A variety of collective phenomena are understood to exist to the extent that workers agree on their perceptions of the phenomena, such as perceptions of their organization’s climate or perceptions of their team’s mental model. Researchers conducting group-level studies of such phenomena measure individuals’ perceptions via surveys and then aggregate data to the group level if the mean within-group agreement for a sample of groups is sufficiently high. Despite this widespread practice, we know little about the factors potentially affecting mean within-group agreement. Here, focusing on work climate, we report an investigation of a number of expected contextual (social interaction) and methodological predictors of mean r_WG, a common statistic for judging within-group agreement in applied psychology and management research. We used the novel approach of meta-CART, which allowed us to assess the relative importance and possible interactions of the predictor variables. Notably, mean r_WG values are driven by both contextual (average number of individuals per group and cultural individualism-collectivism) and methodological factors (the number of items in a scale and scale reliability). Our findings are largely consistent with expectations concerning how social interaction affects within-group agreement and psychometric arguments regarding why adding more items to a scale will not necessarily increase the magnitude of an index based on a Spearman-Brown “stepped-up correction.” We discuss the key insights from our results, which are relevant to the study of multilevel phenomena relying on the aggregation of individual-level data and informative for how meta-analytic researchers can simultaneously examine multiple moderator variables.

各种集体现象被理解为存在于工人对他们对现象的看法达成一致的程度，例如对他们组织的气候的看法或对他们团队的心理模型的看法。对此类现象进行群体层面研究的研究人员通过调查测量个人的看法，然后如果群体样本的平均组内一致性足够高，则将数据汇总到群体层面。尽管有这种广泛的做法，但我们对可能影响平均组内一致性的因素知之甚少。在这里，专注于工作氛围，我们报告了对平均 r _{WG的一些预期背景（社会互动）和方法学预测因子的调查}，在应用心理学和管理研究中判断组内一致性的常用统计数据。我们使用了 meta-CART 的新方法，这使我们能够评估预测变量的相对重要性和可能的​​相互作用。值得注意的是，平均 r _WG价值观是由上下文（每组的平均人数和文化个人主义-集体主义）和方法因素（量表中的项目数量和量表可靠性）驱动的。我们的研究结果与关于社会互动如何影响组内一致性的预期和心理测量学的论点基本一致，即为什么在量表中添加更多项目不一定会增加基于 Spearman-Brown “加强校正”的指数的幅度。我们讨论了我们的结果中的关键见解，这些见解与依赖于个体级数据聚合的多层次现象的研究相关，并为元分析研究人员如何同时检查多个调节变量提供了信息。