Tuesday, April 15, 6:00 pm - 7:00 pm
OSU Hamilton Hall, 1645 Neil Avenue, Room 400, Columbus 43210 (in-person) and Zoom (link will be distributed to registered participants)
Dinner Following @ Bravo Italian Kitchen
10 free spots available for chapter members on a first-come, first-served basis
Event is free but registration is required!
Register now at
https://osu.az1.qualtrics.com/jfe/form/SV_eDPbBmzgpXkVqrI
Peter White, Ph.D.
Chief Data Sciences Officer
Abigail Wexner Research Institute
Nationwide Children’s Hospital
"A New Era in Biomedical Research: Harnessing AI
to Advance Diagnosis & Discovery"
Abstract: Biomedical research is entering a transformative new era, driven by advancements in artificial intelligence (AI) and machine learning (ML). At the Abigail Wexner Research Institute, the Office of Data Sciences (ODS) is pioneering initiatives that integrate advanced AI into pediatric healthcare, redefining diagnosis, treatment, and research. Through a centralized data lake, enhanced data intelligence, and robust translational pipelines, ODS enables researchers and clinicians to leverage vast datasets—from genomics to electronic health records—for precision medicine. Highlighting innovative projects such as DREAM, an AI-driven platform transforming mental health research, and GENiUS, which accelerates genomic diagnosis in neonates and automates the genetic variant assessment process, this presentation will explore how AI technologies streamline complex data analysis, enhance clinical decision-making, and facilitate rapid discovery. Ultimately, this seminar underscores how harnessing AI can empower scientific discovery, significantly advance health outcomes, and pave the way for equitable, data-driven pediatric care.
Monday, September 16
OSU's Fawcett Event Center, 2400 Olentangy River Rd
Fernanda Schumacher, Ph.D.
Assistant Professor, Biostatistics
OSU College of Public Health
Title:
Challenges in Longitudinal Data Analysis:
Complex Made Simple with the R Package skewlmm
Abstract:
When analyzing longitudinal data or other types of repeated measurement data, assumptions commonly used for mixed-effects models are often unreasonable. This talk will focus on the challenges researchers may encounter in such applications, discussing tools for model evaluation and presenting more complex model specifications in R. Specific challenges addressed will include serial correlation, outliers, skewness, and censored and missing data. Through illustrative examples, I will propose simple solutions by leveraging the R package skewlmm. Attendees can expect to gain practical insights and tools to enhance their analyses for continuous outcomes, making complex longitudinal data more approachable and interpretable.
Agenda
5:30pm - 6:30 pm Social Hour (Cash bar and appetizers)
6:30pm - 7:15 pm Speaker
7:15 - 8:15 pm Dinner Buffet
9 pm Conclusion
$10 for members, $20 for non-members and $5 for students.
Parking is free.
From Big Data to Better Insights:
A Primer on Using Machine Learning Methods in a Data-Centric World
Trent D. Buskirk, Ph.D.
Old Dominion University
This is a two-day, virtual event from 1:00 pm - 5:00 pm on August 14 and 15
Description:
The amount of data generated as a by-product in society is growing fast including data from satellites, sensors, transactions, social media, smartphones, and even thermostats, just to name a few. Such data are often referred to as "big data" and can be leveraged to create value in different areas such as health, crime prevention, commerce and fraud detection, among others. This course offers a broad overview of big data to allow participants to understand the need for alternate methods to analyze and visualize such data and introduces machine learning framework. The course will discuss the difference between inference and prediction within the statistical machine learning paradigm as well as the difference between supervised and unsupervised machine learning methods and close with an intuitive, accessible yet rigorous, discussion of four of the most common machine learning methods that every analyst should understand in the era of big data including k-means clustering, k nearest neighbors, tree-based methods and random forest models using examples in R. Time permitting, we will highlight the Rattle package in R that provides an intuitive and accessible graphic user interface for reproducible specification of a broad assortment of machine learning models within the R environment.
About the instructor:
Trent D. Buskirk, Ph.D., is a Professor and Data Science Fellow in the New School of Data Science at Old Dominion University. Prior to this appointment, Trent was the Novak Family Distinguished Professor of Data Science and Chair of the Applied Statistics and Operations Research Department at Bowling Green State University. Dr. Buskirk is a Fellow of the American Statistical Association and his research interests include big data quality, recruitment methods through social media, the use of big data and machine learning methods for health, social and survey science design and analysis, mobile and smartphone survey designs and in methods for calibrating and weighting nonprobability samples and fairness in AI models and interpretable ML methods.
Bo Lu, Ph.D.
Professor, Biostatistics
OSU College of Public Health
June 6, 6:00 pm - 7:00 pm, Cunz Hall or
Zoom https://osu.zoom.us/j/91725006895?pwd=TFFCeDdQOVhUMENDcWNnYXBkSVVwUT09
"Matched Design to Leverage Real World Data in Clinical Trials"
Dinner After - Bravo Italian Kitchen (1803 Olentangy River Rd) - Please RSVP for the dinner to asa.columbus.chapter@gmail.com.
Please join us to celebrate the Columbus Chapter's 5-year anniversary!
This event will take place at 6:00 pm on Wednesday, November 8, 2023 at The Fawcett Center (2400 Olentangy River Rd., Columbus, OH 43210, Alumni Lounge).
The cost is: $10 for members, $20 for non-members and $5 for students. Parking is free.
The evening will include a cash bar, appetizers, a Seminar (see below for speaker info and abstract), a Five Year Anniversary Summary Presentation from Steve MacEachern (OSU Professor of Statistics), and a dinner buffet.
Seminar Title: "Statistical Insights into the Genomic World of Bioinformatics"
Seminar Speaker:
Meng Wang, PhD, Senior Bioinformatics Scientist
Center for Childhood Cancer Research, The Abigail Wexner Research Institute, Nationwide Children’s Hospital
Bioinformatics is an interdisciplinary field of science involving the collection, analysis, and interpretation of genomic sequencing data to decipher the genetic code. Sequencing data are high-dimension, possibly sparse, and have complex underlying structures. In application, GLM, various machine learning and deep learning models are popular due to their abilities to handle such complex data structures. In recent development, single cell genomics has enabled scientists to profile genomic and transcriptive landscape at a unprecedent resolution, but it also elevated the challenges we face in analysis by increasing the curse of dimensionality, heterogeneity, and sparsity in the data. In this talk, I will present a statistician’s life in bioinformatics: the role which statistics has played in second generation sequencing, interdisciplinary communication, as well challenges we currently face in application and methods development.
When:
Friday, August 18, 2023, 9:30 am - 5:30 pm EDT
Where:
Online (Zoom link will be sent to email address used when registering.)
Registration:
Please use this link to register: R Markdown to Quarto
Early-bird deadline ends August 8, 2023; Regular registration ends August 17, 2023.
Instructors
Andrew Bray is an Associate Teaching Professor in the Department of Statistics at UC Berkeley where he develops and teaches courses in statistics and data science. His research interests include statistical computing, data privacy, and applications of statistical models to environmental science. He is one of the authors of the infer R package for resampling based inference and an enthusiastic user of all things R Markdown / Quarto.
Mine Cetinkaya-Rundel is Professor of the Practice at Duke University and Developer Educator at RStudio. Mine's work focuses on innovation in statistics and data science pedagogy, with an emphasis on computing, reproducible research, student-centered learning, and open-source education as well as pedagogical approaches for enhancing retention of women and under-represented minorities in STEM. Mine is a Fellow of the ASA and Elected Member of the ISI as well as the winner of the 2021 Robert V. Hogg Award for Excellence in Teaching Introductory Statistics.
This workshop is designed for those who want to take their R Markdown skills and expertise and apply them in Quarto, the next generation of R Markdown. Quarto is an open-source scientific and technical publishing system that offers multilingual programming language support to create dynamic and static documents, books, presentations, blogs, and other online resources. In this workshop you will learn how to apply your reproducible authoring skills to the Quarto format and learn about new tools and workflows for authoring with Quarto in RStudio. You will learn to create static documents as well as slide presentations. The workshop will also introduce you to Quarto projects which you can use to build websites and write blogs and books. Finally, you will learn various ways to deploy and publish your Quarto projects on the web.
Tuesday, June 6th from 3:30 - 5:00 pm.
In Person Option: Fisher Hall Room 168, Franklin University, 300 E. Rich St, Columbus, OH 43215
Virtual Option: Register Here
See the following link for a map of the campus and where visitors can park for free.
Speaker
Susan H. Gawel, MS, PhD. Director Biostatistics, Senior Associate Research Fellow, Abbott Diagnostics Division, Abbott Laboratories
Algorithm Development for Progression of Liver Disease to Liver Cancer
This presentation will focus on the development of algorithms that can assist in predicting the likelihood of liver disease and liver cancer. The talk will explore the current challenges in diagnosing liver disease and the transition to liver cancer and how these challenges have prompted the development of novel solutions. Clinical algorithms developed using different statistical models in the diagnosis and prediction of liver disease and liver cancer will be compared, with attention on data training and validation. The presentation will also discuss the potential benefits of using these algorithms in clinical practice and the challenges in clinical adoption.
November 15, 2022: Fall Speaker Event
"A Potential Outcomes Approach to Selection Bias"
Presenter: Dr. Eben Kenah, Division of Biostatistics, College of Public Health, The Ohio State University
Time: 5:30 pm - 7:00 pm EST with optional dinner after
RSVP: asa.columbus.chapter@gmail.com
In person option:
OSU Cunz Hall, Room 160
1841 Neil Avenue
Columbus OH 43210
Virtual option:
Join Zoom Meeting
https://osu.zoom.us/j/97158797574?pwd=aVgzUDlnSS9BRzd5TEZuUGFmZW4rdz09
Meeting ID: 971 5879 7574
Password: 280727
August 19, 2022: Traveling Course "Data Visualization with R"
Instructor: Aaron Williams, Urban Institute
Full-Day Course, 9:00 am - 5:30 pm (EDT), Zoom online meeting
More details can be found at https://community.amstat.org/coc/chapterresources/travelingcourse/datavisualization .
Use this link to register: https://www.eventbrite.com/e/data-visualization-with-r-tickets-344370881577 .
April 8, 2022, 3:30 pm - 4:30 pm EDT: Virtual Social Event
Join the Columbus Chapter for a fun "History of Statistics" game via Zoom. Every participant will get a prize!
Register in advance for this meeting: https://osu.zoom.us/meeting/register/tJMofuytqz4pEtEnFsakrbkPzA-NLj--lGg0 . After registering, you will receive a confirmation email containing information about joining the meeting.
April 1-3, 2022: ASA DataFest @ OSU
A detailed DataFest event timeline is available at https://data-analytics.osu.edu/datafest .
To register as a DataFest mentor and/or judge, please use this link https://osu.az1.qualtrics.com/jfe/form/SV_2rUi4JIJld79hLU .
November 12, 2021, 3:30 pm - 5:00 pm EST: ASA Columbus Chapter Fall Speaker Event
"Operating under Uncertainty: Disease surveillance of COVID-19"
Dr. David Kline, Assistant Professor, Dept. of Biostatistics and Data Science, Division of Public Health, Wake Forest School of Medicine
Register: https://osu.zoom.us/meeting/register/tJElceirrjsuH9OF5PjMAOHnWFRk7Siw3G3r
After registering, you will receive a confirmation email containing information about joining the virtual (Zoom) meeting.
Consider this scenario:
Boss: ‘”Hey Jesse, would you please bring me a rock from outside?"
Employee: “Sure Boss. Here is a nice, round one.”
Boss: “No, I wanted a flat rock.”
Employee: “Okay, here’s a different one. It’s a nice, flat rock.”
Boss: “No I wanted a large rock.”
Employee: “How’s this one? It’s a large, gray, flat rock."
Boss: “Isn’t there a brown one?”
And on it goes . . .
Have you ever been in a similar situation? What did you do, or what should you have done? Please join us for a lively discussion about dealing with this kind of difficult boss, co-worker, client, etc. We will brainstorm strategies for handling these and other situations. Among the types of people we’ll discuss are:
Mr. "I'm not really sure what I want" -- constant change of heart; says one thing in person and something completely different in an e-mail an hour later.
Mr. "I need this done yesterday" -- general lack of awareness of the space-time continuum; belief that having an idea means work is accomplished.
Ms. "Won't this take 5 minutes?" -- belief that she can do what you do in a much shorter time frame than is really possible.
Ms. "What you did was great, but..." -- goes along with everything you propose, only to basically toss it all out once it's finished and go in a completely new direction.
Check out some other “challenging” examples in this flyer: https://cdn2.hubspot.net/hub/53/file-1524889572-jpg/blog-files/wonderful-world-of-clients.jpg .
Lecture by Dale Rhoda, Nov. 13, 2020
Abstract: Dale Rhoda studied math and physics in the 1980s at Northeastern University and earned master’s degrees in public policy (Duke University), industrial and systems engineering (OSU), applied statistics (OSU) and public health with a focus on biostatistics. He also did a graduate inter-disciplinary specialization in survey research at OSU. His public health work today focuses on design and analysis of household surveys in low and middle-income countries. His clients include the Bill & Melinda Gates Foundation, the World Health Organization, and the American Red Cross. Dale’s first career – the work that prompted him to later study statistics – was developing weather information systems for air traffic planners at MIT Lincoln Laboratory and the US Department of Transportation. He helped develop the radars that protect major US airports from hazardous wind shear, including the radar in Pataskala that protects passengers flying in and out of John Glenn International Airport. This talk will include stories and movies from his early work studying factors that affect whether commercial airline pilots fly passengers around thunderstorms, or through them. Dale will also tell stories from recent work, describing statistical and practical challenges when estimating the proportion of children who receive vital vaccines in the first year of life.
Lecture by Daniel Heitjan, June 12, 2020
Abstract: Randomized clinical trial designs often incorporate one or more planned interim analyses. In event-based trials, one may prefer to schedule the interim analyses at the times of occurrence of specified landmark events, such as the 100th event, the 200th event, and so on. Because an interim analysis can impose a considerable logistical burden, and the timing of the triggering event in this kind of study is itself a random variable, it is natural to seek to predict the times of future landmark events as accurately as possible. Early approaches to prediction used data only from previous trials, which are of questionable value when, as commonly occurs, enrollment and event rates differ unpredictably across studies. With contemporary clinical trial management systems, however, one can populate trial databases essentially instantaneously. This makes it possible to create predictions from the trial data itself — predictions that are as likely as any to be reliable and well calibrated statistically. This talk will describe work that some colleagues and I have done in this area. I will set the methodologic development in the context of the study that motivated our research: REMATCH, an RCT of a heart assist device that ran from 1998 to 2001 and is considered a landmark of rigor in the device industry.
Lecture by Haoda Fu, Oct. 3, 2019
Dr. Haoda Fu is a senior research advisor and a enterprise lead for Machine Learning, Artificial Intelligence, and Digital Connected Care from Eli Lilly and Company. Dr. Haoda Fu is a Fellow of ASA (American Statistical Association). He is also an adjunct professor of the biostatistics department, Indiana university school of medicine. Dr. Fu received his Ph.D. in statistics from University of Wisconsin - Madison in 2007 and joined Lilly after that. Since he joined Lilly, he is very active in statistics methodology research. He has more than 90 publications in the areas, such as Bayesian adaptive design, survival analysis, recurrent event modeling, personalized medicine, indirect and mixed treatment comparison, joint modeling, Bayesian decision making, and rare events analysis. In recent years, his research area focuses on machine learning and artificial intelligence. His research has been published in various top journals including JASA, JRSS, Biometrics, ACM, IEEE, JAMA, Annals of Internal Medicine etc.. He has been teaching topics of machine learning and AI in large industry conferences including teaching this topic in FDA workshop. He was board of directors for statistics organizations and program chairs, committee chairs such as ICSA, ENAR, and ASA
Biopharm session.
Lecture by Peter Mueller, June 4, 2019
Abstract: We propose a categorical matrix factorization method to infer latent diseases from electronic health records data. A latent disease is defined as an unknown cause that induces a set of common symptoms for a group of patients. The proposed approach is based on a novel double feature allocation model which simultaneously allocates features to the rows and the columns of a categorical matrix. Using a Bayesian approach, available prior information on known diseases greatly improves identifiability of latent diseases. This includes known diagnoses for patients and known association of diseases with symptoms. We validate the proposed approach by simulation studies including mis-specified models and comparison with sparse latent factor models. In an application to Chinese electronic health records (EHR) data, we find results that agree with related clinical and medical knowledge.
The Mathematical Biosciences Institute (MBI) and ASA Columbus hosted a workshop on Bayesian Causal Inference from June 2-4, 2019 in Columbus, OH. The workshop’s goals were to promote the use of Bayesian methodology in causal reasoning, to present the latest theory and application developments of Bayesian framework/model in causal inference, and to discuss current and future research directions.
Tutorials were offered by Fan Li, Peter Muller and Steven MacEachern on June 2, and invited talks were presented by distinguished researchers on June 3-4.
Lecture by David Friedenberg, Dec 6, 2018
Abstract: Brain-computer interface (BCI) systems that directly link neural activity to assistive devices have shown great promise for improving the daily lives of individuals with paralysis. Using BCIs, individuals with tetraplegia have demonstrated control of computer cursors, robotic arms, communication devices, and their own paralyzed limbs through imagined movements. In anticipation of these technologies transitioning from the laboratory setting to everyday usage, several groups have surveyed potential BCI users to identify patient priorities and desired characteristics for a clinically viable BCI. This talk will focus on the neural decoding algorithms used in BCIs and how careful algorithm choices can help meet patient requirements, moving the field closer to devices that can help patients. We will discuss recent results using statistical and machine learning methods to decode neural activity enabling a paralyzed man to regain partial control of his hand. This work is part of a clinical trial that is jointly led and funded by Battelle and The Ohio State University Wexner Medical Center.
Lecture by Don Rubin, June 13, 2018
Abstract: When motivating the use of randomized experiments that are more complicated than pure randomized ones, it is natural to begin by describing bad allocations that can occur with complete (pure) randomization; for example, all women get treated, all men get control, which can be avoided by blocking on the covariate sex. But what to do with many covariates? Computers now let us examine many allocations and discard the unappealing ones, thereby effectively randomly choosing from an acceptable subset of allocations. This was an impossibility when classic experimental design books were written, more than a half century ago, but is certainly possible now. This presentation will summarize the applied implications of this work and current extensions.
Oct 26, 2017