Center for Targeted Machine Learning and Causal Inference

Advance methodological innovation

Develop cutting-edge statistical and machine-learning methods for causal inference that handle randomized trials and observational data in complex settings (e.g., time-varying exposures, clustered data).

Promote rigorous, transparent, reproducible science

Foster standards of transparency (e.g., Causal Roadmap, open-source software, reproducible code) and robustness in empirical work to ensure credible findings and decision-making.

Translate methodology into real-world impact

Apply advanced methods to pressing health and policy challenges (infectious and non-communicable diseases, global health equity, precision health) and partner with stakeholders (industry, regulators, global initiatives) to ensure that methodological advances inform practice.

Build capacity and train the next generation

Provide high-quality training, workshops, seminars, and resources for students, post-docs, practitioners, and collaborators so that the community is equipped to apply and extend modern causal Al methods.

Foster interdisciplinary and collaborative research

Create and sustain partnerships across disciplines (biostatistics, epidemiology, computer science, domain health sciences), across institutions (national and international), and between academia, industry, and regulatory agencies.

Ensure broad dissemination and implementation

Publish open-source software and tools, share best-practice guidelines, conduct workshops/webinars, and promote adoption of methods in practical settings (trials, observational studies, regulatory submissions).

Promote equity, domestic and global health, and policy relevance

Prioritize work that addresses disparities, global health contexts (e.g., low-resource settings), and evidence generation for policy or regulatory decision-making, thereby maximizing societal impact.