init.fit: Method to initialize EM parameters. Carries out a single GLM...

In emax.glm: General Tools for Building GLM Expectation-Maximization Models

Description

Method to initialize EM parameters. Carries out a single GLM fit and applies random noise to form starting space.

Usage

init.fit(y, x, K, weight = c(1), family = poisson(), noise = 1)

Arguments

y	A vector of observation of length n.
x	An n-by-p design matrix.
K	Number of EM classes to be fit.
weight	A n length vector of observation weight terms. This is currently designed to be either the exposure for a Poisson model or the number of trials for a Logistic model.
family	GLM family to fit.
noise	Standard deviation of the white noise to be applied when generating random initial states.

Value

A K-length list, each holding parameters.

Examples

x <- model.matrix(~ 1 + factor(wool) + factor(tension), data = warpbreaks)
y <- warpbreaks$breaks

init.fit(y = y, x = x, K = 2)

emax.glm documentation built on July 4, 2019, 5:04 p.m.