Biostatistics and Data Research Lab

The BDRL has established successful and long-term collaborations with multiple faculty members within and outside the CNRC, contributing to study design, analysis plans, and power calculations. These efforts include critical thinking activities that have resulted in successful funding for a variety of grant mechanisms.

The BDRL provides high-quality analytical and methodological support to investigators interested in basic, clinical, and epidemiological research projects. A significant portion of the lab’s work focuses on diet, environmental, and molecular factors that impact chronic diseases including obesity, diabetes, cancer, and bone disorders, and how social drivers of health can moderate these factors. The lab can assist with statistical planning for postdoctoral fellowships, Data Safety and Monitoring Boards and manuscripts. Its expertise spans multiple analytic methods with a special interest in longitudinal designs, hierarchical modeling, and simulations of complex models. While primarily serving CNRC, BCM, and Texas Children’s Hospital, the BDRL occasionally collaborates with external investigators and trainees.

The lab collaborates with research teams on designing questionnaires and assessment tools to ensure high-quality, reliable data capture. Services include designing REDCap databases for project screening forms, surveys, and health-related data collection, building data analysis specifications, and conducting data quality control checks to prepare analysis-ready datasets. The BDRL also processes publicly available data or collaborates to transfer and summarize data, generating descriptive statistics and charts. In the discipline of biostatistics, these steps optimize the effective use of data and provide a critical foundation for answering research questions.

In addition to its core research and analytic activities, the Biostatistics and Data Research Lab is committed to advancing rigor, reproducibility, and transparency (RRT) across its many research activities. The lab supports the preparation of National Institutes of Health and other funding proposals by addressing the rigor of prior research, embedding rigorous research practices within the research strategy, and detailing assurances for how proposed studies will produce robust and unbiased results. Lab members maintain and continually refine reproducible coding practices, staying current with emerging tools and techniques to enhance computational reproducibility in all analytic work. The lab also assists internal investigators with critical review of and computational reproducibility analyses of published studies, helping to verify and strengthen the evidence base that informs ongoing and future research. Looking ahead, the lab plans to further support RRT efforts possibly through targeted training and workshops and the development of internal standard operating procedures for analytic reproducibility.

The team conducts literature reviews based on the latest guidance and appropriate databases such as PubMed, Embase, and other research repositories. These reviews allow the lab to stay current on hot topics like AI/ML, obesity prediction, and methods development. This effort enhances contributions to publications and grants while providing the preliminary data essential for proposals.

Each project concludes with a comprehensive report containing narratives, tables, and charts. The team assists with creating table shells, checking narrative content for methodological accuracy, ensuring results are correctly interpreted, and identifying errors in formatting or typing. These reports serve as key productivity milestones and deliverables. Additionally, the lab generates productivity reports that document project distribution, collaborator demographics, end-of-study satisfaction scores, and subject areas to ensure sustainability and quality improvement.

The BDRL is committed to educating and assisting faculty, staff, and fellows in biostatistics and software training. The lab is equipped with state-of-the-art computing and analytical tools, including SAS, SPSS, Mplus, Python, and R. It maintains an inventory of relevant literature, workshops, training sessions, and webinars to advance team knowledge and technical skills. These resources are leveraged for training and one-on-one mentoring, ensuring the continuous development of faculty and trainees.