Skip to main content

Gregory P. Samsa

Professor of Biostatistics & Bioinformatics
Biostatistics & Bioinformatics, Division of Biostatistics
Duke Box 2721, Durham, NC 27710
2424 Erwin Road Ste 1105, 11045 Hock Plaza, Durham, NC 27705

Overview


Greg Samsa is an applied statistician whose primary interests are in study design, instrument development, information synthesis, practice improvement, effective communication of statistical results, and teaching. He is a believer in the power of statistical thinking, as broadly defined.

Current Appointments & Affiliations


Professor of Biostatistics & Bioinformatics · 2021 - Present Biostatistics & Bioinformatics, Division of Biostatistics, Biostatistics & Bioinformatics
Director, Research Integrity Office · 2016 - Present Biostatistics & Bioinformatics, Division of Biostatistics, Biostatistics & Bioinformatics
Member of the Duke Cancer Institute · 2013 - Present Duke Cancer Institute, Institutes and Centers

Recent Publications


A Case Where It Is Better to have an Unstandardized measure of the Right Construct than a Standardized Measure of a Related One: Application to Coding Interviews Within a Course in SAS Programming

Journal Article Journal of Curriculum and Teaching · November 1, 2025 Interview-based examinations provide richer data than formats such as multiple choice and short answer, albeit at the cost of being less standardized. This describes administering a coding interview as the final examination in a class on SAS programming, p ... Full text Cite

Fabrication in a study about honesty: A lost episode of columbo illustrating how forensic statistics is performed.

Journal Article Account Res · October 2025 The three steps of a typical forensic statistical analysis are (1) verify that the raw data file is correct; (2) verify that the statistical analysis file derived from the raw data file is correct; and (3) verify that the statistical analyses are appropria ... Full text Link to item Cite

Feasibility of an Intervention to Support Shared Decision-Making for Critically Ill Infants.

Journal Article J Pediatr · August 2025 OBJECTIVE: To develop and pilot an intervention to support communication and decision-making for critically ill infants. STUDY DESIGN: In this single-arm, mixed-methods, prospective, feasibility study, we enrolled infants, parents, and clinicians at a sing ... Full text Link to item Cite
View All Publications

Recent Grants


2/3 CTSA K12 Program at Duke University

ResearchMentor · Awarded by National Institutes of Health · 2025 - 2030

View All Grants

Education, Training & Certifications


University of North Carolina, Chapel Hill · 1988 Ph.D.