Peter M Steiner

Peter M. Steiner is a Professor in the Department of Human Development and Quantitative Methodology at the University of Maryland, specializing in quantitative methodology, measurement, and statistics (QMMS). He previously held faculty positions at the University of Wisconsin-Madison (2010–2019), the Institute for Policy Research at Northwestern University (2007–2010), and the Institute for Advanced Studies in Vienna (1997–2007). He earned a Ph.D. and M.Sc. in Statistics from the University of Vienna and an M.Sc. in Economics from Vienna University of Economics and Business.

His research focuses on causal inference methodologies, including causal replication designs, quasi-experimental techniques, and factorial survey methods. Key areas include double robust estimation, propensity score analysis, mediation analysis, and addressing selection bias. He has contributed to improving replication practices in social sciences and developed frameworks for assessing correspondence between experimental and non-experimental results.

• Education:
  • Ph.D. in Statistics, University of Vienna
  • M.Sc. in Economics, Vienna University of Economics and Business
  • M.Sc. in Statistics, University of Vienna

He received the prestigious Causality in Statistics Education Award from the American Statistical Association in 2019. His work emphasizes methodological rigor in evaluating policy interventions and experimental designs, with applications in education and social sciences. Courses taught include Graphical Models for Causal Inference, Causal Inference & Evaluation, and Causal Mediation Analysis.

• Key Contributions:
  • Pioneered within-study comparison designs for causal replication
  • Developed DAG-based causal modeling frameworks
  • Advanced multilevel propensity score methods

His research portfolio includes over 50 peer-reviewed articles in top journals like Psychological Methods, Journal of the American Statistical Association, and Sociological Methods & Research. Current projects focus on integrating machine learning with causal inference and improving reproducibility in social science research.