Replication Data for: Using Screeners to Measure Respondent Attention on Self-Administered Surveys: Which Items and How Many?

Inattentive respondents introduce noise into data sets, weakening correlations between items and increasing the likelihood of null findings. “Screeners” have been proposed as a way to identify inattentive respondents, but questions remain regarding their imple- mentation. First, what is the optimal number of Screeners for identifying inattentive respondents? Second, what types of Screener questions best capture inattention? In this paper, we address both of these questions. Using item-response theory to aggregate individual Screeners we find that four Screeners are sufficient to identify inattentive respondents. Moreover, two grid and two multiple choice questions work well. Our findings have relevance for applied survey research in political science and other disci- plines. Most importantly, our recommendations enable the standardization of Screeners on future surveys.注意力不集中的受访者会为数据集引入噪声，削弱各调查题项间的相关关系，同时提升出现虚无结果的概率。学界已提出将注意力甄别题（Screeners）作为识别注意力不集中受访者的手段，但关于其实施仍存在诸多疑问。其一，用于识别注意力不集中受访者的甄别题最优数量应为多少？其二，何种类型的甄别题最能有效捕捉受访者的注意力不集中情况？本研究针对上述两个问题展开探讨。本研究借助项目反应理论（Item Response Theory）对单道甄别题进行聚合分析，结果表明仅需4道甄别题即可有效识别注意力不集中的受访者。进一步分析显示，2道矩阵题与2道多项选择题的组合效果最佳。本研究结论可为政治学及其他学科的应用调查研究提供参考。尤为重要的是，本研究提出的建议可为未来调查中甄别题的标准化实施提供依据。