Estimating Statistical Power and Required Sample Sizes for Organizational Research Using Multilevel Modeling
介绍多层模型中统计功效的基本概念，分析影响功效的独特因素，并给出估计固定效应、方差成分和跨层交互作用功效的计算方法，同时讨论模拟研究结果、经验法则和现有功效分析软件。
The use of multilevel modeling to investigate organizational phenomena is rapidly increasing. Unfortunately, little advice is readily available for organizational researchers attempting to determine statistical power when using multilevel models or when determining sample sizes for each level that will maximize statistical power. This article presents an introduction to statistical power in multilevel models. The unique factors influencing power in multilevel models and calculations for estimating power for simple fixed effects, variance components, and cross-level interactions are presented. The results of simulation studies and the existing general rules of thumb are discussed, and the available power analysis software is reviewed.