Co-Principal Investigator: Eric Hedberg (NORC)

In many states, the data from statewide longitudinal data systems (SLDS) are available to a small group of state education agencies and scholars. In addition, data linking, either between educational data systems (i.e. between K-12 and postsecondary data systems) or between educational data and other state data (e.g. postsecondary and workforce data), can be challenging. There are education researchers in the academy and in research firms that have the capacity to use state longitudinal data for productive research purposes. A few individual researchers have obtained access to longitudinal data in a handful of states and demonstrated the potential usefulness of these data. However, the transaction costs of accessing these data can be high. As a result, wide access to these data has not been achieved.

In this project, researchers plan to evaluate variants of two statistical disclosure control methods. The first is the GenMASSC approach used by several census agencies, and the second is a multiple imputation approach. Using the SLDS data, both approaches will be evaluated in terms of their ability to protect against disclosure and preserve the information in the original datasets so that educational researchers with conventional training (i.e., those who are not themselves statisticians) can use standard software to carry out analyses. Researchers plan to make it possible for applied education researchers routinely to gain access to SLDS data for their research. The project team is working closely with states to address their concerns that FERPA restrictions limit their ability to make SLDS data available to more researchers. If the researchers find that one or both of the statistical disclosure control methods adequately meet the states' concerns about disclosure risk and the researchers’ needs for accurate data, states could make their SLDS data widely available to education researchers.

Products and Publications

Journal article, monograph, or newsletter

Hedges, L.V. (2018). Challenges in Building Usable Knowledge in Education. Journal of Research on Educational Effectiveness, 11(1), 1–21.

Hedges, L.V., and Schauer, J.M. (2019). Statistical Analyses for Studying Replication: Meta-Analytic Perspectives. Psychological Methods, 24(5), 557.

Hedges, L.V., and Schauer, J.M. (2019). More Than One Replication Study Is Needed for Unambiguous Tests of Replication. Journal of Educational and Behavioral Statistics, 1076998619852953.