small.em: Carry out several short EM fits to test for optimal starting...

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

Description

Carry out several short EM fits to test for optimal starting locations.

Usage

small.em(x, y, b.init = "fit", weight = c(1), K = 2, maxiter = 5,
  tol.1 = 1e-04, tol.2 = 1e-04, noise = 0.2, sample.size = 500,
  repeats = 5, debug = FALSE, family = "poisson",
  method = "numeric", maxiter.NR = 20)

Arguments

x	An n-by-p design matrix.
y	A vector of observation of length n.
b.init	The method to initialize EM parameters. Built in methods are "random" and "fit" for pure white noise, and white noise around GLM estimates. Alternatively, pass a list of length K, each element consisting of a vector of length p. Users can also pass a zero-argument function to produce starting states.
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.
K	Number of EM classes to be fit.
maxiter	Maximum number of re-weighting rounds to do in fitting the EM model. Primarily used to perform the 'small.em' warm-up routine.
tol.1	Escape tolerance of the Newton-Raphson step.
tol.2	Escape tolerance of the re-weighting step.
noise	Standard deviation of the white noise to be applied when generating random initial states.
sample.size	Number of cases to randomly select from the input data.
repeats	Number of repetitions of the initialization to make.
debug	Returns step-size in NR and re-weighting steps as a message if TRUE.
family	GLM family to fit.
method	Control string. Set to 'numeric' or 'pracma'.
maxiter.NR	Maximum number of Newton-Raphson steps to take.

Value

A 'small.em' list containing the parameters, weights, log likelihood and BIC values.

Examples

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

warm_up <- small.em(x = x, y = y, K = 2, b.init = "random", sample.size = 50)
summary(warm_up)

params <- select_best(warm_up)

m <- em.glm(x = x, y = y, K = 2, b.init = params)
summary(m)

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