Columbia University

What you'll study

The programme combines core theoretical statistics with specialised biostatistical methods and interdisciplinary collaborations. Early coursework typically covers measure-theoretic probability, statistical inference, asymptotic theory, linear models and computational statistics. Biostatistics-specific subjects include survival analysis, longitudinal and correlated data, clinical trials design and analysis, causal inference, statistical genetics, high-dimensional data analysis and Bayesian methods for biomedical applications.

Training emphasises both theory and computation: students learn modern computational approaches (MCMC, variational methods, scalable algorithms) and applied tools (R, Python, specialized bioinformatics software). Course work is complemented by seminars, reading courses and rotations that expose students to applied problems in epidemiology, genomics, imaging and clinical trials.

Programme structure typically involves a period of formal coursework and teaching/mentoring experience, qualifying or comprehensive examinations to assess readiness for research, a period of supervised research leading to a dissertation, and participation in departmental and cross‑school seminars and journal clubs. Students often collaborate closely with faculty in Columbia’s Department of Statistics, the Mailman School of Public Health (Biostatistics), the Columbia University Irving Medical Center and affiliated research centres.

Entry requirements

Applicants are expected to have a strong background in mathematics and statistics. Typical preparation includes advanced calculus, linear algebra, multivariable probability, mathematical statistics and experience with statistical computing. A bachelor’s degree with substantial quantitative coursework is the minimum; many successful applicants hold a master’s degree in statistics, biostatistics, mathematics or a related discipline.

Application materials normally include academic transcripts, a statement of purpose describing research interests (with emphasis on biostatistics applications if relevant), a curriculum vitae, and two or three letters of recommendation that can speak to quantitative and research ability. Prior research experience or demonstrated potential for independent research strengthens an application. International applicants must demonstrate English language proficiency according to Columbia’s general admissions policies.

Career prospects

Graduates of a PhD in Statistics with biostatistics focus move into research‑oriented careers across academia, clinical and translational research, pharmaceutical and biotech companies, public health agencies, and data‑driven roles in industry. Common roles include tenure‑track faculty in statistics or biostatistics, statistical scientists in clinical trials and regulatory science, quantitative analysts in genomics and precision medicine, and senior data scientist positions that require expertise in causal inference, high‑dimensional modelling and Bayesian computation.

Alumni also find positions in government research labs, international health organisations and private research institutes where advanced statistical methodology is applied to epidemiology, health policy, imaging and multi‑omics data integration.

Why study at Columbia University

Columbia offers distinctive interdisciplinary strengths: statisticians work closely with the Mailman School of Public Health, Columbia University Irving Medical Center and a broad network of biomedical research groups. This creates abundant opportunities for applied collaborations in clinical trials, epidemiology, genomics and imaging.

The Department and affiliated units host regular seminars, workshops and reading groups that expose students to leading research and visiting scholars. Students benefit from access to extensive computing resources, large biomedical data sets, and the research ecosystem of New York City, including industry partners and research hospitals.

Faculty at Columbia include researchers active in both theoretical statistics and applied biostatistics, offering supervision across a wide range of topics from methodological foundations to translational biomedical applications. The programme supports students’ development as independent researchers prepared for leadership roles in academia, healthcare research and industry.