Nandita Mitra

Nandita Mitra
  • Professor of Biostatistics
  • Professor of Statistics and Data Science

Contact Information

  • home Address:

    622 Blockley Hall, 423 Guardian Drive, Philadelphia, PA 19104

Research

Teaching

Past Courses

  • BSTA5110 - Biostats in Practice I

    Biostatistics in Practice offers Biostatistics students an opportunity to acquire and demonstrate proficiency in statistical collaboration, data analysis and scientific writing. The project is defined by several elements: A scientific question or hypothesis arising in medical research; the statistical methodology needed to address the question; the development of a study design and/or analysis of a relevant data set; and a summary of the results of these analyses. In most cases, a collaborating medical scientist provides the research question and the data. The student, under the supervision of a biostatistics faculty member, identifies the appropriate statistical methods and conducts the analysis. The analysis should be sufficiently extensive and detailed to support a manuscript publishable in the medical literature. Enrollment open to Biostatistics student only.

  • BSTA6990 - Lab Rotation

    Student lab rotation.

  • BSTA7000 - Ideas & Controversies in Stats

    This graduate-level seminar explores the driving forces behind modern statistical thought by engaging directly with foundational papers and debates that have shaped the field. Anchored in Roderick Little’s Seminal Ideas and Controversies in Statistics, the course emphasizes conceptual understanding and historical context rather than formal proofs. Three central themes structure the semester: 1. Philosophical Foundations of Inference • Likelihood principle • Bayesian vs. frequentist paradigms • Fisher’s fiducial inference • Hypothesis testing debates (Fisher vs. Neyman–Pearson) 2. Methodological Developments • Regression and shrinkage estimation • Multiple comparisons • Robust inference methods 3. Statistical Design & Randomization • Experimental design foundations • Randomization as the basis of inference • Modern perspectives on causal estimation Students will analyze seminal and modern papers, present key controversies, and articulate their relevance to contemporary statistical practice. Recommended Prerequisites: Graduate-level courses in probability, statistical inference, and regression.

  • BSTA7900 - Causal Inf in Biomed Res

    This course considers approaches to defining and estimating causal effects in various settings. The potential-outcomes approach provides the framework for the concepts of causality developed here, although we will briefly consider alternatives. Topics considered include: the definition of effects of scalar or point treatments; nonparametric bounds on effects; identifying assumptions and estimation in simple randomized trials and observational studies; alternative methods of inference and controlling confounding; propensity scores; sensitivity analysis for unmeasured confounding; graphical models; instrumental variables estimation; joint effects of multiple treatments; direct and indirect effects; intermediate variables and effect modification; randomized trials with simple noncompliance; principal stratification; effects of time-varying treatments; time-varying confounding in observational studies and randomized trials; nonparametric inference for joint effects of treatments; marginal structural models; and structural nested models. Prerequisite: If course requirement not met, permission of instructor required.

  • BSTA8990 - Pre-Dissertation Lab Rot

  • BSTA9950 - Dissertation

    Ph.D. students enroll in this course after passing their candidacy exam. They work on their dissertation full-time under the guidance of their dissertation supervisor and other members of their dissertation committee.

  • HPR6080 - App Reg Hlth Pol Res

    This course deals with the work-horse of quantitative research in health policy research--the single outcome, multiple predictor regression model. Students will learn how to 1) select an appropriate regression model for a given set of research questions/hypotheses, 2) assess how adequately a given model fits a particular set of observed data, and 3) how to correctly interpret the results from the model fitting procedure. After a brief review of fundamental statistical concepts, we will cover analysis of variance, ordinary least squares, and regression models for categorical outcomes, time to event data, longitudinal and clustered data. We will also introduce the concepts of mediation, interaction, confounding and causal inference. Prerequisite: Permission needed from Instructor.

  • HPR9900 - Hpr Thesis I

    Each student completes a mentored research project that includes a thesis proposal and a thesis committee and results in a publishable scholarly product. Prerequisite: Course only open to Masters of Science in Health Policy Research students.

  • HPR9901 - Hpr Thesis II

    Each student completes a mentored research project that includes a thesis proposal and a thesis committee and results in a publishable scholarly product. Prerequisite: Course only open to Masters of Science in Health Policy Research students.

In the News

Knowledge @ Wharton

Activity

Latest Research

Dane Isenberg, Edward Kennedy, Richard Landis, Nandita Mitra, James M. Robins, Jason Roy, Alisa J. Stephens-Shields, Wei Yang, Dylan Small (2024), Marshall Joffe’s Contributions to Causal Inference, Biostatistics, and Epidemiology, American Journal of Epidemiology , 193 (4), pp. 563-576.
All Research

In the News

How AG1 Built Trust Through Podcast Marketing

Paulie Dery, chief marketing officer at AG1, on turning trusted podcast voices into lasting brand growth.…Read More

Knowledge @ Wharton - 2026/07/16
All News