Clinical Trials Tech University

Yawei Cheng

*********@*****.*** 806-***-****

Highland Ridge Ave, Gaithersburg, MD

SUMMARY

• 6+ years of experience in statistical analysis, data management, and biostatistics, with a strong focus on clinical trials and longitudinal data analysis.

• Proficient in advanced statistical programming and modeling, with a deep understanding of clinical trial design, epidemiology, and psychology research.

• Experienced in working with large datasets, managing clinical trials, and collaborating with multidisciplinary teams.

• Strong problem-solving abilities, multitasking skills, and a passion for contributing to research that advances mental health and suicide prevention.

• Excellent communicator, able to translate complex statistical concepts into actionable insights for both technical and non- technical audiences.

• Over 6 years of experience teaching undergraduate-level mathematics and statistics courses, demonstrating strong instructional skills and a commitment to fostering student success. EDUCATION

• PhD • Texas Tech University • Lubbock, TX • Mathematics (Statistics Focused) 08/2021 – 08/2023

• MS • Texas Tech University • Lubbock, TX • Statistics 08/2017 – 05/2021

• MS • Texas Tech University • Lubbock, TX • Petroleum Engineering 08/2013 – 05/2015

• BS • Chongqing University of Science & Technology • Chongqing, China • Petroleum Engineering 08/2009 – 06/2013 SKILLS

Programming

R, SAS (BASE, STAT, GRAPH, PROC SQL, MACRO), Python, Mplus, MATLAB, C++, SPSS Database Management

MS SQL, MySQL, PostgreSQL, REDCap, MS Access

Statistical Techniques

Clinical trial analysis, Longitudinal data analysis, Generalized Linear Modeling, Predictive Modeling, Bayesian analysis, Survival analysis, Regression analysis, Network analysis, Design of Experiments, Hypothesis testing, Multivariate analysis, Machine learning, Cluster analysis, Correlation analysis, Data pre-processing, Data visualization Data Management

Data Preprocessing, Data Cleaning, Data Visualization

WORK EXPERIENCE

Statistician (Texas Tech University, Lubbock, TX) 11/2023 – Current

• Developed and implemented Statistical Analysis Plans (SAPs) for randomized, double-blind, placebo-controlled clinical trials, ensuring compliance with study protocols and regulatory requirements.

• Defined primary and secondary endpoints, analysis populations (e.g., ITT, PP, Safety), and appropriate statistical methods

(e.g. Chi-square tests).

• Managed the handling of missing data using advanced imputation techniques such as multiple imputation to ensure robustness of analyses.

• Conducted sample size calculations and powered clinical trials based on specified hypotheses and assumptions, ensuring statistical rigor.

• Performed interim analyses using O'Brien-Fleming stopping rules to assess trial progression, making critical recommendations for study continuation.

• Created detailed statistical reports, tables, and figures for submission and internal review.

• Applied Latent Class Analysis (LCA) and Multinomial Logistic Regression to analyze categorical data, identifying distinct patterns of parental control. These patterns were significantly associated with health outcomes such as dietary knowledge and physical activity, offering insights into behavior trends using large nationally representative datasets.

• Developed and compared machine learning models to classify patterns of parental control in TV watching. The Latent Class Analysis (LCA) model demonstrated the best classification accuracy, outperforming other models in identifying distinct behavior patterns.

• Applied the robust maximum likelihood estimator (MLR) to conduct latent class analysis (LCA) on large categorical data, identifying four distinct patterns of parental control over time. These findings revealed significant associations between parental control, demographic factors, and adolescent health outcomes, contributing to policy recommendations for enhancing parental engagement in health programs.

• Checked the model adequacy of statistical analyses by employing techniques such as residual analysis, goodness-of-fit tests, and cross-validation. These methods ensured that the models, including regression and machine learning algorithms, met key assumptions and provided reliable, unbiased estimates, allowing for accurate predictions and valid interpretations of the results. RESEARCH EXPERIENCE

Research & Teaching Assistant (Texas Tech University, Lubbock, TX) 08/2017 – 08/2023

• Developed and validated machine learning models to predict outcomes from longitudinal health data, using techniques like latent growth curve modeling and network analysis.

• Conducted research on big-five personality traits and disordered eating, applying network analysis to identify key associations between variables, and used bootstrapping to ensure model stability.

• Created custom visualizations using ggplot2 and seaborn to present findings on health data, improving the clarity of complex statistical results for non-technical audiences.

• Applied latent profile analysis (LPA) to identify the latent subpopulations for elders’ cognitive function patterns

• Performed a latent transition analysis (LTA) to estimate the probabilities of transition for elders’ cognitive function patterns over time

• Used longitudinal mediation analysis by applying and comparing 4 cross-lagged panel models

• Applied multiple imputations for missing data to reduce the biases of selective attrition CERTIFICATIONS

Coursera

Clinical Trials Analysis, Monitoring, and Presentation Design and Interpretation of Clinical Trials

JOURNAL PUBLICATIONS

• Cheng, Y., Barnhart, W. R., Liang, G., Chen, G., Lu, T., & He, J. (2022). Appetitive traits and body mass index in Chinese adolescents: An 18-month longitudinal study with latent growth curve analyses. Obesity Research & Clinical Practice. http://doi.org/10.1016/j.orcp.2022.12.002

• Cheng, Y. & Liang, G., Barnhart, W. R., Chen, G., Lu, T., & He, J. (2023). A network analysis of disordered eating, big-five personality traits, and psychological distress in Chinese adults. International Journal of Eating Disorders. https://doi.org/10.1002/eat.24012

• Cheng, Y., Barnhart, W. R., Weng, H., Liang, G., Chen, G., Lu, T., & He, J. (2024). Patterns of Cognitive Functions in Chinese Older Adults and Associations with Demographics, Diet, and Lifestyle: Latent Class and Transition Analyses with Nationally Representative Data. (Under review)

• Cheng, Y., Barnhart, W. R., Weng, H., Liang, G., Chen, G., Lu, T., & He, J. (2024). Patterns of Parental Control in TV Watching in Chinese Adolescents and Associations with Demographics, Dietary Knowledge, and Physical Activity: Latent Class and Transition Analyses with Nationally Representative Data. (In preparation)

• Weng, H., Barnhart, W. R., Cheng, Y., Chen, G., Cui, T., Lu, T., & He, J. (2022). Exploring the bidirectional relationships among night eating, loss of control eating, and sleep quality in Chinese adolescents: A four-wave cross-lagged study. International Journal of Eating Disorders, 1-10. http://doi.org/10.1002/eat.23800

• Liang, G., Barnhart, W. R., Cheng, Y., Lu, T., & He, J. (2023). The Interplay among BMI, body dissatisfaction, body appreciation, and body image inflexibility in Chinese young adults: a network perspective. Journal of Contextual Behavioral Science. https://doi.org/10.1016/j.jcbs.2023.07.004

• Weng, H., Barnhart, W. R., Cheng, Y., Cui, T., Lu, T., & He, J. (2024). Latent dietary patterns and associations with cognitive functions and psychological and physical well-being in Chinese older adults: Latent profile and transition analyses with nationwide cohort panel data. (Under review)

Contact this candidate