STANDARD ERRORS AND SAMPLE SIZES FOR 2-LEVEL RESEARCH

The hierarchical linear model approach to a two-level design is consid ered, some variables at the lower level having fixed and others having random regression coefficients. An approximation is derived to the co variance matrix of the estimators of the fixed regression coefficients (for variables at the lower and the higher level) under the assumptio n that the sample sizes at either level are large enough. This covaria nce matrix is expressed as a function of parameters occurring in the m odel. If a research planner can make a reasonable guess as to these pa rameters, this approximation can be used as a guide to the choice of s ample sizes at either level.