sp_OP: OP algorithm for loading matrix estimation

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

Description

Iterative algorithm for estimating a loading matrix from the posterior samples, resolving the orthogonality indeterminacy.

Usage

sp_OP(
  Phi_sample,
  tol = 10^-7,
  itermax = 50,
  init = NULL,
  updatesample = FALSE,
  trace = TRUE
)

Arguments

Phi_sample	Posterior samples for a loading matrix, a 3-dimensional array of dimension p x k x nchain.
tol	Tolerance for the OP algorithm. Default is 0.001.
itermax	Maximum number of iterations. Default is 10.
init	Starting point for the optimization.
updatesample	Should the posterior samples be updated? Default is FALSE.
trace	Print tracing information. Default is TRUE.

Value

A list containing the estimated loading matrix, plus the number of iterations performed and the Frobenius norm of the difference between the last two iterations of the algorithm.

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