Skip to contents

Creates candidate groups based on a SuSiE model

Usage

susie_groups(alphas, X, q, max_pep = 1, max_size = 25, prenarrow = TRUE)

Arguments

alphas

An L x p matrix of alphas from a SuSiE object.

X

the N x p design matrix. If not NULL, will also add hierarchical groups based on a correlation cluster of X.

q

The nominal level at which to control the error rate

max_pep

The maximum posterior error probability (PEP) allowed in a candidate group. Default is 1.

max_size

maximum allowable size for each group.

prenarrow

If true, prenarrows the candidate groups as described in the paper. Defaults to TRUE.