Research Specialist Intermediate

University of Virginia:
Research Specialist Intermediate - Charlottesville, VA Responsibilities

• Play a key role in advancing cancer-related population health research within the Population Health and Cancer Outcomes Core (PHCOC).
• Support the Core Director and Lead Statistician in producing analytical reports on cancer incidence, mortality, treatment patterns and outcomes using large scale state and national databases to inform clinical practice, population health strategy and public health policy.
• Responsible for full data lifecycle - from data acquisition and preprocessing to statistical modeling, visualization and reporting of results.
• Teach and share analytical knowledge and best practices with the broader university research community.
• Extract and clean data from large-scale cancer-related administrative and clinical databases, including SEER‑Medicare, state cancer registries, the Virginia All-Payer Claims Database (APCD), and Electronic Health Record (EHR) data.
• Generate analytical patient cohorts using SQL in virtual machine and cloud computing environments.
• Conduct advanced statistical analyses, including linear and logistic regression, survival analysis, Cox proportional hazards modeling, propensity score matching, Blinder‑Oaxaca decomposition, longitudinal data analysis, and econometric modeling to examine cancer outcomes and disparities in cancer care.
• Utilize statistical software packages such as SAS, Stata, R, and Python to perform data analysis.
• Apply machine learning and artificial intelligence tools to identify predictive factors and optimize analytic performance.
• Assist in the preparation of administrative and compliance documents required for database access and data use agreements.
• Perform geospatial analyses to assess geographic variation in cancer burden, healthcare access, and outcomes, using tools such as ArcGIS.
• Create data visualizations, dashboards, and infographics to communicate findings, using tools such as Tableau, Canva, Lucidchart, and Microsoft PowerPoint.
• Prepare publication-ready written and graphical outputs for manuscripts, reports, and conference presentations.
• Collaborate with faculty, clinicians, and researchers to interpret statistical findings and translate analytical results into actionable insights for research and policy.
• Contribute to the development and implementation of standardized analytic workflows and reproducible data pipelines for quality assurance and reproducibility.
• Lead teaching workshops throughout the year to train students and staff in working with healthcare claims and population datasets.

Bachelor's degree in statistics, biostatistics, data science, economics, public policy or a closely related quantitative field along with a minimum of 3 years of relevant quantitative data modelling experience. OR Master’s degree in statistics, biostatistics, data science, economics, public policy or a closely related quantitative field will be accepted in lieu of experience.

• Data management, data cleaning, and preprocessing to conduct rigorous statistical analysis and interpretation
• Advanced statistical methodologies, including linear and logistic regression, longitudinal data analysis, and econometric modeling
• Statistical programming for large datasets using software such as SAS, Stata, R, and Python
• Extracting and querying large-scale datasets using SQL in both local and cloud environments
• Applied machine learning and artificial intelligence tools to identify predictive factors and improve analytic performance
• Batch processing and data science workflows for efficient handling of large scale datasets
• Working with community-level and population-based data sources, including the American Community Survey (ACS)
• Working within virtual machine and cloud-based environments for data processing and analysis
• Spatial data analysis using ArcGIS or related GIS tools
• Creating data visualizations, dashboards, and infographics using software such as Tableau, R, or Python
• Developing standardized analytical workflows, reproducible data pipelines, technical documentation and using version control tools such as Git
• Managing multiple projects simultaneously,…