Advancing Statistical Modeling in the Social and Behavioral Sciences
Who We Are
Our research group is comprised of faculty, postdoctoral researchers, and students at Indiana University. If you’re interested in learning more, please see the “Contact Us” link below
Our research aims to advance knowledge related to various statistical models commonly used in the social and behavioral sciences, including particularly multilevel models and latent variable models. Some of our recent research topics include missing data and measures of effect size. Although we focus on methodological questions, we remain sensitive to the needs and challenges that applied researchers in our field may face.
Multiple Imputation's Impact On Growth Curve Estimates
Using simulated as well as empirical data, this study investigates the impact of multiple imputation tools, such as Amelia and MICE, on growth estimates from the multilevel model for change and latent growth curve model. We ground our study in an applied setting by using longitudinal survey response rates from approximately 1,000 colleges and universities that participated in the National Survey of Student Engagement (NSSE) between 2010 and 2018. The research team includes Shimon Sarraf (project lead), Ricky Granderson, Melissa Lee, Jonah Li, Prof. Julie Lorah, and Asmalina Saleh.
Applying Effect Sizes in Positive Psychology Research: Three Empirical Benchmarks
This project examines the use of effect sizes and proposes three empirical benchmarks of effect sizes in positive psychology (PP). Recent Research in PP has examined the effectiveness of positive psychological interventions (PPIs). This study aims to promote the application of effect sizes (ES) in PP research, contributing to contextualizing the interpretation of findings. In particular, we propose three empirical benchmarks: (1) trajectory of change over time; (2) person-activity fit of PPIs in multicultural contexts; and (3) observed ES for similar PP contexts. We contend that these three benchmarks contribute by providing applied researchers with a framework and guidance for reporting results. These benchmarks are closely aligned with PP’s fundamental framework: (1) positive subjective experience; (2) positive institutions; and (3) positive individual traits. Using publicly available data, we demonstrate how to calculate relevant ES measures, and interpret and contextualize findings.
New course announcement: Exploring Careers in Statistics (EDUC-F 203), Spring 2021, 2nd 8-week session
This one-credit course designed for students identifying as female will introduce you to the field of statistics and the various career and graduate school opportunities in statistics that you may be interested to pursue. In this course, we will meet regularly as a class to discuss issues in the field of statistics, such as diversity and learn more about fields where statistics may be applied, such as biostatistics and the health sciences, educational statistics, and data analytics. In addition, you will be paired with and meet regularly with a graduate student mentor. No prior statistics experience is required. You will leave the course with a basic understanding of the types of career trajectories and fields that make use of statistics and an idea of how your interests might fit within this landscape. To learn more, or to request permission to enroll, please contact the instructor: Dr. Julie Lorah, .