A taxonomy of data synthesis
Abstract: As more data is shared and concerns over the replicability, reproducibility, and generalizability of psychological and other social sciences continues, more researchers aim to conduct multi-study or multi-sample research (e.g., using traditional meta-analysis, individual participant data meta-analysis [IPD-MA], or coordinated analysis). However, existing frameworks of data synthesis neither clearly differentiate different approaches or compare their convergence, unique considerations, and more. This talk has three main goals. First, I provide an overview of data synthesis methods and organize these into a taxonomy of methods of data synthesis. Second, using empirical data from 26,205 participants across 10 longitudinal studies, I provide a tutorial for estimating prospective meta-analytic and sample-specific associations between the Big Five personality traits and crystallized abilities along with four moderators of these associations across each method. Finally, I compare convergence and divergence of findings across methods. I conclude by making recommendations and providing a flow chart for choosing the most appropriate method of data synthesis given research goals, questions, and data availability.
Export event as iCal