Please scroll down to the bottom of the page for the most recent upcoming events
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Boston Chapter of the ASA x Cytel Webinar: Generating the Right Evidence at the Right Time
Join the Boston Chapter of the ASA and Cytel for an insightful 1-hour webinar featuring Dr. Frank Bretz, Distinguished Quantitative Research Scientist at Novartis, as he discusses a new class of flexible augmented clinical trial designs that aim to improve evidence generation in drug development.
Date: Wednesday, April 2, 2025
Time: 9:00 – 10:00 AM ET | 3:00 – 4:00 PM CET
Location: Online (Zoom link will be provided to registered attendees)
Cost: Free
Don't miss this opportunity to gain insights into cutting-edge statistical methodologies in clinical trial design!
Registration Link
Presentation Title: Generating the Right Evidence at the Right Time: Principles of a New Class of Flexible Augmented Clinical Trial Designs
Abstract:
Drug development has historically followed a sequential approach, prioritizing regulatory approval before addressing questions relevant to other stakeholders involved in bringing new medicines to patients, such as health technology assessment bodies, payers, patients, and physicians. However, this approach can be inefficient, as data generated later in the process - often through observational studies - may be difficult to compare with earlier randomized trial data, leading to challenges in understanding and interpreting treatment effects. Moreover, the scientific questions these later experiments aim to address often remain vague.
Compressing evidence generation timelines to address questions beyond regulatory approval can be achieved through various strategies. In this talk, we present a newly proposed study design, FACTIVE (Flexible Augmented Clinical Trial for Improved eVidence gEneration), which augments confirmatory randomized controlled trials with concurrent, close-to-real-world elements. This approach enables, for example, the exploration of broader study populations, alternative comparators or outcomes, and different conditions, potentially gated by an interim analysis of the confirmatory randomized controlled trial.
Following an overview of the design, including its variations and alternatives, we will discuss potential applications and the benefits of integrating FACTIVE into the evidence generation process.
Reference: Dunger-Baldauf, C., Hemmings, R., Bretz, F., Jones, B., Schiel, A. and Holmes, C., 2023. Generating the right evidence at the right time: Principles of a new class of flexible augmented clinical trial designs. Clinical Pharmacology & Therapeutics, 113(5), pp.1132-1138. Read More
About the Speaker:
Frank Bretz joined Novartis in 2004 and currently serves as a Distinguished Quantitative Research Scientist. With a keen interest in advancing drug development practices, he has contributed to methodological advancements in pharmaceutical statistics, including adaptive designs, dose finding, estimands, and multiple testing.
Frank holds adjunct professorial positions at Hannover Medical School (Germany) and the Medical University of Vienna (Austria). He was a member of the ICH E9(R1) Expert Working Group on Estimands and sensitivity analysis in clinical trials and currently serves on the ICH E20 Expert Working Group on Adaptive clinical trials. He is also a Fellow of the American Statistical Association.
Link to the recording
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
2025 Mosteller Statistician of the Year Award
The Boston Chapter of the American Statistical Association is delighted to announce that Dr. Judith Lok, Professor in the Department of Mathematics and Statistics at Boston University, is the esteemed recipient of the 2025 Mosteller Statistician of the Year Award.
Honoree and Speaker: Dr. Judith Lok, Professor in the Department of Mathematics and Statistics at Boston University
Talk Title: Causal Inference: a Statistics Playground, with Lessons Learned
Date: April 28, 6:00 - 8:00 PM (ET)
Location: River Room of the Boston University Hillel, 213 Bay State Road, MA 02215
Abstract:
I am writing a textbook titled "Causal Inference: A Statistics Playground". It targets students and statisticians in and out of academia who work with or want to learn about causal inference.
Causal inference methods address questions like "what would happen if" through data analysis. The textbook primarily concentrates on data from non-randomized (observational) studies, which are abundant. Estimating treatment effects from observational data is challenging due to confounding by indication: when comparing treated and untreated individuals/units, differences arise not only from the effect of the treatment but also from pretreatment differences between the two groups. Causal inference offers methods to overcome confounding by indication and other biases, allowing for the estimation of treatment effects from observational data.
In this lecture, I will explore recent applications of causal inference, touch upon the methods behind them, and share key lessons learned. Scientific progress does not come from following the crowd. When I began studying causal inference, many scientists dismissed the notion of drawing causal conclusions from non-randomized data. More recently, skepticism among statisticians about analyzing data of trials where the intervention package changed over time led me to work on Learn-As-you-GO (LAGO). LAGO is an adaptive trial design that adjusts the composition of a multi-component intervention package during the trial. Our team has developed conditions on the learning process that adjust the intervention package to prevent failed trials while obtaining valid inference (consistency, asymptotic normality, and preservation of Type-1 error). Thus, statistics in general, and causal inference in particular, is a playground where it is okay to break the rules if one is prepared to suffer (or enjoy) the consequences: developing rigorous mathematical proofs. Another lesson learned: it is rarely feasible to carry out reliable causal inference applications in isolation. Engaging with subject matter experts about assumptions and models is both a pleasure and a necessity for drawing valid causal conclusions. As a result, many causal inference statisticians become data scientists: they are skilled in both statistics and a field of application. For me, the field of application has been HIV/AIDS and, more broadly, public health.
Bio of the Speaker:
Dr. Lok is a distinguished leader in the field of causal inference, renowned for her pioneering contributions to mediation analysis, structural nested models, and adaptive causal methods. Her research has significantly advanced statistical methodology and its applications in clinical and biomedical research, particularly in improving treatment strategies for infectious diseases. She has published extensively in leading journals, including Annals of Statistics, Statistics in Medicine, Biometrics, and high-impact clinical journals.
Dr. Lok has also been the principal investigator on numerous prestigious grants, including an NIH R01 award for developing methods to analyze the causal effects of HAART on HIV outcomes, an NSF grant to advance causal inference methods for mediation and methods to compare confidence regions, and an mPI R01 to develop Learn-As-you-GO (LAGO) adaptive clinical trials.
Beyond her research, Dr. Lok is a dedicated mentor and a passionate advocate for student development. Since 2019, she has served as the faculty advisor for the Boston University Student Chapter of the ASA (BUSCASA), where she has played an instrumental role in fostering student engagement in the statistical community. Her leadership has been particularly evident in the New England Student Research Symposium on Statistics and Data Science, which she co-organized in 2020, 2022, and 2024. Dr. Lok has consistently gone above and beyond to mentor students, providing personalized feedback on their presentations and ensuring they receive meaningful learning experiences.
Her service to the Boston Chapter and the broader statistical community is exceptional. Dr. Lok was instrumental in organizing the first in-person Student Research Symposium at Boston University, securing funding and suitable venues to create an enriching experience for participants. Her contributions extend nationally, having served as IMS chair for the 2017 ENAR Spring Meeting, organizing multiple invited sessions at Joint Statistical Meetings, and contributing as associate editor of Epidemiological Methods and co-editor of Statistical Communications in Infectious Diseases.
About the Award: Each year, the Boston Chapter presents the Mosteller Statistician of the Year Award to a distinguished statistician who has made exceptional contributions to the field and has demonstrated outstanding service to the statistical community, including the Boston Chapter. Originally established in 1990 as the Statistician of the Year Award, it was renamed in 1997 in honor of its first recipient, Fred Mosteller, on his 80th birthday.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Boston Chapter of the ASA Webinar: Integrating external control data in RCTs using a novel propensity score and exchangeability model approach
Join the Boston Chapter of the ASA for an insightful 1-hour webinar featuring Dr. Wei Wei, Assistant Professor at the division of Medical Oncology, Yale School of Medicine, as he discusses a novel approach that combines the propensity score weighting (PW) and the multi-source exchangeability modelling (MEM) approaches to augment the control arm of a RCT in the rare disease setting development.
Date Wednesday, May 6, 2025
Time: 1:00 – 2:00 PM ET
Location: Online (Zoom link will be provided to registered attendees)
Cost: Free
Don't miss this opportunity to gain insights into cutting-edge statistical methodologies in clinical trial design!
Registration Link
Presentation Title: Propensity score weighted multi-source exchangeability models for incorporating external control data in randomized controlled trials
Abstract:
Among clinical trialists, there has been a growing interest in using external data to improve decision-making and accelerate drug development. We propose a novel approach that combines propensity score weighting (PW) and the multi-source exchangeability modelling (MEM) approaches to augment the control arm of a RCT. First, propensity score weighting is used to construct weighted external controls that have similar observed pre-treatment characteristics as the current trial population. Next, the MEM approach evaluates the similarity in outcome distributions between the weighted external controls and the concurrent control arm. The amount of external data we borrow is determined by the similarities in pretreatment characteristics and outcome distributions. The proposed approach can be applied to binary, continuous and survival data. We evaluate the performance of the proposed PW-MEM method and several competing approaches based on simulation and re-sampling studies. Our results show that the PW-MEM approach improves the precision of treatment effect estimates while reducing the biases associated with borrowing data from external sources.
Reference: Wei W, Zhang Y, Roychoudhury S. the Alzheimer's Disease Neuroimaging Initiative, Propensity score weighted multi-source exchangeability models for incorporating external control data in randomized clinical trials. Statistics in Medicine. 2024; 43(20): 3815-3829. Read More
About the Speaker:
Dr. Wei is an assistant professor at the division of Medical Oncology, Yale School of Medicine. Dr. Wei's current research focuses on the development of Bayesian statistical designs for master protocols and the leveraging of external data to improve the design and analysis of cancer clinical trials. Dr. Wei has extensive experience in drug development from early phase to late phase trials and has served as the principal statistician on numerous investigator-initiated oncology trials.
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Upcoming short course by the New Researchers Network of the National Institute of Statistical Sciences (NISS).
Overview:
As data science and statistics become increasingly embedded in scientific research and industry, the role of computing is evolving. Today, data scientists must go beyond traditional statistical software and spreadsheets—they need to build data science products that power real-time predictions, business decisions, and analytical tools. This short course, led by Alex Reinhart, will provide an introduction to essential software engineering skills for data scientists and statisticians. Participants will explore best practices for writing code that is reliable, scalable, and maintainable—whether for research applications, industry use cases, or product development. Attendees will gain practical insights into building robust data science solutions, making their work more efficient and impactful. Whether you're an academic researcher or an industry professional, this course will equip you with the computing skills necessary to take your data science work from code to product.
Date and time: Thursday, April 3 · 1 - 3 pm EDT
Location: Online
Registration: https://www.niss.org/events/short-course-alex-reinhart-code-products-software-engineering-data-science.
Abstract:
Short Course title: From Code to Products - Software Engineering for Data Science
Statisticians and data scientists increasingly rely on computing. We use computers to analyze data, but as data science and statistics are embedded into more areas in science and industry, the kinds of computing we need are changing. Now, beyond spreadsheets and statistical software, data scientists need to know how to build data science products: software to deliver predictions, recommendations, or business decisions, often in real time. Instead of writing code to implement an analysis and generate results for a report, we write code that becomes part of products, data pipelines, or analysis tools used by others. In this short course, we'll discuss the computing skills statisticians need, both in industry and in academic research. Topics will include software design and organization, testing, version control, automation, and other software engineering tools, including examples in R and Python.
About the Instructor
Alex Reinhart is an Assistant Teaching Professor in the Department of Statistics & Data Science at Carnegie Mellon University. His teaching and research focus on statistical methods, data science, and statistical applications in real-world settings. He is particularly interested in statistical inference, uncertainty quantification, and improving the accessibility and reproducibility of statistical research. Reinhart holds a Ph.D. in Statistics from Carnegie Mellon University, where his research explored statistical techniques for uncertainty quantification in nuclear detection. He is also the author of Statistics Done Wrong: The Woefully Complete Guide, a book that highlights common statistical misconceptions and pitfalls in scientific research. In addition to his teaching and research, Reinhart is committed to statistical education and mentorship, guiding students in applying rigorous statistical methods to practical problems. His work bridges the gap between theoretical statistics and applied problem-solving, contributing to advancements in data science and statistical practice.