Introduction to Design and Analysis of Hierarchical Models
Business Knowledge Series course (Live Web)
|
Duration: 1
half-day session Please note the System Requirements below. CEUs: 0.3 | ||
| Available for on-site training or can be scheduled at any SAS training facility if demand warrants. |
This session introduces hierarchical models. Hierarchical designs are used in many areas of research, with the most prominent use in the social sciences. The structure of a hierarchical design is that it involves nesting smaller units into larger units, a feature of a multilevel design. Multilevel designs are used by researchers in many areas (Raudenbush and Bryk (2002) and Milliken and Johnson (1992)), and those researchers have used different terminologies to describe the designs. Multilevel designs are designs that involve more than one size of experimental unit where small units are nested within larger units--thus, the name multilevel. Split-plot designs are multilevel designs, and they have been used by physical and biological science researchers since the 1930s. Hierarchical designs and now multilevel designs have been used by social science researchers in the past few years. The structures are identical, and the models needed to describe resulting data are identical. The process of constructing a model for the analysis of data from a hierarchical design involves putting together models at each of the levels in the structure. This presentation provides a general framework within which to identify or design and then analyze multilevel designs, whether called split-plot, hierarchical, or multilevel. Repeated measures designs are multilevel designs. A collection of examples involving hierarchical designs is used to demonstrate the analyses, including a discussion on repeated measures analyses. All of the models that are required to provide appropriate analyses of these designs are members of the class of mixed models. The MIXED and GLIMMIX procedures of the SAS System are used to fit all of the models.