Testing Nonnested Models
介绍非嵌套模型间的回归检验方法，从Cox原理出发推导J检验和JA检验，并以线性与对数线性模型为例说明如何构造检验，附有实证示例。
Abstract Applied economic research often involves testing between nonnested models. In such situations informal criteria are often used in preference to readily available testing procedures. This article deals with regression‐based tests between nonnested models, showing the development of the J ‐ and JA ‐tests from the Cox principle. Testing between linear and log‐linear models is discussed as an example of how tests can be constructed when the dependent variables of competing models have a monotonic functional relationship. An empirical example is given to illustrate the procedures.