Department of Psychology, Fordham University, Bronx, NY 10458, USA.
Psychol Methods. 2012 Jun;17(2):215-27. doi: 10.1037/a0027129. Epub 2012 Feb 6.
Racial/ethnic diversity has become an increasingly important variable in the social sciences. Research from multiple disciplines consistently demonstrates the tremendous impact of ethnic diversity on individuals and organizations. Investigators use a variety of measures, and their choices can affect the conclusions that can be drawn and limit the ability to compare and generalize results across studies effectively. The current article reviews 3 popular approaches to the measurement of diversity: the simplistic majority-minority approach and 2 multiple categories variants, the generalized variance and the lesser used entropy statistic. We discuss the properties of each approach and reject the majority-minority approach. We provide 5 examples using the generalized variance and entropy statistics and illustrate their versatility and flexibility. We urge investigators to adopt these multicategory measures and to use our discussion to determine which measure of diversity is most appropriate given the nature of one's data set and research question.
种族/民族多样性已成为社会科学中一个日益重要的变量。来自多个学科的研究一致表明，民族多样性对个人和组织有着巨大的影响。研究人员使用各种方法，他们的选择会影响到可以得出的结论，并限制在研究之间进行比较和概括结果的能力。本文综述了多样性测量的 3 种常用方法：简单的多数-少数方法和 2 种多类别变量，即广义方差和使用较少的熵统计。我们讨论了每种方法的特性，并拒绝了多数-少数方法。我们提供了 5 个使用广义方差和熵统计的例子，说明了它们的多功能性和灵活性。我们敦促研究人员采用这些多类别措施，并根据自己数据集和研究问题的性质，使用我们的讨论来确定哪种多样性衡量方法最合适。
