SAS Macro for Nonparametric Bootstrap Multilevel Modeling

Multilevel models have been widely used to analyze hierarchically structured data. However, researchers often encounter a challenging issue with their data; i.e., the number of higher level units (e.g., the second level units) is sometimes small. Both parametric and non-parametric residual bootstrap multilevel modeling can be applied to address the problem in multilevel modeling with small a number of higher units. The authors of the present study have developed a user-friendly SAS macro RBMLM for such modeling. In the proposed presentation, the authors will discuss the theory of residual bootstrap multilevel modeling and the strategy of conducting such modeling. Real data will be used to demonstrate how to apply the SAS macro to conducting non-parametric residual bootstrap multilevel modeling, and the results will be compared with those from the regular multilevel model. The SAS macro can also be used for non-parametric residual bootstrap multilevel modeling when data do not meet the normality assumption.