Biological Data Scientist

University of Wisconsin Madison•Madison, WI

19h•Hybrid

About The Position

The University of Wisconsin–Madison is hiring a research data analyst for the Caunca Research Lab in the Department of Neurology. The role supports research on the epidemiology and biological drivers of vascular contributions to cognitive impairment and dementia, including work involving neuroimaging and blood-based biomarkers. The analyst will manage, coordinate, transform, analyze, and interpret data from multiple complex longitudinal cohort studies. Data sources may include surveys, laboratory assays, neuroimaging, geocoding, event data, and administrative linkages. The successful candidate will develop data management systems and code for merging, harmonizing, and analyzing complex, longitudinal, and multilevel data. The role involves using R, STATA, and/or SAS; applying established statistical methods; and supporting reproducibility through codebooks, reproducible code, code review, and publishable workflows. The analyst will oversee work by students and fellow staff, develop recommendations from research findings, contribute to independent and collaborative manuscripts and presentations, and help design analytic plans and future studies. The position may require some onsite work at a designated campus location, with some work permitted remotely. Applicants may be considered for Data Scientist I, II, or III, with the final title determined by the finalist’s experience and qualifications.

Requirements

Experience managing, analyzing, and interpreting research data from complex cohort studies using R and/or STATA and/or SAS.
Ability to manage and analyze data using established statistical methods, oversee analysis work by students and fellow staff, and develop recommendations based on research findings.
Ability to participate in preparing manuscripts and presentations for academic conferences and key stakeholders.
Ability to contribute to designing subsequent data-collection waves, including sampling strategies, survey instruments, and questionnaires.
Working knowledge of causal inference methods and/or prediction modeling.
Ability to communicate effectively in a team setting.
Ability to write reproducible code, conduct code review, and post code publicly for reproducibility.

Nice To Haves

At least 1–2 years of experience working in an epidemiology or biostatistics group.
For Data Scientist I or II: a master's degree in public health, biostatistics, and/or epidemiology is preferred.
For Data Scientist III: a PhD in public health, biostatistics, and/or epidemiology is preferred.
Experience or background in prediction modeling, machine learning, and high-dimensional data analysis.

Responsibilities

Implement appropriate data science techniques under the guidance of data scientists, statisticians, and/or researchers to identify data patterns and answer research questions, including through visualization, statistical analysis, machine learning, and data mining.
Document approaches used to address research questions.
Prepare datasets for analysis through cleaning and quality assurance, transformation, restructuring, and integration of multiple data sources.
Create reproducible workflows and reports that clearly communicate patterns to researchers and/or administrators.
Organize and automate project steps for data preparation and analysis.
Manage, coordinate, transform, analyze, and interpret data from complex longitudinal cohort studies.
Develop data management systems and code to merge, harmonize, and analyze complex data.
Oversee the work of students and fellow staff conducting or interpreting analyses.
Develop recommendations based on research findings.
Participate in preparing independent and collaborative manuscripts and presenting findings at academic conferences and to stakeholders, including community organizations.
Contribute to analytic plans and the design of future studies and subsequent waves of data collection, including sampling strategies, survey instruments, and questionnaires.