Arguments

x

data, can be either a vector or a matrix with the 1st column being the observed values and the 2nd column being the corresponding frequencies.

m0

order of the finite mixture model, default value: m0 = 1.

lambda

level of penalty, default value: lambda = 0.

inival

initial values for the EM-algorithm, a 2m0-dimension vector including m0 mixing proportions and m0 component parameters, or a matrix with 2m0 columns, default value: inival = NULL. (if not provided, random initial values are used.)

len

number of random initial values for the EM-algorithm, default value: len = 10.

niter

number of iterations for all initial values in the EM-algorithm. The algorithm runs EM-iteration niter times from each initial value. The iteration will restart from the parameter value with the highest likelihood value at the point and run until convergence. default value: niter = 50.

tol

tolerance level for the convergence of the EM-algorithm, default value: tol = 1e-6.

rformat

form of the digital output: default of R package is used when rformat = T; If rformat = T, the digital output is rounded to the 3rd dicimal place if it is larger than 0.001, keeps 3 significant digits otherwise. The default value of rformat is F.

Value

Return the PMLE or MLE of the parameters with order = m0 (mixing proportions and component parameters), log-likelihood value at the PMLE or MLE and the penalized log-likelihood value at the PMLE.

See Also

emtest.pois, pmle.pois, rmix.pois

Examples

#generate a random sample from a 2 component Poisson mixture,
#compute the PMLE of the parameters under the 2 component Poisson mixture model,
#plot the histgoram of the observations and the fitted probability mass function.
x <- rmix.pois(200,c(0.3,0.7),c(2,5))
out <- pmle.pois(x,2)
plotmix.pois(x,out)