The generalized Friedman's urn (GFU) model has been extensively applied to
biostatistics. However, in the literature, all the asymptotic results conce
rning the GFU are established under the assumption of a homogeneous generat
ing matrix, whereas, in practical applications, the generating matrices are
often nonhomogeneous. On the other hand, even for the homogeneous case, th
e generating matrix is assumed in the literature to have a diagonal Jordan
form and satisfies lambda>2 Re(lambda(1)), where lambda and lambda(1) are t
he largest eigenvalue and the eigenvalue of the second largest real part of
the generating matrix (see Smythe, 1996, Stochastic process. Appl. 65, 115
-137). In this paper, we study the asymptotic properties of the GFU model a
ssociated with nonhomogeneous generating matrices. The results are applicab
le to a variety of settings, such as the adaptive allocation rules with tim
e trends in clinical trials and those with covariates. These results also a
pply to the case of a homogeneous generating matrix with a general Jordan f
orm as well as the case where lambda = 2 Re(lambda(1)). (C) 1999 Elsevier S
cience B.V. All rights reserved.