As. Papadopoulos et Rc. Tiwari, BAYESIAN-APPROACH FOR BOD AND DO WHEN THE DISCHARGED POLLUTANTS ARE RANDOM, Ecological modelling, 71(4), 1994, pp. 245-257
A stochastic model for biochemical oxygen demand (BOD) and disserved o
xygen (DO) at a distance t downstream, when pollutants are discharged
over a continuous stretch, is a random differential equation of the fo
rm X(t) = AX(t) + Y(t), t greater than or equal to O, with the initial
condition X(O)= X(O). Assuming that X(O) is a random vector having a
bivariate normal distribution with the mean vector mu(O) and the preci
sion (the inverse of the variance-covariance) matrix Lambda(O), we pro
vide the prediction equation ($) over cap X(t) at any point t by emplo
ying (i) a normal prior for mu(O) keeping Lambda(O) fixed and known, a
nd (ii) a normal-Wishart prior for (mu(O), Lambda(O)). The theory is s
upplemented by numerical studies.