Valid questions: the development and evaluation of a new library learning analytics survey
Purpose. This article describes the development processes, sampling and analysis practices and the assessment of reliability and validity of a new survey that sought to evaluate undergraduate students' perceptions and expectations related to privacy and library participation in learning analytics studies. This article provides other researchers with information required to independently evaluate the survey's efficacy, as well as guidance for designing other surveys. Design/methodology/approach. Following question development, pre-survey validity assessments were made using subject matter expert panel review and cognitive interviews. Post-hoc analysis of survey construct reliability was evaluated using the Omega coefficient, while exploratory factor analysis was utilized to assess construct validity. Survey design limitations and potential bias effects are also examined. Findings. The survey exhibited a high level of reliability among research constructs, while the exploratory factor analysis results suggested that survey constructs contained multiple conceptual elements that should be measured separately for more nuanced analysis. Practical implications. This article provides a model for other researchers wishing to re-use the survey described or develop similar surveys. Social implications. As learning analytics interest continues to expand, engaging with the subjects, in this case students, of analysis is critical. Researchers need to ensure that captured measurements are appropriately valid in order to accurately represent the findings. Originality/value. This survey is one of very few addressing library learning analytics that has undergone extensive validity analysis of the conceptual constructs.
Additional Information© 2023, Emerald Publishing Limited. The Data Doubles project on which this article is based was funded by the Institute of Museum and Library Services (LG-96-18-0044-18). The views, findings, conclusions, or recommendations expressed in this article do not necessarily represent those of the Institute of Museum and Library Services. The authors would like to thank Data Doubles research team members Kyle M. L. Jones (PI), Michael Perry, Mariana Regalado, Dorothea Salo, and Maura A. Smale for their contributions to the Data Doubles project and survey, and research assistants Rushikesh Gawande and Ajinkya Pawale for their support with R coding and development.
Accepted Version - Asher_2023_ValidQuestions_AuthorAccepted.pdf