Research Data Analyst

Stanford Reglab; Palo Alto (CA); On-site; USD 90,000 - 150,000; Full time

Job summary

Stanford's Division of Clinical Informatics seeks a Research Data Analyst to contribute to clinically applied machine learning, foundation models, and multicenter studies. You will work with researchers, data scientists, and clinicians to prepare and analyze complex datasets, evaluate model performance, and generate insights for reproducible research.

The role involves building end-to-end analytical pipelines, data quality assessment, cohort development using OMOP CDM, and collaboration across

Qualifications

• Experience developing and implementing algorithms for processing large datasets.
• Background in computer science, engineering or a related field with strong statistics and research.
• Excellent project and time management skills with attention to detail.
• Ability to work collaboratively with stakeholders across a large institution.
• Outstanding problem solving and analytical skills; strong writing abilities for grants/papers.
• Proficiency in SQL, Python and shell scripting.

Responsibilities

• Collect, manage and clean datasets.
• Interpret, analyze, and visualize multivariate relationships in data.
• Develop algorithms and statistical models; perform analyses for reporting.
• Identify data quality issues and determine root causes.
• Create reports, charts and tables for investigators and publication.
• Collaborate with faculty and research staff on data collection and methods.
• Provide documentation based on audit criteria to investigators.

Skills

SQL

Python

Shell scripting

Statistics

Data visualization

Machine learning concepts

Education

Bachelor's degree

Tools

SQL

Python

Shell scripting

Job description

Situated in Stanford’s highly dynamic research environment, the Division of Clinical Informatics is seeking a Research Data Analyst to contribute to our research program focused on clinically applied machine learning, foundation models and multi-center observational studies. The successful candidate will work closely with researchers, data scientists and clinical/domain experts to prepare and analyze complex datasets, evaluate model performance, generate meaningful insights, and contribute to rigorous, reproducible research.

The job duties listed below are typical examples of work performed by positions in this job classification and are not designed to contain or be interpreted as a comprehensive inventory of all duties, tasks, and responsibilities. Specific duties and responsibilities may vary depending on department or program needs without changing the general nature and scope of the job or level of responsibility.

Duties include:

• Collect, manage and clean datasets.
• Employ new and existing tools to interpret, analyze, and visualize multivariate relationships in data.
• Develop algorithms and statistical models, and perform statistical analyses appropriate to data and reporting requirements.
• Use system reports and analyses to identify potentially problematic data and determine root cause for data problems
• Develop reports, charts, graphs and tables for use by investigators and for publication and presentation.
• Collaborate with faculty and research staff on data collection and analysis methods.
• Provide documentation based on audit and reporting criteria to investigators and research staff.
• Contribute to the development of a research program centered on machine learning with an initial focus on data from electronic health records
• Develop and evaluate machine learning models and reproducible end-to-end analytical pipelines using hospital data, including appropriate quality control and bias assessment
• Contribute technical expertise to program development activities, including research proposals, project planning, and stakeholder engagement.
• Coordinate and support knowledge sharing, documentation, and dissemination of methods and best practices within the research community
• Support single- and multicenter observational research using the OMOP Common Data Model, including cohort development, quality assessment, and reproducible analysis.

The ideal candidate for this position is an individual with knowledge of clinical data, sense of curiosity, attention to detail, quality analysis and validation methodologies, and strong interpersonal skills needed to work collaboratively with technical and non-technical stakeholders within and outside the Stanford research community, including faculty, researchers, clinicians, hospital administrators, engineering teams, IT staff and research coordinators.

What to expect during the interview process:

A typical interview process consists of resume screening, phone screenings, group and/or 1:1 interviews via zoom, reference and background checks. You may be required to demonstrate proof of programming and writing abilities. Interview candidates should expect to meet with other researchers, faculty, data scientists and software engineers.

Resources

1. Division of Clinical Informatics: https://med.stanford.edu/peds-clinical-informatics.html
2. Research IT Website: https://med.stanford.edu/sdsr/research-technology.html
3. STARR: https://starr.stanford.edu/
4. OHDSI CDM: https://www.ohdsi.org/data-standardization/the-common-data-%20model/

* - Other duties may also be assigned

DESIRED QUALIFICATIONS:

• Experience developing and implementing algorithms for the processing of large datasets.
• Background in computer science, engineering or a related field with a strong understanding of statistics and scientific research
• Excellent project and time management skills and strong attention to detail
• Ability to work collaboratively with stakeholders across a large institution
• Outstanding problem solving and analytical skills
• Excellent writing skills to help with development of grants and papers
• Proficiency in SQL, Python and shell scripting
• Ability to work independently and in a diverse team environment
• Excellent verbal and written communication skills along with strong interpersonal skills
• Demonstrated creativity and latitude in problem solving, including the ability to prioritize and execute multiple competing tasks

Manage and analyze large amounts of information, which is typically technical or scientific in nature including creating large and complex data sets, abstracting and formatting data, importing and exporting data between files, performing statistical analysis, and preparing reports and manuscripts for publication.

Core Duties

• Collect, manage and clean datasets.
• Employ new and existing tools to interpret, analyze, and visualize multivariate relationships in data.
• Create databases and reports, develop algorithms and statistical models, and perform statistical analyses appropriate to data and reporting requirements.
• Use system reports and analyses to identify potentially problematic data, make corrections, and determine root cause for data problems from input errors or inadequate field edits, and suggest possible solutions.
• Develop reports, charts, graphs and tables for use by investigators and for publication and presentation.
• Analyze data processes in documentation.
• Collaborate with faculty and research staff on data collection and analysis methods.
• Provide documentation based on audit and reporting criteria to investigators and research staff.
• Communicate with government officials, grant agencies and industry representatives.

Minimum Education

Bachelor's degree or a combination of education and relevant experience.

Minimum Experience

Experience in a quantitative discipline such as economics, finance, statistics or engineering.

Knowledge, Skills and Abilities

• Substantial experience with MS Office and analytical programs.
• Strong writing and analytical skills.
• Ability to prioritize workload.