Shelby J. Haberman

Princeton University, Washington University in St. Louis, University of Chicago

Papers

Total Citations

H-Index

About

Shelby J. Haberman is a pioneering figure in the development of log-linear models and the analysis of categorical data, with foundational contributions that have shaped modern statistical methodology. His work on the analysis of residuals in contingency tables and the theory of generalized linear models has provided essential tools for researchers across the social and biological sciences. While his early papers on "robot data screening" (1966–1970) introduced automated search techniques for multivariate problems, amassing a combined 26 citations, his most enduring impact lies in his later theoretical advancements, including the Haberman residuals—a standard diagnostic for assessing model fit in categorical data analysis. His 1978 monograph, *Analysis of Qualitative Data*, remains a seminal reference, and his contributions to the theory of exponential families and maximum likelihood estimation have been cited over 2,000 times collectively. A Fellow of the American Statistical Association and the Institute of Mathematical Statistics, Haberman’s rigorous yet accessible work continues to guide students and researchers in navigating complex multivariate datasets with precision and insight.