symm_fit_ind_EM_noAssumption: symm_fit_ind_noAssumption.R

In csmGmm: Conditionally Symmetric Multidimensional Gaussian Mixture Model

symm_fit_ind_noAssumption.R

Description

Fit the conditionally symmetric multidimensional Gaussian mixture model for sets of independent elements, but we don't assume that the means in the composite alternative are greater in magnitude than those in the composite null.

Usage

symm_fit_ind_EM_noAssumption(
  testStats,
  initMuList,
  initPiList,
  sameDirAlt = FALSE,
  eps = 10^(-5),
  checkpoint = TRUE
)

Arguments

testStats	J*K matrix of test statistics where J is the number of sets and K is number of elements in each set.
initMuList	List of 2^K elements where each element is a matrix with K rows and number of columns equal to the number of possible mean vectors for that binary representation.
initPiList	List of 2^K elements where each element is a vector with number of elements equal to the number of possible mean vectors for that binary representation.
sameDirAlt	Boolean, set to TRUE for replication testing, which uses a smaller alternative space.
eps	Scalar, stop the EM algorithm when L2 norm of difference in parameters is less than this value.
checkpoint	Boolean, set to TRUE to print iterations of EM

Value

A list with the elements:

muInfo	List with same dimensions as initMuList, holds the final mean parameters.
piInfo	List with same dimensions as initPiList, holds the final mixture proportions
iter	Number of iterations run in EM algorithm.
lfdrResults	J*1 vector of all lfdr statistics.

Examples

set.seed(0)
testStats <- cbind(rnorm(10^4), rnorm(10^4))
testStats[1:200, 1] <- rnorm(100, mean=3)
testStats[201:400, 1] <- rnorm(100, mean=5)
testStats[401:600, 2] <- rnorm(100, mean=3)
testStats[601:800, 2] <- rnorm(100, mean=5)
testStats[801:1000, 1:2] <- rnorm(200, mean=7)
initMuList <- list(matrix(data=0, nrow=2, ncol=1), matrix(data=c(0, 3, 0, 5), nrow=2, ncol=2),
matrix(data=c(3, 0, 5, 0), nrow=2, ncol=2), matrix(data=c(7, 7), nrow=2, ncol=1))
initPiList <- list(c(0.9), c(0.02, 0.02),c(0.02, 0.02), c(0.02))
results <- symm_fit_ind_EM_noAssumption(testStats = testStats,
initMuList = initMuList, initPiList = initPiList)

csmGmm documentation built on April 4, 2025, 2:02 a.m.