Liang and Hanfelt (1994) described a teratology study comparing control and treatment groups in which the ML estimate of the treatment effect in a beta-binomial model differs by a factor of 2 depending on whether one assumes the same overdispersion parameter for each group. By contrast, with variance function (13.11), the quasi-likelihood estimate of the treatment effect is the same whether one assumes the same or different ϕ for the two groups. Explain why, and discuss whether this is an advantage or disadvantage of that method.