Health Services Data Science Associate

The Palo Alto Veterans Institute for Research (PAVIR) is seeking a Health Services Data Science Associate to lead and coordinate data management, data exploration and visualization, as well as data analyses across the nationally distributed, cross-functional team. This position will build capacities for data analyses among health care professionals and facilitate data based decision-making among diverse VHA stakeholders. In addition, the Data Science Associate will establish data cleaning and coding processes, and lead team statistical analyses for grant submissions and peer-reviewed journal articles.

The Health Services Data Science Associate will play a key role in developing the data management and analysis infrastructure to support our growing cross-national team. The role includes data management and database programming (i.e., SQL) and data exploration and statistical analyses (i.e., R). The successful Data Science Associate has a strong desire to optimize coding, programming, data management and analysis processes in a transparent, collaborative and reproducible workflow.

The Health Services Data Science Associate position is part of Team Participatory System Dynamics (PSD), which is working to change the way health care quality improvement decisions are made across all layers of the largest integrated health care system in the United States – the Veterans Health Administration (VHA).

The competitive candidate will have strong data science capabilities, including the ability to assess and act quickly on requests from team members and stakeholders to keep several data management and analysis tasks progressing simultaneously. This is an excellent opportunity for an individual who is interested in developing skills at the cutting edge of social, technological, and data based innovations to improve the quality of health care systems. This position is located at the VHA Menlo Park, CA campus in the National Center for PTSD, Dissemination and Training Division (NCPTSD).

This is a regular, full time (40 hours/week), exempt position.

PAVIR is a nonprofit foundation affiliated with the Veterans Affairs Palo Alto Health Care System (VAPAHCS). As a condition of employment, all PAVIR employees are required to have an approved appointment with VAPAHCS and complete a background check before they can commence work.

Teamwork and Collaboration:
•    coordinate effectively with programmers, engineers, project co-investigators and mentees to meet project goals
•    develop data and code management and documentation protocols to ensure high-quality, transparent and reproducible code for use by a variety of colleagues and VHA stakeholders, including the public
•    conduct analyses independently, yet solicit input and make adjustments based on input from team members; produce analyses for iterative improvement based on stakeholder feedback
•    review analyses and provide recommendations for analyses completed by other team members
•    participate in system design, decisions and code reviews
•    provide support and guidance for project work conducted by external consultants
Data Management/Database Programming:
•    work effectively with VHA data warehouse, an enterprise-wide SQL database; create and maintain databases from multiple primary and/or secondary sources
•    identify and understand documentation and definitions for existing VHA SQL databases using online documentation and through the establishment of effective working relationships with VHA colleagues via in person and online interactions
•    develop and maintain data systems and databases for research projects that comply with administrative policies, procedures and requirements of the VA Palo Alto, Stanford and other institutional review boards (IRBs), the VHA Office of Research Oversight (ORO), and the data security guidelines and policies of the VHA Office of Information Technology
•    define and extract data from the VHA corporate data warehouse in support of Team PSD researchers
Developmental Data Work:
•    develop research proposals, including power and sample size calculations for large multi-site trials
•    conduct literature reviews to provide citations and justification for analyses within relevant fields
•    develop, submit and update data protocols to VA Palo Alto, Stanford and other institutional review boards (IRBs)
Data Exploration and Visualization:
•    evaluate the reliability of source information, adjust and weight raw data
•    create figures and tables that are accessible, communicate insights and contextualize data
•    design, develop and deploy routinized programs for sustainable and scalable data visualization and analyses based on input and consultation from team members and frontline VHA stakeholders
•    prepare and organize graphic, tabular and written/narrative summaries of exploratory analyses and statistical analyses for team meetings, reports for distribution to VHA leadership and frontline staff, grant applications, and scientific manuscripts
•    develop complex, sophisticated, accurate programs in R
•    run tests and check validity of data and programs through use of frequencies, listings, summaries, and calculation of meaningful data metrics, as well as through package and code checking tools (e.g., devtools and testthat in R)
Data Analysis:
•    plan, execute and interpret data analyses, primarily in R; find the best, innovative quantitative ways to analyze novel data
•    select the appropriate statistical techniques needed to analyze study data and test hypotheses
•    conduct univariate and multivariate regression analyses including, Poission/Negative binomial, logistic, survival and multilevel/mixed-effect models
•    power analyses for multi-site implementation studies
•    evaluate missing data and impute missing values
•    Bayesian growth curve modeling to quantify the degree of uncertainty in key parameter estimates, obtaining probabilities for parameters that would benefit from additional exploration
•    time-series and integrated moving average (ARIMA) models to detect and correct for autocorrelation-biased residuals in time-series observations
•    statistical process control for non-normal data and small, unbalanced samples (i.e., p-charts and X-bar r charts)
Data Communication/Dissemination:
•    draft, proofread and/or edit research materials; recommendations to team members regarding the clarity, organization and layout
•    prepare presentations (poster and slide deck) for professional meetings, principally in rMarkdown and associated packages
•    co-author manuscripts and publications with a reproducibility workflow (e.g., rMarkdown, Github)
•    develop interactive web-based data visualizations using shiny or other R packages
•    provide leadership in designing and implementing data infrastructure for a scaling project
•    share data and code as appropriate via online repositories.


• Required: Bachelor Degree in quantitative discipline, e.g., statistics, computer science, information science, public health, economics or related discipline (or equivalent combination of education, training and experience)
• Desired: Master’s or Ph.D. in quantitative discipline, e.g., statistics, computer science, information science, public health, economics or related discipline.

• Required: 2 years or more of R programming experience; SQL programming expertise; experience working with large data sets.
• Desired: 2-3 years experience in mathematics, statistics, biostatistics, epidemiology, psychometrics, econometrics or related area. Background in health services research, public health or health economics with graduate-level training in research methods and statistics. Experience completing data analysis for peer-reviewed manuscripts and federal grant applications.

Knowledge / Skills / Abilities:
•    Excellent R programming skills across a wide range of packages; skill with other statistical software or programming languages is a strength, but is not required
•    Experience with SQL databases; experience with the VHA corporate data warehouse desired, but not required
•    Record of developing or participating in successful, extramurally-funded research, or have the training, commensurate experience and interest in developing a successful research trajectory
•    Effective collaborator and contributor to multidisciplinary and interdisciplinary teams
•    Excellent interpersonal and communications skills in both written and spoken English
•    Demonstrated commitment to complete projects
•    Demonstrated willingness to both teach others and learn new techniques
•    Prior experience managing/leading a data project
•    Detail‐oriented, strong programming and quantitative skills.

Environmental Conditions / Physical Demands:
Physical: Sitting in front of a computer for long periods of time, repetitive movement, etc.
Environmental: Exposure to office equipment and office environment.

PAVIR engages in nonprofit medical research and works with sponsors and the Veterans Affairs Palo Alto Health Care System (VAPAHCS) in administering funds for conducting research to find new and improved ways to combat human disease and help people with disabilities. Please refer to our website for additional information:

PAVIR is pleased to be an Equal Opportunity Employer for Minorities, Females, Protected Veterans, and Qualified Individuals with a Disability. If you need special assistance or an accommodation to apply for a posted position, please contact – Human Resources department.

How to Apply:
Please apply online for job code ‘ZIM1701.17’ via our Jobs page (, and include your cover letter and your resume/curriculum vitae as ONE document.

Health Services Data Science Associate

Leave a Reply

Scroll to top
Privacy Policy