succotash_summaries: Provides posterior summaries in the SUCCOTASH model.

In dcgerard/succotashr: Surrogate and Confounder Correction Occuring Together with Adaptive Shrinkage

Description

succotash_summaries will return useful posterior summaries used in estimation and testing/FDR control.

Usage

succotash_summaries(Y, Z, pi_vals, alpha, sig_diag, tau_seq, scale_val = 1)

Arguments

Y	A matrix of dimension p by 1. These are the observed regression coefficients of the observed variables.
Z	A matrix of dimension k by 1. The (estimated) confounding covariates.
pi_vals	A vector of length M. The (estimated) mixing proportions.
alpha	A matrix. This is of dimension p by k and are the coefficients to the confounding variables.
sig_diag	A vector of length p containing the variances of the observations.
tau_seq	A vector of length M containing the standard deviations (not variances) of the mixing distributions.
scale_val	A positive numeric. The amount to scale the variances by

Details

The posterior distribution is just a mixture of normals. This function will the posterior means as a point estimate. It will also return local false sign and discovery rates. These are useful for controlling for multiple testing.

Value

lfdr (local false discovery rate) A vector of length p. The posterior probability that β_j = 0.

lfsr (local false sign rate) A vector of length p. The posterior probability of making a sign error.

betahat A vector of length p. The posterior estimates of β.

dcgerard/succotashr documentation built on May 15, 2019, 1:25 a.m.