Benedetti J K, Brown M B
Biometrics. 1978 Dec;34(4):680-86.
In a multidimensional contingency table strategies have been proposed to build log-linear models using either stepwise methods or standardized estimates of the parameters of the saturated model. Brown (1976) proposed a two-step procedure to screen effects and then test a subset of models. Alternate methods of model building are discussed with respect to the final choice of model and with respect to intermediate information available to the data analyst during the selection process.
在多维列联表中，已经提出了一些策略，可使用逐步法或饱和模型参数的标准化估计来构建对数线性模型。布朗（1976年）提出了一个两步程序来筛选效应，然后对模型子集进行检验。关于模型的最终选择以及在选择过程中数据分析师可获得的中间信息，讨论了模型构建的替代方法。
