Lead Data Scientist, Causal Inference & Clinical Outcomes
New
J
JobgetherHealthcare analytics
Fully remote position within the United States.ContractLead
Salary150 USD per hour
Apply NowOpens the employer's application page
Job Details
- Experience
- Extensive professional experience in data science, biostatistics, epidemiology, health economics, or clinical outcomes research.
- Required Skills
- PythonSQLR
Requirements
- Advanced degree in Statistics, Data Science, Biostatistics, Epidemiology, Health Economics, or a closely related quantitative discipline.
- Extensive professional experience in data science, biostatistics, epidemiology, health economics, or clinical outcomes research.
- Demonstrated expertise in causal inference and observational study design.
- Experience evaluating healthcare interventions and measuring clinical outcomes.
- Strong proficiency in Python, R, and SQL.
- Experience working with large-scale healthcare claims and EHR datasets.
- Deep understanding of propensity score matching, quasi-experimental research methods, statistical validation, and confounding adjustment.
- Ability to independently design and execute technically sophisticated analytical studies.
- Experience developing statistical methodologies for clinical, actuarial, or external stakeholder review.
- Knowledge of healthcare data privacy, HIPAA, and protected health information requirements.
- Preferred: Experience evaluating chronic care management, population health, value-based care, or Medicare-related programs.
- Preferred: Familiarity with APCM, CCM, healthcare reimbursement models, dbt, Amazon Redshift, or Looker.
Responsibilities
- Design and lead longitudinal, quasi-experimental clinical outcomes studies.
- Evaluate APCM and CCM program effectiveness using healthcare claims and EHR data.
- Define patient cohorts, comparison groups, outcome measures, and analytical frameworks.
- Measure hospitalization, readmission, post-discharge follow-up, and other clinical and financial outcomes.
- Apply causal inference methods, including propensity score matching, inverse probability weighting, and difference-in-differences.
- Address confounding variables, selection bias, and limitations in observational healthcare data.
- Build and maintain analytical workflows using Python, R, and SQL.
- Collaborate with BI, clinical, actuarial, and healthcare client teams on methodologies and outcome measures.
- Prepare executive-ready presentations, research reports, and supporting documentation.
- Review prior vendor deliverables and transfer relevant research knowledge to the internal BI team.
View Full Description & ApplyYou'll be redirected to the employer's site
