To Experts, x = x1 + x3 y = x2 + x3 x3 = cov(x1,x2) By refer to package "bivpois", I'ld like to downweight previous x,y in my data based on date, I am wondering if lambda3 should robust as well, since lambda3 measure the co-relationship of lambda1 and lambda2, but if robust lambda3 might effect the covariance of lambda1 and lambda2 I though. I am sorry if misunderstanding the concept of a bivariate Poisson. Appreciate if experts willing to share precious advice. -- View this message in context: http://n4.nabble.com/Robust-Bivariate-Poisson-tp991214p991214.html Sent from the R help mailing list archive at Nabble.com.