Appendix: Pseudo Code for Step 1 of the Gibbs Sampler
a. First, generate a Wishart random variable A(i) = [Σ(i) ]-1 ~ W (S-1, ν ).
i. Let LL = S-1, where L is a lower triangular matrix from the Cholesky de-
composition of S-1. We obtain S-1 as the inverse of the estimated variance-
covariance matrix of the error terms.
ii. Assume that Q ~ W (I, ν ). Then LQL ~ W (LL, ν ) = W (S-1, ν )
iii. Now from Anderson (1984) UU ' = Q ~ W (I, ν ), where U is lower triangular,
all uij are independent, uij∙ ~ N(0,1), i > j, and u2i ~ χ2(ν — i + 1) random
variable, which implies that LUU 'L' ~ W (S-1, ν ). Thus, we draw uij values
and form Q(i) = U(i)U(i) .
iv. Now use L and Q(i) compute LQ(i)L'∕ν = A(i).
b. Compute Σ(i) = [A(i)]-1 , which is an inverse-Wishart random variable.
28
More intriguing information
1. Word searches: on the use of verbal and non-verbal resources during classroom talk2. Comparison of Optimal Control Solutions in a Labor Market Model
3. Pursuit of Competitive Advantages for Entrepreneurship: Development of Enterprise as a Learning Organization. International and Russian Experience
4. Handling the measurement error problem by means of panel data: Moment methods applied on firm data
5. he Virtual Playground: an Educational Virtual Reality Environment for Evaluating Interactivity and Conceptual Learning
6. National urban policy responses in the European Union: Towards a European urban policy?
7. The name is absent
8. Integrating the Structural Auction Approach and Traditional Measures of Market Power
9. CAN CREDIT DEFAULT SWAPS PREDICT FINANCIAL CRISES? EMPIRICAL STUDY ON EMERGING MARKETS
10. A parametric approach to the estimation of cointegration vectors in panel data