splitEM_GLM {multinomialLogitMix}

Split-small EM scheme.

Description

Split two randomly selected clusters based on a model with one component smaller than the current one. This procedure is repeated within a small-EM scheme. The best split is chose to initialize the model.

Usage

splitEM_GLM(y, x, K, smallerModel, tsplit = 10, maxIter = 20, 
	emthreshold = 1e-08, maxNR = 5, nCores, 
	split = TRUE, R0, method)

Arguments

y

y

x

x

K

k

smallerModel

smla

tsplit

tsp

maxIter

max

emthreshold

thr

maxNR

maxn

nCores

nc

split

spi

R0

ro

method

meth

Value

val

Author(s)

Panagiotis Papastamoulis

References

Papastamoulis, P., Martin-Magniette, M. L., and Maugis-Rabusseau, C. (2016). On the estimation of mixtures of Poisson regression models with large number of components. Computational Statistics & Data Analysis, 93, 97-106.