The Biostatistics Group provides statistical collaboration with investigators in Duke Anesthesiology for research projects in the areas of clinical, genomic and basic science research. We play a critical role in many key areas of a research project, including study design, data management, data analysis, scientific interpretation of the results, and preparation of the manuscript for publication. We also participate in the development of study protocols and grant proposals by helping investigators formulate research ideas, analytic strategies and power estimates for achieving study objectives. Our mission is to promote research of the highest quality by encouraging application of sound statistical principles, conducting accurate and reproducible data analysis, and developing productive collaborations with investigators and all other members of the research team. We encourage investigators in Duke Anesthesiology to schedule an initial meeting during the project planning stage, preferably before the collection of the data, so that statistical consideration can be taken into account early on. We also strongly encourage investigators to have their data ready for analysis at least four weeks before any deadline, if applicable.

Statisticians and Expertise

Our statisticians provide expertise on many aspects of statistical study design and analysis that are crucial to the success of a research project. Our team has extensive experience in analyzing clinical, genomic and basic science data using a wide array of contemporary analysis methods involving statistical modeling, hypothesis testing and parameter estimation. Most importantly, our statisticians are familiar to the clinical terminology and types of data often used in the anesthesiology research domain.

The Biostatistics Group is directed by Dr. Yi-Ju Li, whose research areas are in statistical method development and applications for genomic studies of human complex diseases. Throughout her academic career, she has also worked on many clinical projects that are more biostatistics-centered. In addition to her leadership role in the group, she leads the genetic/genomic projects in our group with the assistance from Ms. Jane La, Ms. Mary Cooter, Mr. Matthew Fuller, and Ms. Morgan Rosser who are biostatisticians in the group and provide statistical support for the clinical projects.

Cooter Wright and Rosser received their master’s degrees in biostatistics and Fuller and La received their master’s degree in statistics. They provide strong foundations in theoretical and applied statistical methods. Cooter Wright has multiple years of experience in applied research of clinical outcomes modeling, longitudinal and correlated data methods, and methods for observational studies. Fuller’s training has covered classical statistical theory and modern statistical methods for high-dimensional data, including machine learning for data science applications. Rosser was trained in the classic statistical application for clinical and public health-related research. She has experience with correlated data analysis, predictive modeling of clinical outcomes, bioinformatics, and big data analysis. La has training in statistical methods and computational statistics. She has experience in processing and analyzing large clinical and genetic datasets. She spends a portion of her time assisting with Anesthesiology projects.

What We Offer

• Provide office hours for initial consultation, preferably during the study planning stage or prior to data collection.
• Provide expertise in all aspects of study design, power calculation, database development, and statistical analysis planning.
• Participate in protocol development for IRB submission.
• Collaborate in grant proposal development for grant submission.
• Outline statistical analysis plan (SAP) for transparency and documentation of the analysis strategy.
• Collaborate in manuscript development and publication, particularly the description of statistical methods and presentation of the results.
• Collaborate in conference abstract/paper submission and presentation.
• Provide statistical education to clinical trainee and investigators through one-on-one exchanges during the work of each project, as well as statistical lectures to provided continuing education opportunities to all members of Duke Anesthesiology.
• Participate in Data Safety and Monitoring Boards for clinical trial study protocol within Duke Anesthesiology.

Research Program

Our members are closely connected with many clinical or basic research projects within Duke Anesthesiology. Effective collaboration requires critical evaluation and appropriate application of contemporary statistical methods. We emphasize constant learning of new statistical methodology and software, as well as new method development motivated by research projects we are involved. Areas of interest include applications of factor analysis to postoperative cognitive data, methods for missing data, survival analysis for time-to-event data, genetic association methods for common and rare variants for different phenotypes of interest, feature identification and classification in high-dimensional data, such as microarray and proteomic data.

Goals

The Biostatistics Group strives to promote a greater understanding of statistical principles and to conduct high-quality data management and analysis that lead to high-quality translational research at Duke. We will continue to improve the workflow on project prioritization and progress tracking, and continue to emphasize the documentation of our work to ensure the reproducibility of the data analysis. All final analysis data sets and computer scripts will be secured in a central location as the way of following the guideline of Duke’s translational medicine quality framework.

As research within Duke Anesthesiology advances, this group will continue to apply their complementary mix of quantitative skills and a strong commitment to effective collaboration to ensure the department’s statistical needs are met. We look forward to productive collaborations on challenging research initiatives.