optimize_pi: Estimate mixture weights by maximum (penalized) likelihood

Description Usage Arguments Value

View source: R/opt.R

Description

This is an internal (non-exported) function. This help page provides additional documentation mainly intended for developers and expert users.

Usage

1
2
3
4
5
6
7
optimize_pi(
  matrix_lik,
  pi_init = NULL,
  prior = NULL,
  optmethod = c("mixSQP", "mixIP", "mixEM", "cxxMixSquarem"),
  control = list()
)

Arguments

matrix_lik

a matrix of likelihoods, where the (i,k)th entry is the probability of observation i given it came from component k of g

pi_init

numeric vector specifying value from which to initialize optimization

prior

numeric vector specifying prior to use in the penalized likelihood

optmethod

a string, giving name of optimization function to use

control

a list of parameters to be passed to optmethod

Value

numeric vector specifying the optimal mixture weights


mashr documentation built on May 24, 2021, 1:06 a.m.