Assessing Reproducibility of Analytic Findings Derived Through National Survey Data Integration Efforts: A Case Study Linking Patient-Level Clinical Trial Data with Medical Expenditure Panel Survey Data
Steven B. Cohen
RTI International
Jennifer Unangst
RTI International
Feng Yu
RTI International
The quality and content of national population-based surveys are enhanced through integrated designs that link additional medical, behavioral, environmental, socio-economic and financial content from multiple sectors. The integration of national survey data with such content has the capacity to provide greater insights than possible from any of the component sources. While it is preferential to restrict these data enhancement efforts to situations that permit one-to-one linkages, this is often not possible. In this paper, we focus on a data integration effort that is impacted by many-to-many linkages and provide a model for assessing the reproducibility of analytic findings attributable to alternative linkage applications. Examples are provided using data from the MEPS and cancer patient phase III clinical datasets. This data integration effort permits studies assessing the influence of health-related and socioeconomic factors, access to and use of health care, and health behaviors in concert with clinical trial treatment effects on cancer patient outcomes. In this study, we assess the reproducibility and reproducibility and stability of analytic results.