Gibbs update of regression coefficients and additive effects for replicated relational data

Draws jointly from the full conditional distribution of the regression coefficients beta together with the additive sender/receiver effects a and b, pooling the information contained in the replicate slices of a longitudinal design that share a common beta, a and b. The draw is obtained by forming the complete joint Gaussian posterior precision matrix over (beta, a, b) from sufficient statistics accumulated across slices, after whitening the within-dyad correlation, and sampling from it.

Usage

rbeta_ab_rep_fc(Z.T,Sab,rho,X.T,s2=1)

Arguments

Z.T

n x n x T array of latent relations with multiplicative effects already removed; the third margin indexes the replicates

Sab

2 x 2 covariance matrix of the additive row/column effects

rho

within-dyad (reciprocity) correlation

X.T

n x n x p x T design array

s2

dyadic variance

Value

beta

regression coefficients

a

additive row effects

b

additive column effects

Author

lame authors