View source: R/vc_score_perm.R
vc_score_perm | R Documentation |
This function computes an approximation of the Variance Component test for a
mixture of χ^{2}s using Davies method from davies
vc_score_perm( y, x, indiv, phi, w, Sigma_xi = diag(ncol(phi)), na_rm = FALSE, n_perm = 1000, progressbar = TRUE, parallel_comp = TRUE, nb_cores = parallel::detectCores() - 1 )
y |
a numeric matrix of dim |
x |
a numeric design matrix of dim |
indiv |
a vector of length |
phi |
a numeric design matrix of size |
w |
a vector of length |
Sigma_xi |
a matrix of size |
na_rm |
logical: should missing values (including |
n_perm |
the number of permutation to perform. Default is |
progressbar |
logical indicating whether a progress bar should be displayed when computing permutations (only in interactive mode). |
parallel_comp |
a logical flag indicating whether parallel computation
should be enabled. Only Linux and MacOS are supported, this is ignored on Windows.
Default is |
nb_cores |
an integer indicating the number of cores to be used when
|
A list with the following elements:
score
: an approximation of the observed set score
scores_perm
: a vector containing the permuted set scores
gene_scores_unscaled
: approximation of the individual gene scores
gene_scores_unscaled_perm
: a list of approximation of the permuted individual gene scores
davies
#rm(list=ls()) set.seed(123) ##generate some fake data ######################## n <- 100 r <- 12 t <- matrix(rep(1:3), r/3, ncol=1, nrow=r) sigma <- 0.4 b0 <- 1 #under the null: b1 <- 0 #under the alternative: b1 <- 0.7 y.tilde <- b0 + b1*t + rnorm(r, sd = sigma) y <- t(matrix(rnorm(n*r, sd = sqrt(sigma*abs(y.tilde))), ncol=n, nrow=r) + matrix(rep(y.tilde, n), ncol=n, nrow=r)) x <- matrix(1, ncol=1, nrow=r) #run test scoreTest <- vc_score_perm(y, x, phi=t, w=matrix(1, ncol=ncol(y), nrow=nrow(y)), Sigma_xi=matrix(1), indiv=rep(1:(r/3), each=3), parallel_comp = FALSE) scoreTest$score
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.