Mingze Zhang
About Mingze Zhang
Mingze Zhang is a Teaching and Research Assistant at The George Washington University, where he has worked since 2017. He has made significant contributions to statistical modeling, including improving Covid-19 mortality rate predictions and enhancing hurricane prediction accuracy.
Work at The George Washington University
Mingze Zhang has been employed at The George Washington University as a Teaching/Research Assistant since 2017. In this role, Zhang engages in various academic and research activities, contributing to the university's research initiatives. The position has provided opportunities to develop expertise in statistical methods and time series analysis, particularly in the context of health and environmental data.
Education and Expertise
Mingze Zhang earned a Doctor of Philosophy (PhD) in Statistics from The George Washington University, completing the program from 2017 to 2022. Prior to this, Zhang obtained a Bachelor's degree in Statistics from the University of Science and Technology of China, studying there from 2013 to 2017. This educational background has equipped Zhang with a strong foundation in statistical theory and methodologies.
Background in Statistics
Zhang has a background in statistical analysis, having worked as a Statistician at Sanofi for three months in 2021 and at Astellas Pharma US for three months in 2020. These positions involved applying statistical techniques to real-world problems, enhancing skills in data analysis and model development.
Research Contributions
Zhang has made significant contributions to statistical modeling and prediction. Notably, Zhang improved Covid-19 mortality rate prediction by 31% using a newly proposed time series model. Additionally, Zhang enhanced hurricane prediction accuracy by 27% through a novel count time series model that incorporates the Markov property. These research efforts demonstrate a focus on applying statistical methods to critical issues.
Statistical Methodologies Developed
Zhang has developed various statistical methodologies, including a model selection approach utilizing 10-fold cross-validation and a nonparametric estimator for time series analysis. Furthermore, Zhang reduced computational time by 53% through a sequential model selection procedure, showcasing efficiency in statistical modeling processes.