析因设计资料单独效应分析的SAS实现  

Analysis of simple effect on factorial design with SAS

作　　者：张旭东[1] 彭斌[1] 王润华[1] 

机构地区：[1]重庆医科大学公共卫生学院卫生统计教研室,重庆400016

出　　处：《重庆医科大学学报》2008年第12期1509-1512,共4页Journal of Chongqing Medical University

摘　　要：目的:探讨析因设计资料单独效应分析的SAS实现方法。方法:将析因设计的总的误差均方作为标准误,通过构造参数的对比系数矩阵,利用SAS的GLM过程中Contrast语句编程实现单独效应分析,并结合实例给出SAS程序来实现三因素析因设计资料的统计分析。结果:给出了设计参数对比系数矩阵的方法。结论:通过构造设计矩阵,在SAS中编写Contrast语句来实现单独效应分析,是一种方便可行的方法。Objective： To explore the approach to analyzing simple effect on factorial design with SAS. Methods： The mean square of error coming from factorial design was considered as standard error（SE ）, and simple effect analysis under Contrast statement in GLM was conducted by designing the contrast coefficient matrix of the parameter, and SAS program was realized based on an example of 3-way factorial design. Results： he procedures of designing the contrast coefficient matrix of the parameter were achieved. Conclusion： It is convenient and feasible to conduct simple effect analysis under Contrast statement by constructing design matrix.

关 键 词：析因设计 单独效应 对比系数矩阵 

分 类 号：O212.6[理学—概率论与数理统计]