Fall 2025
Time & Location: All talks are on Wednesdays in TBA at TBA PM unless otherwise noted.
Organizer: Xiang ji, Michelle Lacey and Yuwei Bao
October 01
Title: Causal Inference in Pharmaceutical Statistics
Speaker: Yixin Fang - AbbVie
Abstract: In this talk, the estimand framework followed in the pharmaceutical industry will be discussed, using the language of causal inference. The definition of causal estimand and statistical estimand will be addressed, as well as the differences between randomized controlled trials (RCT) and non-interventional studies (NIS). Two basic identification strategies—the G-formula strategy and the weighting strategie—will be presented. With regard to estimation of the estimand, doubly robust methods will be discussed.
Additionally, a brief description will be provided of the difference between FDA submissions, which are focused on regulatory approval for marketing a product, and HTA submissions, which are focused on gaining reimbursement and demonstrating value to payers and healthcare systems. In particular, methods for direct and indirect comparisons will be discussed.
In summary, this talk is intended to serve as a high-level introduction to important causal inference topics for students interested in pursuing a career in the pharmaceutical industry.
Please join this seminar via: https://tulane.zoom.us/j/97158638464
Time: 3:00 PM
Location: Zoom only 971 5863 8464
_______________
October 15
Title: Scalable topic modelling decodes spatial tissue architecture for large-scale multiplexed imaging analysis
Speaker: Xiyu Peng - Texas A&M University
Abstract: Recent progress in multiplexed tissue imaging is advancing the study of tumor microenvironments to enhance our understanding of treatment response and disease progression. Despite its popularity, there are significant challenges in data analysis, including high computational demands that limit feasibility for large-scale applications and the lack of a principled strategy for integrative analysis across images. To overcome these challenges, we introduce a spatial topic model designed to decode high-level spatial architecture across multiplexed tissue images. Our method integrates both cell type and spatial information within a topic modelling framework, originally developed for natural language processing and adapted for computer vision. We benchmarked its performance through various case studies using different single-cell spatial transcriptomic and proteomic imaging platforms across different tissue types. We show that our method runs significant faster on large-scale image datasets, along with high precision and interpretability. It consistently identifies biologically and clinically significant spatial “topics”, such as tertiary lymphoid structures.
Time: 3:00 PM
Location: Dinwiddie Hall 108
_______________
November 05
Title: The Systematic Manipulation of the Scientific Publication and Citation Processes
Speaker: Bill Woodall - Professor Emeritus, Virginia Tech (Host): Xiang Ji
Abstract: I became aware of the extent of the attacks on the publication and citation processes though Taylor & Francis, the publisher of Quality Engineering for which I am the editor.
All areas of science are being affected, from mathematics to medicine. The following are some of the primary concerns: authorships being sold, fake papers produced by paper mills, sham reviews, unethical behavior of guest editors for special issues, bribes offered to editors, the rise of predatory journals and conferences, citation cartels, plagiarism, misuse of AI, and the fabrication of data and images.
These and other issues, illustrated with numerous examples, will be discussed in this presentation. A related issue is the proliferation of junk science.
Efforts to protect the scientific literature will be discussed, such as the contributions by individual sleuths and the use of the STM Integrity Hub that was established by the major academic publishers. There will also be some discussion of the article retraction process. Over 10,000 scientific papers were retracted in 2023, a record number.
Time: 3:00 PM
Location: Dinwiddie Hall 108
_______________
November 19
Topic: Composite likelihood approaches to phylogenetic inference under the multispecies coalescent
Speaker: Laura Kubatko - Ohio State University (Host): Xiang Ji
Abstract: Species-level phylogenetic inference under the multispecies coalescent model remains challenging in the typical inference frameworks (e.g., the likelihood and Bayesian frameworks) due to the dimensionality of the space of both gene trees and species trees. Algebraic approaches intended to establish identifiability of species tree parameters have suggested computationally efficient inference procedures that have been widely used by empiricists and that have good theoretical properties, such as statistical consistency. However, such approaches are less powerful than approaches based on the full likelihood. Methods based on composite likelihood are a compromise between these two approaches that enable computationally efficient inference while maximizing use of the available sequence data. In this talk, I’ll describe the relationship between these two approaches, highlighting the strengths and weaknesses of each and providing directions for future work.
Time: 2:00 PM
Location: Gibson Hall 400D
_______________
