Research

Research Interests

My research advances the methodological foundations of empirical science across the social and behavioral sciences. I develop and refine statistical and psychometric methods that enable researchers to design more rigorous studies, draw more accurate inferences, and build a cumulative scientific literature. Without appropriate research design and principled analysis methods, empirical findings become unreliable—hindering both scientific progress and practical application. My collaborations span psychology, management, education, marketing, information technology, and behavioral medicine, applying and extending methodological tools to address substantive questions in each domain. As Tukey observed, “the best thing about being a statistician is that you get to play in everyone’s backyard!”

Research Design and Sample Size Planning

My primary contributions center on the interplay between effect sizes, confidence intervals, statistical significance, and sample size planning. Sample size planning is one of the most consequential decisions in study design. Studies with excessive sample sizes waste resources, delay knowledge dissemination, and may expose more participants to risk than necessary. Conversely, underpowered studies compromise inferential precision, reduce the likelihood of detecting meaningful effects, and squander participants’ and researchers’ efforts. My work provides principled frameworks—particularly accuracy in parameter estimation (AIPE) approaches—for determining appropriate sample sizes based on specific inferential goals. The design stage is where researchers exert the greatest influence on study quality, and where potential methodological shortcomings can be prevented rather than patched after the fact.

Broader Methodological Interests

Beyond research design, my work encompasses longitudinal data analysis, mixed-effects and multilevel models, mediation analysis, general latent variable models, finite mixture modeling, statistical classification and discrimination, bootstrap methods, Monte Carlo simulation design, and psychometric theory. These methods are not siloed; they often combine synergistically to address complex research questions. Statistical computing undergirds this work, with most of my methodological developments implemented in R packages (including MBESS, BUCCS, and SMRD) that make these tools accessible to applied researchers.

A unifying theme across my research is methodological cross-fertilization. Techniques developed in one discipline frequently remain unknown to adjacent fields facing similar analytical challenges. By working across traditional disciplinary boundaries, I identify opportunities to adapt and refine methods for new contexts, elevating methodological practice across multiple domains.

Collaboration

I collaborate extensively with applied researchers on projects ranging from focused investigator-initiated studies to large-scale federally funded initiatives. These partnerships provide opportunities to develop new methods in response to real analytical challenges and to apply existing techniques in novel contexts. If you believe my methodological expertise could advance your research, I welcome inquiries. While my capacity for new collaborations depends on current commitments and project fit, I’m particularly interested in partnerships that involve complex design questions, novel measurement challenges, or opportunities for methodological innovation.

Get Involved

Potential PhD students interested in working with me should learn more and consider applying to Notre Dame’s Analytics program. Doctoral students interested in methodological or applied research on generative AI in the context of human-centered outcomes are also welcome to contact me.