The purpose of this event is to promote interdisciplinary research within the flagship institutions of the state of Georgia. Our conference will enable junior researchers in the Southeast region of the United States, including graduate students, to present their work, to see state of the art developments in research on statistics and related scientific areas, and to interact with some of the key players in the area. Georgia Statistics Day puts emphasis on mentoring of junior researchers and on interaction between senior and junior researchers. (Brochure - Coming Soon)
Please contact conference organizers if you would like to attend the conference.
Code of Conduct | GA Statistics Day Vision Policy
Abstract Submission:
- The abstract submission deadline is October 10, 2025. To submit your abstract, please click here.
Organizers
Abhyuday Mandal, University of Georgia
Date and Location
Friday 10/31/2025
The Georgia Center for Continuing Education & Hotel
1197 South Lumpkin Street, Athens, GA 30602
Registration
- To register, please click here.
Registration Payment
- GA Chapter Member Registrations (must provide membership id)
- Students ($100 until October 3, $150 afterwords)
- Regular ($150 until October 3, $200 afterwords)
- Non-member Registrations:
- Students ($110 until October 3, $160 afterwords)
- Regular ($160 until October 3, $210 afterwords)
Keynote Speaker
 |
Liza Levina, Collegiate Professor of Statistics at the University of Michigan
Title: Towards Interpretable and Trustworthy Network-Assisted Prediction
Abstract: When training data points for a prediction algorithm are connected by a network, it creates dependency, which reduces effective sample size but also creates an opportunity to improve prediction by leveraging information from neighbors. Multiple prediction methods on networks taking advantage of this opportunity have been developed, but they are rarely interpretable or have uncertainty measures available. This talk will cover two contributions bridging this gap. One is a conformal prediction method for network-assisted regression. The other is a family of flexible network-assisted models built upon a generalization of random forests (RF+), which both achieves competitive prediction accuracy and can be interpreted through feature importance measures. Importantly, it allows one to separate the importance of node covariates in prediction from the importance of the network itself. These tools help broaden the scope and applicability of network-assisted prediction to practical applications.
Liza Levina - Website
|
