Skip to main content
. Author manuscript; available in PMC: 2015 Jan 1.
Published in final edited form as: J Comput Graph Stat. 2013 Apr 28;23(2):543–563. doi: 10.1080/10618600.2013.791193
Algorithm 3: Iterative Procedure for Parameter Covariance Estimation
1. Set Γ̂(0) =I, Λ(0) = I, and t = 1, where I is an identity matrix.
2. Draw N samples using Γ̂(t−1), an orthogonal basis for the factor slice sampler.
3. Compute Λ(t) and its corresponding eigenvectors Γ(t).
4. Find A, where A is a rotation matrix such that Λ(t−1)A = Λ(t). Set t = t + 1.
5. Repeat steps 2 through 4 until Σ (A− I) is below a preset threshold.