sp_fa_control: Auxiliary function for 'sp_fa'.

In rdevito/MSFA: Maximum Likelihood Estimation and Bayesian analysis of MSFA models

Description

Set parameters for posterior sampling and prior hyperparameters for the sparse Bayesian infinite factor model. For the latter, the notation follows closely the paper by Bhattacharya and Dunson (2011).

Usage

sp_fa_control(
  nrun = 30000,
  burn = 20000,
  thin = 1,
  nu = 3,
  asigma = 1,
  bsigma = 0.3,
  a1 = 2.1,
  b1 = 1,
  a2 = 2.1,
  b2 = 1
)

Arguments

nrun	Number of posterior simulations. Default is 30000.
burn	Burn-in trials. Default is 20000.
thin	Thinning of posterior samples. Default is 1 (no thinning).
nu	Parameter entering the gamma distribution assumed for phi. Default is 3.
asigma	Shape parameter for the gamma distribution assumed for 1/sigma^2. Default is 1.
bsigma	Scale parameter for the gamma distribution assumed for 1/sigma^2. Default is 0.3.
a1	Shape parameter for the gamma distribution assumed for delta1. Default is 2.1.
b1	Scale parameter for the gamma distribution assumed for delta1. Default is 1.
a2	Shape parameter for the gamma distribution assumed for deltal. Default is 2.1.
b2	Scale parameter for the gamma distribution assumed for deltal. Default is 1.

References

Bhattacharya, A. and Dunson, D.B. (2011). Sparse Bayesian infinite factor models. Biometrika, 98, p. 291-306.

rdevito/MSFA documentation built on March 18, 2020, 2:57 p.m.