O'Connor Brian P
Department of Psychology, Lakehead University, 955 Oliver Road, Thunder Bay, ON, P7B 5E1 Canada.
Behav Res Methods Instrum Comput. 2004 Feb;36(1):17-28. doi: 10.3758/bf03195546.
Levels-of-analysis issues arise whenever individual-level data are collected from more than one person from the same dyad, family, classroom, work group, or other interaction unit. Interdependence in data from individuals in the same interaction units also violates the independence-of-observations assumption that underlies commonly used statistical tests. This article describes the data analysis challenges that are presented by these issues and presents SPSS and SAS programs for conducting appropriate analyses. The programs conduct the within-and-between-analyses described by Dansereau, Alutto, and Yammarino (1984) and the dyad-level analyses described by Gonzalez and Griffin (1999) and Griffin and Gonzalez (1995). Contrasts with general multilevel modeling procedures are then discussed.
只要从同一二元组、家庭、教室、工作小组或其他互动单元中的多个人收集个体层面的数据,就会出现分析层次问题。来自同一互动单元中个体的数据的相互依赖性也违反了常用统计检验所依据的观测独立性假设。本文描述了这些问题所带来的数据分析挑战,并给出了用于进行适当分析的SPSS和SAS程序。这些程序进行了丹塞罗、阿卢托和亚马里诺(1984年)所描述的数据内部和数据之间的分析,以及冈萨雷斯和格里芬(1999年)以及格里芬和冈萨雷斯(1995年)所描述的二元组层面的分析。然后讨论了与一般多层建模程序的对比。