Core C: Statistics and Informatics Core (2.0)

Researchers

  1. Kevin Delucchi, PhD
  2. Stuart Gansky, MS, DrPH
  3. Jing Cheng, MD, MS, PhD
Research Fields: 
Regulatory Science

The Statistics and Informatics Core of this UCSF TCORS Center will provide full and ongoing support for all statistical analysis and data management activities of the Center. This Core will continue to facilitate the UCSF TCORS’ tradition of a cohesive approach to tobacco regulatory science and will help achieve the center’s integrated theme of combining health effects, behavior, and impact analysis to provide actionable information for regulation of and public communications about current and emerging tobacco products.  This Core will achieve these goals by accomplishing two Specific Aims:

(1) Provide quantitative support through research planning, support for data management, and biostatistical advice and analysis to all projects

(2) Provide training, support and resources for collaboration and data sharing

This Core will be engaged in all five of the Center projects, the Rapid Response Projects, Developmental Pilot Projects, and trainees in the Career Enhancement Core. We will collaborate with each project team to ensure the study is properly designed, conduct sample size and power analyses, help develop measures, create randomization schedules when applicable, and develop analysis plans. This Core will contribute to the career enhancement of young investigators needing statistical advice or support with their projects. We will leverage our experience in tobacco research and data systems to collaborate with the project teams on secure data acquisition, assuring data quality, monitoring project progress, finalizing analysis-ready data sets, and performing biostatistical analysis for projects. We will coordinate and manage requests for data sharing. This Core will also train project team members to use the secured data system for data acquisition and management, build and use a secured website for the distribution of study documents, and de-identify data sets and make them publicly available for data sharing via UCSF DataShare.