cTWAS Prior-Estimation Settings — CtwasPriorParam-class • pecotmr

The EM stage that estimates cTWAS's group priors (group_prior / group_prior_var). These are exactly the settings estCtwasGroupPriors takes, so the bundle travels from ctwasPipeline to that function whole.

Usage

CtwasPriorParam(
  thin = 0.1,
  niterPrefit = 3L,
  niter = 30L,
  varStructure = c("shared_type", "shared_context", "shared_nonSNP", "shared_all",
    "independent"),
  fallbackToPrefit = FALSE
)

Arguments

thin: Numeric. Proportion of SNPs retained when assembling region data for the EM. Default 0.1. This is stochastic thinning for speed, unrelated to VariantPruningParam, which decides which variants enter a gene's weight matrix.
niterPrefit: Integer. Iterations for the prefit EM. Default 3.
niter: Integer. Iterations for the accurate EM. Default 30.
varStructure: How the prior variance is shared across groups; one of "shared_type" (default), "shared_context", "shared_nonSNP", "shared_all" or "independent".
fallbackToPrefit: Logical. When the accurate EM returns NaN on underpowered data, fall back to the prefit estimates rather than failing. Default FALSE. A pecotmr recovery step, not a cTWAS argument.

Value

A CtwasPriorParam object, a MethodParam.

Examples

CtwasPriorParam(thin = 1, niter = 10, fallbackToPrefit = TRUE)
#> <CtwasPriorParam>
#>   thin                     1
#>   niterPrefit              3
#>   niter                    10
#>   varStructure             shared_type
#>   fallbackToPrefit         TRUE