Statistical Treatment Choice
本文提出两种统计方法改进：一是合并不同数据集（旧客户与新客户）时处理回归变量不匹配问题，二是对推荐的治疗选择进行统计推断并以透明方式传达给决策者。在瑞士针对失业者的积极劳动力市场项目选择中进行了试点应用。
AbstractChoosing among a number of treatments the most suitable for a particular client is an issue of everyday concern. In this article two methodological advances for statistically assisted treatment choice are developed: First, it permits one to combine a dataset on previously treated clients with a dataset on new clients when the regressors available in these two datasets do not coincide. It thereby incorporates additional regressors on previously treated clients that are not available for the current clients. Such a situation often arises because of cost considerations, data confidentiality reasons, or time delays in data availability. Second, statistical inference on the recommended treatment choice is analyzed and conveyed to the agent or caseworker in a comprehensible and transparent way. The implementation of this methodology in a pilot study in Switzerland for choosing among active labor market programs for unemployed job seekers is described.KEY WORDS: Active labor market policiesStatistical treatment rules