postsamples.Rdpostsamples generates samples from the posterior distribution of a 2D GLM coefficient map (e.g., corresponding to a single brain slice) of a regressor in the BHMSMA model for each subject based on multi-subject or single subject analyses (see References).
postsamples(nsample, n, grid, glmcoefstd, waveletcoefmat,
hyperparam, pkljbar, analysis, wave.family="DaubLeAsymm",
filter.number=6, bc="periodic", seed)Number of samples to be generated.
Number of subjects.
The number of voxels in one row (or, one column) of the brain slice of interest. Must be a power of 2. The total number of voxels is grid^2. The maximum value of grid for this package is 512.
An array of dimension (n,grid,grid), containing for each subject the standardized GLM coefficients obtained by fitting GLM to the time-series corresponding to the voxels.
A matrix of dimension (n,grid^2-1), containing for each subject the wavelet coefficients of all levels stacked together (by the increasing order of resolution level).
A vector containing the estimates of the six hyperparameters.
A matrix of dimension (n,grid^2-1), containing the piklj bar values (see References for details).
"MSA" or "SSA", depending on whether performing multi-subject analysis or single subject analysis.
The family of wavelets to use - "DaubExPhase" or "DaubLeAsymm". Default is "DaubLeAsymm".
The number of vanishing moments of the wavelet. Default is 6.
The boundary condition to use - "periodic" or "symmetric". Default is "periodic".
Must be a positive integer. Provide to set random number generation seed for reproducibility.
A list containing the following.
An array of dimension (n,grid,grid,nsample), containing for each subject the posterior samples of the GLM coefficients.
An array of dimension (n,grid,grid), containing for each subject the posterior discovery maps of the GLM coefficients (for details see Morris et al. (2011)).
The wavelet computations are performed by using the R package wavethresh.
Sanyal, Nilotpal, and Ferreira, Marco A.R. (2012). Bayesian hierarchical multi-subject multiscale analysis of functional MRI data. Neuroimage, 63, 3, 1519-1531.
Morris, J.S. et al. (2011). Automated analysis of quantitative image data using isomorphic functional mixed models, with application to proteomic data. Ann. Appl. Stat. 5, 894-923.
set.seed(1)
n <- 3
grid <- 8
nsample <- 5
glmcoefstd <- array(rnorm(n*grid*grid),
dim=c(n,grid,grid))
waveletcoefmat <- array(rnorm(n*(grid^2-1)),
dim=c(n,(grid^2-1)))
hyperparam <- rep(.2,6)
pkljbar <- array(runif(n*(grid^2-1)),
dim=c(n,(grid^2-1)))
analysis <- "multi"
postsample <- postsamples(nsample,n,grid,glmcoefstd,
waveletcoefmat, hyperparam,pkljbar,analysis,seed=1)
#> Error in post_samp(nsample, grid, n, waveletcoefmat, pkljbar, C4, C5, seed): object '_BHMSMAfMRI_post_samp' not found
dim(postsample$samples)
#> Error in eval(expr, envir, enclos): object 'postsample' not found
#[1] 3 8 8 5