Assessing the Performance of Panel Data Synthesis Approach

Organizations that seek to advance their ability to screen employees and mitigate risk may use Inference Enterprise Modeling (IEM) to develop models to predict the effects of proposed enhancements. However, organizations that do not have the resources to perform these tasks may outsource this work to a third-party expert. Since there exist concerns about disclosing information about individuals, sensitive details of organizations, and other private information, information shared with external parties may be aggregated to hide confidential information while providing essential data required by third parties to perform their duties. In this study, we evaluate how models constructed from aggregated data compare to models constructed using full data. We further define IEM best practices in the area of population modeling.