Colorado School of Public Health

Get to Know Students Series: Ziwei Tian

Written by Colorado School of Public Health | November 19, 2026

Ziwei Tian is a PhD student in the Department of Biostatistics & Informatics at the Colorado School of Public Health, University of Colorado Anschutz Medical Campus. 

    • M.S. in Biostatistics, University of Michigan  
    • B.S. in Life Science Informatics, Statistics, University of Michigan  
    • Research interests: Genomics, transcriptomics, and multiomics data integration; computational immunology; longitudinal and spatial data analysis; graphical models and network analysis; machine learning; deep learning
What led you to choose the ColoradoSPH Biostatistics & Informatics Department for your PhD studies? 

I chose the ColoradoSPH Biostatistics & Informatics Department because I was looking for a PhD program that would allow me to develop rigorous statistical methodology while staying closely connected to biomedical and public health research. The department stood out to me because of its balance between theoretical training, computational skills, and collaborative applied research. I was also drawn to the CU Anschutz environment, where biostatisticians have many opportunities to work with investigators in medicine, genomics, immunology, and public health. That combination felt like a strong fit for my interests and long term goals. 

 Why did you choose to study biostatistics?

I have always been interested in both life science and mathematics, and biostatistics gives me a way to bring those interests together. I like that biostatistics is not only about developing models, but also about asking whether those models answer meaningful scientific questions. In biomedical research, data are often complex, noisy, high dimensional, and collected over time, so careful statistical thinking is needed to make valid conclusions. I am especially interested in methods for genomics, longitudinal data, network modeling, and multimodal biomedical data, where statistical methods can help reveal biological patterns that are not easy to see directly. 

 What has been your favorite class so far? 

Two of my favorite classes have been Statistical Methods in Genomics and Theory and Algorithms in Data Science. Statistical Methods in Genomics was especially useful for my research because it connected statistical methods with real genomic technologies and applications. I appreciated that the course covered topics such as gene expression, RNA sequencing, epigenetics, single cell and spatial methods, and network analysis. The visit to the Genomics Core Facility also helped connect the statistical methods we learned in class to the experimental process that generates the data. 

I also really enjoyed Theory and Algorithms in Data Science because it helped me understand the theoretical foundations behind many machine learning and deep learning methods. The course connected algorithms, optimization, statistical learning theory, and implementation, which is important for my research because I often work with methods that require both computational and theoretical understanding. 

How would you describe the student community in the department?

I would describe the student community as welcoming, supportive, and intellectually curious. Students come from different academic and professional backgrounds, which makes conversations in classes and seminars more interesting. Even though PhD training can be very independent, there are many opportunities to connect with other students through classes, seminars, student association activities, and department events. I have also found that students are willing to share advice about coursework, research, teaching, and navigating the program. Overall, the department feels collaborative rather than competitive. 

Tell us about a project you are currently working on that you are excited about.

One project I am excited about focuses on developing statistical methods for longitudinal and spatial biomedical data, with applications to immune mediated diseases such as lupus nephritis. Methodologically, I am interested in time varying biological networks, including continuous time extensions of sparse time series chain graphical models, which can characterize both dynamic relationships across time and contemporaneous associations among biological features. In parallel, I am applying multimodal analysis to lupus nephritis kidney biopsy data, where spatial transcriptomic measurements, cell type annotations, immune infiltration, and pathology related information can be integrated to understand how inflammatory signals are organized across tissue. 

What advice would you give to prospective students applying to this program?

My advice would be to think carefully about why biostatistics is the right field for the questions you want to study. A strong quantitative background is important, but it is also important to be curious about biomedical and public health problems. In this program, many research questions come from real scientific collaborations, so being able to communicate with nonstatistical collaborators is just as valuable as technical training. 

I would also encourage prospective students to be open minded when they enter the program. It is helpful to have research interests, but those interests may evolve after taking classes, attending seminars, and talking with faculty and other students. The program provides many opportunities to explore different areas, so students do not need to have everything fully decided before they start. 

 What do you like to do outside of research? Or What do you like about living in Colorado? 

Outside of research, I enjoy photography and birding. Colorado is a great place for both because there are so many different landscapes, parks, and hiking areas to explore. I also enjoy visiting hot springs and spending time outdoors. Living in Colorado has made it easier to take short breaks from research and recharge, whether that means going for a hike, taking photos, or simply enjoying the mountain views.