factor_infinite: Runs gibbs sampler for a factor model with potentially...

In dcbdan/s525: Implementation of common Bayesian models

Description

The model is as follows:

y_i = Λ η_i + ε_i

ε_i \sim N_p(0, Σ)

where Σ = diag(σ_1^2, ..., σ_p^2).

See Bhattacharya, Anirban, and David B. Dunson. 'Sparse Bayesian infinite factor models.' Biometrika (2011): 291-306.

Usage

factor_infinite <- function(
  Y,
  k_star,
  niter = 1000,
  a_sig = 1,
  b_sig = 1,
  rho = 3,
  a1 = 1,
  a2 = 3)

Arguments

Y	n by p matrix
k_star	number of factors to cut off at
niter	number of iterations for the gibbs sampler to run.
a_sig	shape hyper parameter for the σ^2
b_sig	shape hyper parameter for the σ^2
rho	hyper parameter
a1	hyper parameter
a2	hyper parameter

Value

sigma2	An niter x p matrix of posterior values
lambda	An niter x p x k_star array of posterior values

dcbdan/s525 documentation built on May 19, 2019, 10:48 p.m.