Remote job
Real World Biostatistician - RWA CMH experience (hiring in Canada and US)
Job details
About this role
Role overview
This Biostatistician role focuses on real-world evidence (RWE) generation across multiple therapeutic areas, supporting clinical development, HEOR, regulatory strategy, and market access initiatives. The position designs and analyzes observational studies using electronic medical records (EMR) and claims data, applying advanced statistical methods including causal inference and trial emulation. The role is open to candidates based in Canada and the US.
Responsibilities
- Design and execute real-world evidence studies using EMR and claims data, including data specifications, statistical analysis plans, and protocols - Apply causal inference methods such as propensity score methods, weighting, matching, GLM/GLMM, MMRM, survival analysis, and random forest - Develop external control arms and borrowing strategies, including trial emulation frameworks - Conduct sample size estimation and power calculations for observational and hybrid study designs - Perform analyses using healthcare coding systems including ICD and NDC - Collaborate cross-functionally with HEOR, market access, regulatory, and clinical development stakeholders - Translate complex analytical results into clear, actionable insights for decision-makers
Requirements
- M.S. or Ph.D. in Biostatistics, Statistics, Epidemiology, or related field - 5+ years of experience in RWE/RWD analytics in industry or an equivalent setting - Strong experience with EMR and/or claims data - Proficiency in healthcare coding systems such as ICD and NDC - Programming expertise in at least one of SAS, R, or Python - Working knowledge of SQL logic and OMOP data structures - Solid understanding of causal inference methods and observational study design
Nice to have
- Ph.D. strongly preferred - Therapeutic area experience in diabetes, cardiovascular disease, or metabolic disorders - Familiarity with trial emulation methodologies and external control borrowing / hybrid designs - Basic machine learning methods applied to RWD - Experience working across multiple common data models such as OMOP, Sentinel, or PCORnet