“…For the random vector (R 1 (a 0 ), · · · , Rn(a 0 )), applying the constraints [23,25] 15) this vector follows a Dirichlet distribution [41,74], D (ξ 1 (a 0 ), · · · , ξn(a 0 )). Then, every random variable Rp(a 0 ), p = 1, · · · , n, follows a standard Beta distribution [40,41], B(ξp(a 0 ), ψp(a 0 )), with ξp(a 0 ) > 0 and ψp(a 0 ) = n q=1,q =p ξq(a 0 ) > 0 satisfying 17) and is calculated from the mean values obtained at step 1. Finally, the optimal hyperparameter vectors (ρ 1 (a 0 ), ρ 2 (a 0 )) and (ξ 1 (a 0 ), · · · , ξn(a 0 )) are identified by minimising the residual for the standard deviation (3.6), and taking into account relations (3.10), (3.13), and (3.16).…”