Using Hierarchical Linear Models to Examine Moderator Effects: Person-by-Organization Interactions
介绍了分层线性模型（HLM）在检验跨层次交互效应中的应用，并与调节多元回归（MMR）进行比较，通过组织间测验效度数据示例说明HLM能处理更多组织、提高统计检验力。
A cross-level interaction is said to occur when the effects of client or employee characteristics interact with organizational characteristics to influence an employee or client outcome variable. Hierarchical linear modeling (HLM) is briefly described, particularly as it applies to the study of cross-level interactions. HLM is then compared to moderated multiple regression (MMR). An HLM model incorporating cross-level interactions is illustrated with data from a study of test validity across organizational units. An HLM model for person-organization congruence is then described. As compared to MMR, HLM can more readily handle large numbers of organizations. By increasing the number of organizations that can be studied, HLM should increase the power of the designs that researchers can use.