Exercise 10.2 Example X.8: Assume in model M1 three choices for the inverse Wishart prior IW(D, 2) for G the covariance matrix of the random effects, varying by the choice of D:

(a) D = diag(0.001, 0.001),

(b) D =  2 −0.1 −0.1 0.02  and

(c) D = diag(100, 100). Evaluate the rate of convergence of the three Gibbs samplers and compare their posterior estimates with those obtained from a frequentist analysis using the SAS procedure MIXED. Use ‘chapter 10 Pothoff-Roy growthcurves.odc’. What is your conclusion?