Considerations for the use of plausible values in large-scale assessments

Large-scale assessments are rich sources of data that can inform a diverse range of research questions related to educational policy and practice. For this reason, datasets from large-scale assessments are available to enable secondary analysts to replicate and extend published reports of assessment results. These datasets include multiple imputed values for proficiency, known as plausible values. Plausible values enable the analysis of achievement in large-scale assessment data with complete-case statistical methods such as t-tests implemented in readily-available statistical software. However, researchers are often challenged by the complex and unfamiliar nature of plausible values, large-scale assessments, and their datasets. Misunderstandings and misuses of plausible values may therefore arise. The aims of this paper are to explain what plausible values are, why plausible values are used in large-scale assessments, and how plausible values should be used in secondary analysis of the data. Also provided are answers to secondary researchers' frequently asked questions about the use of plausible values in analysis gathered by the authors during their experience advising secondary users of these databases.