Modeling and Inference for Multivariate Binary Data with Positive Dependence
提出一种自然融入正相依结构的多元二元数据模型，源自可靠性理论，适用于任何需要正相依假设的领域，并讨论了极大似然估计方法。
A model is proposed for multivariate binary data that incorporates positive dependence among components in a natural way. The model is derived from reliability-theoretic concepts, but is regarded as appropriate for analysis of multivariate binary data in any field when positive dependence is an appropriate assumption. Maximum likelihood estimation by iterative solution of likelihood equations is discussed for the general model, and asymptotically efficient estimates are obtained in closed form for the fully parameterized (saturated) model. The estimation procedures are illustrated on a data set from Martin and Bradley (1972).