Estimate Sparsity from mr.ash Mixture Proportions

Computes an empirical estimate of the proportion of non-zero effects (sparsity) from the mr.ash fit. mr.ash fits a mixture model with a point mass at zero (spike) plus continuous components (slab), and learns the mixture proportions via variational EM. The sparsity estimate 1 - pi[1] is the empirical Bayes estimate of the non-null proportion, which can be used as a data-driven prior for the inclusion probability parameters (pi for bayesC, probIn for BayesB) of spike-and-slab Bayesian methods.

Usage

estimateSparsity(weightResults)

Arguments

weightResults

Named list of weight vectors or matrices as returned by learnTwasWeights. The mr.ash element should have a "fit" attribute containing the model fit object (set retainFits = TRUE in learnTwasWeights to obtain this).

Value

A scalar sparsity estimate (proportion of non-zero effects).

Examples

estimateSparsity(list(mrash_weights = structure(c(0.1, 0, 0.3),
  fit = list(pi = c(0.6, 0.2, 0.2)))))
#> [1] 0.4