“Small” or “Large” Farm: Some Methodological Considerations
讨论在欠发达国家农业研究中，将样本武断分为大小农场并分别估计生产函数的方法问题，提出用累积正态或逻辑函数替代虚拟变量，以判断分类是否合理及划分点。
Abstract Often the estimation of agricultural production technologies in less developed countries is achieved by dividing the sample arbitrarily into “small” and “large” farms and estimating a separate production function for each group. This is equivalent to including an appropriate dummy variable in a single regression on the whole sample. A modification of this approach is to replace the dummy variable (a step‐function) by either a cumulative normal or logistic function. The parameters of such a “generalized dummy variable” convey valuable information on whether a small‐large categorization is appropriate and, if so, where the division should be made.