摘要
本文目的是介绍偏好评分资料的数据结构及其对应的结合分析方法。产生此类资料的场合类似于“多因素析因设计或正交设计”,但计量结果变量的取值在一定程度上受到评价者主观或偏好的影响。结合分析模型是基于各属性(或因素)的“分值效用或水平效用”可以“简单叠加”的假定成立的条件下构造出来的,当实际问题符合此假定时,其分析结果是正确的;否则,要慎重使用。必要时,需要选择其他统计模型。本文通过一个实例,并利用SAS中TRANSREG过程演示实现结合分析的详细步骤。
The purpose of this paper was to introduce the data structure of the preference data and its corresponding analysis method called the conjoint analysis. The situations which could produce such kind of the data mentioned before were similar to "the factorial design or orthogonal design of the multi-factors". The value of the measurement variables, however, could be affected by the subjectivity or preference of the valuators. The conjoint analysis model was set up under the condition of the assumption that the "Part-Worth Utility or Level-Worth Utility" could be simply superimposed. When the actual problem was conformed the assumption mentioned before, the analyzed results was correct, otherwise the conjoint analysis should be used with caution. The other statistical model should be selected when it was necessary. The paper showed that detailed steps of performing the conjoint analysis by using the TRANSREG procedure in SAS through a real example.
作者
胡良平
Hu Liangping(Graduate School, Academy of Military Sciences PLA China, Beijing 100850, China;Specialty Committee of Clinical Scientific Research Statistics of World Federation of Chinese Medicine Societies, Beijing 100029, China)
出处
《四川精神卫生》
2019年第3期209-215,共7页
Sichuan Mental Health
基金
国家高技术研究发展计划课题资助(2015AA020102)
关键词
属性
析因设计
正交设计
偏好评分
结合分析
Attribute
Factorial design
Orthogonal design
Preference score
Conjoint analysis
