Webinars
Web-based training is becoming increasingly popular as a cost-effective alternative to live training courses. Let the training come through your computer so you don’t have to leave your work environment. If you work with a team of statisticians, register once and gather your colleagues in a conference room so you can view the training session together and maximize your professional development budgets
September 25, 2024 - 12:00 - 1:30 p.m. ET - "The Art of Data Privacy: An Introduction to Statistical Data Privacy and Confidentiality"
Presenter: Dr. Claire McKay Bowen
Recording available here and slides available here.
Abstract:
At what point does the sacrifice to our personal information outweigh the public good?
In a data-driven era, data users and researchers frequently leverage personal or confidential data to help policymakers make evidence-based, data-informed decisions, such as improving economic recovery or creating a more efficient COVID-19 vaccine distribution. However, access to confidential data comes with several privacy concerns, especially for underrepresented groups. Striking the right balance is crucial to avoid real disclosure risks that may not be obvious, like stalkers utilizing excessive location data or malicious parties learning sensitive medical information through linkable health or genetic data.
This talk will cover the importance of balancing these competing needs and walks through the issues the U.S. government and private sector must navigate when collecting and disseminating data. Specifically, the talk will answer the questions of what data privacy and confidentiality is, why should you care, what is being done now, and what are the future challenges using a famous piece of art.
Bio: Dr. Bowen is currently a senior fellow and the Statistical Methods Group Lead at the Urban Institute, researching methods of data privacy and confidentiality. She earned a Master’s and PhD at the University of Notre Dame. In 2021, the Committee of Presidents of Statistical Societies identified her as an em
erging leader in statistics for my technical contributions and leadership to statistics and the field of data privacy and confidentiality. I am also a member of the Census Scientific Advisory Committee, a committee member of the National Academies of Sciences, Engineering, and Medicine Approaches for Data Governance and Protecting Privacy, and an advisory board member of the Future of Privacy Forums.
July 24, 2024 - 12:00 - 1:30 p.m. ET - "An Overview of Statistical Data Integration in Health Policy"
Presenter: Dr. Susan Paddock
Recording available here and Slides available here.
Abstract: Data integration techniques leverage the relative strengths of input sources to obtain a blended source that is richer and more informative than any single component. This is important for health policy, as analyses typically rely on a variety of data sources, most of which were not designed for the intended research use case. These data sources include electronic health records, health care claims and other administrative data, surveys, and more. In this webinar, an overview of opportunities and challenges of statistical data integration to facilitate health policy analysis will be provided. The presentation will include the use of a data quality framework for structuring data quality assessments of candidate input data sources. The statistical techniques to be presented include combining probability surveys with nonprobability (convenience) sources, blending randomized controlled trial data with data representing ‘real world populations,’ small area estimation, and method for expanding the number of variables in a dataset via record linkage or statistical matching (data fusion). Motivating examples will be provided to illustrate concepts.
Bio: Susan Paddock is Chief Scientist and Executive Vice President at NORC at the University of Chicago. Her team at NORC includes statisticians, survey methodologists, data scientists, quantitative social scientists, and AI researchers who are engaged in projects for federal, other governmental, and private sector clients on topics that span multiple substantive research areas including education, health, global, and public affairs. Susan has published methodological developments in the areas of Bayesian methods, causal inference, hierarchical modeling, longitudinal data analysis, and missing data techniques. Susan has served on editorial boards for several journals, including Annals of Applied Statistics, Journal of the American Statistical Association, and Harvard Data Science Review. She is a fellow of the American Statistical Association (ASA) and was the recipient of the 2013 Mid-career Award of the Health Policy Statistics Section of the ASA. She is the 2024-2026 Vice President of ASA. Susan received her Ph.D. in statistics from Duke University and her BA in mathematics and biostatistics from the University of Minnesota.
May 22, 2024 - 12:00 - 1:30 p.m. ET - "Introduction to Record Linkage"
Presenter: Dr. Natalie Shlomo
Recording available here and slides available here.
Abstract: Record linkage brings together information from records in two or more data sources that are believed to belong to the same entity based on a common set of matching variables. Matching variables, however, can appear with errors and variations and the challenge is to link statistical entities when their data is subject to errors. I will describe the classic Fellegi and Sunter (1969) probabilistic record linkage framework. I will then present extensions and innovations that have been developed in recent years to improve on the original framework.
Bio: Dr. Natalie Shlomo is Professor of Social Statistics at the University of Manchester and publishes widely in topics under survey statistics and methodology. She has over 70 publications and refereed book chapters and a track record of generating external funding for her research. She is an elected member of the International Statistical Institute (ISI), a fellow of the Royal Statistical Society, a fellow of the Academy of Social Sciences and President 2023-2025 of the International Association of Survey Statisticians. She also serves on national and international Methodology Advisory Boards and editorial boards.
Homepage:https://www.research.manchester.ac.uk/portal/natalie.shlomo.html
March 6, 2024 - 12:00 - 1:30 p.m. ET - "Bayesian Variable Selection"
Presenter: Dr. Marina Vannucci
Recording available here and slides available here
Abstract: Bayesian variable selection has experienced substantial developments over the past 30 years with the proliferation of large data sets. Identifying relevant variables to include in a model allows simpler interpretation, avoids overfitting and multicollinearity, and can provide insights into the mechanisms underlying an observed phenomenon. Variable selection is especially important when the number of potential predictors is substantially larger than the sample size and sparsity can reasonably be assumed. In this webinar I will provide an overview of Bayesian methods for variable selection, including spike-and-slab priors and shrinkage priors. I will focus on regression settings and will discuss prior constructions that account for specific dependence structures in the covariates. I will also describe extensions of the models to non-Gaussian data. Throughout the talk, I will motivate the development of the models using specific applications from neuroimaging and genomics.
Bio: Dr. Vannucci is Noah Harding Professor of Statistics. She is also an adjunct faculty member of the UT M.D. Anderson Cancer Center, TX. Dr. Vannucci is generally interested in the development of Bayesian statistical models for complex problems and in applications to Science. She has contributed to methodological research on Bayesian variable selection techniques for linear settings, mixture models and graphical models, and to related computational algorithms. Her research is often motivated by real problems that need to be addressed with suitable statistical methods. She has a solid history of scientific collaborations and is particularly interested in applications of Bayesian inference to high-throughput genomics and to neuroscience and neuroimaging. Dr. Vannucci was the recipient of an NSF CAREER award in 2001. She is an elected Member of the International Statistical Institute (ISI), and an elected Fellow of the American Statistical Association (ASA), the Institute of Mathematical Statistics (IMS), the American Association for the Advancement of Science (AAAS), and the International Society for Bayesian Analysis (ISBA). She holds a Laurea (B.S.) in Mathematics and a Ph.D. in Statistics, both from the University of Florence, Italy.
December 13, 2023 - 12:00 - 1:30 p.m. ET "An Introduction to Time Series Analysis via Dynamic Linear Models"
Presenter: Hedibert Lopes
Recording available here and slides available here.
Abstract: This webinar will present an overview of dynamic linear models for analysis and forecasting of non-stationary time series. Topics that will be discussed include model building and methods for Bayesian filtering, smoothing and forecasting. The models and inference tools will be illustrated in the analysis of temporal datasets arising in different applied fields, including neuroscience and environmental science.
Bio: Hedibert Lopes has been Professor of Statistics and Econometrics at INSPER since 2013, where he also runs the Research Group of Statistics, Data Science and Decision. Between 2021-2023, he was Head of Statistics at the School of Mathematical and Statistical Sciences (SoMSS), Arizona State University (ASU) and between 2003-2013 he was Professor of Econometrics and Statistics at the University of Chicago Booth School of Business. Hedibert got his college and master education from UFRJ, where he was also a junior faculty between 1996-2003. He earned his PhD degree from Duke University in 2000. Hedibert has published more than 80 scientific papers in internationally acclaimed journals, such as JASA, Statistical Science, JBES, JCGS, Journal of Econometrics and American Economic Review, amongst many others. He co-authored the book "MCMC: Stochastic Simulation for Bayesian Inference", which currently has half of his ten thousand Google Scholar citations. Finally, he is the only Brazilian who is Fellow of the International Society for Bayesian Analysis (ISBA).
September 20, 2023 - "An Overview of Some Methods for Statistical Analysis with Missing Data"
Presenter: Rod Little
Recording available here and slides available here.
Abstract: Missing data are a common problem in statistics; examples include unit and item nonresponse in surveys, attrition in longitudinal data sets, and missing data arising from noncompliance to treatments in clinical trials. Topics include (a) pros and cons of common methods, specifically analysis of the complete cases, nonresponse weighting and extensions, maximum likelihood, Bayes and multiple imputation; (b) approaches to missing data when the data are potentially missing not at random; (c) subsample ignorable likelihood approaches for regression with missing data, which address particular missing not at random mechanisms by selectively omitting data; and (d) causal inference under noncompliance to treatments as a missing data problem.
Bio: Rod Little is Richard D. Remington Distinguished University Professor of Biostatistics at the University of Michigan, where he also holds appointments in the Department of Statistics and the Institute for Social Research. He has over 300 publications, notably on methods for the analysis of data with missing values and model-based survey inference, and the application of statistics to diverse scientific areas, including medicine, demography, economics, psychiatry, aging and the environment. Little is an elected member of the International Statistical Institute, a Fellow of the American Statistical Association and the American Academy of Arts and Sciences, and a member of the National Academy of Medicine. In 2005, Little was awarded the American Statistical Association’s prestigious Wilks Medal for research contributions, and he gave the President’s Invited Address at the Joint Statistical Meetings. He was the COPSS Fisher Lecturer at the 2012 Joint Statistics Meetings.
July 26, 2023 - "Introduction to Bayesian Modelling of Epidemics: From Population to Individual-level Models"
Presenter: Rob Deardon
Recording available here and slides available here
Abstract: With the onset of the COVID-19 pandemic, there has been an understandable increase in the interest in the mathematical and statistical modelling of infectious disease epidemics. The modelling of infectious disease spread through a population generally requires the use of non-standard statistical models. This is primarily because infection events depend upon the infection status of other members of the population (i.e. we cannot assume independence of infection events).
Typically, statistical inference for these models (e.g., parameter estimation) is done in a Bayesian context using computational techniques such as Markov chain Monte Carlo (MCMC). This is in part due to the non-standard form of the models, but also in part due to the fact that we often have missing or uncertain data; for example, infection times are rarely observed. Bayesian data augmentation provides a natural framework for allowing for such uncertainty.
Further complication is added by the fact that there are often complex heterogeneities in the population which we wish to account for, since, for example, populations do not tend to mix homogeneously. Sometimes, we may wish to account for such heterogeneities using spatial mechanisms that assume that transmission events are more likely to occur between individuals close together in space than individuals further apart. Sometimes, it is more natural to model such heterogeneities using contact networks that represent, for example, the sharing of supplier companies between farms.
Here, we will examine the main characteristics of both population-level and indivdiual-level infectious disease models, and how they can be fitted to data in a Bayesian MCMC framework.
Bio: Rob Deardon is a Professor of Biostatistics with a joint position in the Faculty of Veterinary Medicine and Department of Mathematics & Statistics at the University of Calgary. Much of his recent work has been in the area of infectious disease modelling, but he is also interested in Bayesian & computational statistics, experimental design, disease surveillance methods, spatio-temporal modelling and statistical learning. He currently has a research group consisting of 15 trainees, and has published 75+ papers in peer-reviewed journals. He has served as associate editor of a number of journals including the Journal of the Royal Statistical Society (Series C) and the Canadian Journal of Statistics. He is currently the Graduate Coordinator of the Interdisciplinary Biostatistics Graduate Program at Calgary, and has recently served a 2-year term as the Chair of the Statistics Section of the NSERC Discovery Grant Mathematics & Statistics Evaluation Group.
May 10, 2023 - "Causal inference in statistics: why, what, and how"
Presenters: Erica Moodie
Recording available here and slides available here.
Abstract: An introductory overview on the goals of causal inference, key quantities, and typical methods will be given for situations where an exposure of interest is set at a chosen baseline (“point exposure”) and the target outcome arises at a later time point, focusing on a binary outcome and continuous exposure. Using the potential outcomes framework, principled definitions of causal effects will be presented along with estimation approaches which invoke the no unmeasured confounding assumption.
Short bio: Erica E. M. Moodie is a Professor of Biostatistics at McGill University and a Canada Research Chair (Tier 1) in Statistical Methods for Precision Medicine. She obtained her MPhil in Epidemiology in 2001 from the University of Cambridge and a PhD in Biostatistics in 2006 from the University of Washington, before joining the faculty at McGill. Her main research interests are in causal inference and longitudinal data with a focus on precision medicine. She is the 2020 recipient of the CRM-SSC Prize in Statistics and an Elected Member of the International Statistical Institute. Dr Moodie serves as an Associate Editor of Biometrics and a Statistical Editor of Journal of Infectious Diseases. She holds a chercheur de merite career award from the Fonds de recherche du Quebec-Sante.
March 8, 2023 - "Positioning Household Surveys for the Next Decade: Data Integration and Inclusion"
Presenters: Talip Kilic and Papa Seck
Slides available here.
Recording available here.
Abstract: Established by the UN Statistical Commission in 2015, the Inter-Secretariat Working Group on Household Surveys (ISWGHS) aims to foster improvement in the scope and quality of social and economic statistics as delivered through national, regional and international household survey programmes. Three major objectives of ISWGHS are (a) fostering coordination; (b) promoting advancement and harmonization of survey methodologies; and (c) communicating the importance of household surveys.
As a collaborative group, ISWGHS is a platform to support the exchange of knowledge and experience among international agencies, national statistical offices, academic experts, the private sector and other key players. Such exchange will improve the flow of knowledge and experience among countries and assist in the scaling up of innovative approaches in countries with lower statistical capacity.
In guiding its support to countries in adopting innovative approaches and becoming more resilient to crises such as the COVID pandemic, ISWGHS prepared a paper on Positioning Household Surveys for the Next Decade (Position Paper). The webinar will focus on two of the eight technical priority areas identified by the Position Paper: Enhancing the interoperability and integration of household surveys and Designing and implementing more inclusive, respondent-centric surveys. The presentation will cover innovative approaches in these two areas, with examples from countries.
Short bios: Talip Kilic is the Program Manager in Data Production and Methods Unit Development Data Group at the World Bank. Talip’s research focuses on poverty, agriculture, and gender in low- and middle-income countries, as well as survey methodology to improve the quality, timeliness, and policy-relevance of household and farm surveys. Talip is originally from Istanbul, Turkey, and have a Ph.D. in Economics from American University in Washington, DC, and a Bachelor of Arts in Economics and International Relations from Knox College in Galesburg, IL.
Papa Seck is Chief, Research and Data Section at UN Women and co-Chair, Inter-Secretariat Working Group on Household Surveys. Since joining UN Women in 2009, he has led statistics and data work at UN Women. Prior to joining UN Women, Papa worked for UNDP as a statistics specialist, contributing to three global Human Development Reports. He holds a Master’s degree in Economics from Hunter College and is the co-editor of a book on the consequences of risk and vulnerability for human development.
December 8, 2022 - "Deep learning: opening the black box "
Presenter: Dr. Jennifer A. Hoeting, Hoeting Consulting
Slides Available here
Recording Available here
Abstract: Deep learning algorithms are often presented as black box algorithms. Many cartoon sketches of deep learning are available, but deep learning is rarely translated into the mathematical framework required by most statisticians to understand the topic. In this lecture we will open the black box and explore deep learning from a statistical viewpoint. In addition to an overview of the mathematics of deep learning, we will explore the types of problems when you might consider using a machine or deep learning algorithm and when traditional inferential statistical methods may be preferred. We will provide suggestions of how to get started applying machine and deep learning algorithms to your own data with links to recommended software. This lecture is intended for statisticians who want to learn about deep learning but have little previous exposure to it.
Short bio:
Jennifer A. Hoeting leads Hoeting Consulting. She is Professor Emeritus of Statistics at Colorado State University and Adjunct Professor of Statistics at University of California Santa Cruz. Hoeting's textbook, Computational Statistics (co-authored by Geof H. Givens), has been adopted as a course textbook at more than 120 universities in the US and over 30 other countries. Hoeting is an elected Fellow of the American Statistical Association and received the Distinguished Achievement Medal from the American Statistical Association’s Section on Statistics and the Environment.
September 21, 2022 - "An Introduction to Spatial Statistics with Applications to Disease Mapping"
Presenter: Dr. Alexandra M. Schmidt, Professor, McGill University, Canada
Slides and Resources available here.
Presentation Recording available here.
Abstract: This webinar will provide an introduction to the analysis of spatially structured data. It will introduce Spatial Statistics and focus on the analysis of data that vary over a discrete set of indices (areal data) as, for example, the number of registered cases of Covid-19 across the boroughs of Montreal. We will discuss conditional autoregressive models and how to perform inference procedure under the Bayesian paradigm. At the end of the webinar, participants will have learned how to
• fit conditional auto-regressive (CAR) models;
• fit areal level data using CARBayes in R;
• create disease maps.
Short bio:
Alex Schmidt is Professor of Biostatistics and holds the endowed University Chair in the Department of Epidemiology, Biostatistics and Occupational Health (EBOH) at McGill University. She is an Elected Fellow of the American Statistical Association (2020) and an Elected Member of the International Statistical Institute (2010). She was awarded the Distinguished Achievement Medal (2017) from the American Statistical Association’s Section on Statistics and the Environment and the Abdel El-Shaarawi Young Investigator Award (2008), from The International Environmetrics Society.
Presenter: Dr. Shirin Golchi, Assistant Professor, McGill University, Canada
July 20, 2022 - "An Introduction to Bayesian Inference"
Presentation recording is available here.
Slides and resources are available here.
Presenter: Dr. Shirin Golchi, Assistant Professor, McGill University, Canada
This webinar will provide an introduction to basic concepts in Bayesian inference. Topics that will be covered include essential components of Bayesian statistics, estimation and uncertainty quantification in single and multi- parameter linear and generalized linear models, as well as a brief introduction to Bayesian hierarchical modeling and Bayesian computation. The workshop will include examples of parametric inference in R using R-packages that rely on Stan (rstanarm and brms). At the end of this workshops participants will be able to: 1) Specify simple Bayesian models, 2) Make Bayesian inference in single parameter models, and 3) Fit linear and generalized linear models using rstanarm or brms.
Short bio
Dr. Shirin Golchi is an assistant professor in biostatistics with an interest and specialty in Bayesian modelling and computational methods. She looks for interesting problems where new statistical methodology together with efficient computational tools can help scientists answer important questions. She has worked on a variety of problems with applications in health sciences, physics, social sciences and mathematical biology.
May 11, 2022 - "An Introduction to Small Area Estimation"
- now available online via YouTube: https://youtu.be/8oXfYMSyqEc
-slides available here
-references available here
Presenter: Dr. Carolina Franco, Principal Statistician, NORC at the University of Chicago, USA
Small area estimation (SAE) techniques can lead to greatly improved estimates relative to direct survey estimates when there is a large number of domains of interest and a limited overall sample size, which is often the case in surveys. When successfully applied, SAE can dramatically reduce measures of uncertainty and provide estimates for domains with no survey data. It can allow for publishing of official estimates at lower levels of aggregation. We will discuss the following topics: What is small area estimation (SAE)? What are the potential benefits of SAE? Examples of real applications of small area estimation; An introduction to area-level and unit-level models;; Discussion of frequently used software; Where to learn more…
Short Bio
Dr. Carolina Franco is a Principal Statistician at NORC at the University of Chicago, specializing in small area estimation (SAE). Prior to moving to NORC last year, Dr. Franco spent many several years doing research and consulting at the US Census Bureau, where she worked on important SAE programs used for the production of official statistics, including the Small Area Income and Poverty Estimates (SAIPE) Program, and the Voting Rights Act, Section 203 determinations. She also has extensive experience giving seminars on SAE and has taught SAE through the Joint Program in Survey Methodology at the University of Maryland. She has published several papers on different aspects of SAE.
Other webinars
Visa and Sponsorship Workshop
Sponsors: GWU ASA Student Chapter & Washington Statistical Society
When: 14 April 2023 11-12:30 EDT
Recording available here.
Negotiating the visa and sponsorship process on top of looking and interviewing for jobs adds more uncertainty and anxiety. We will cover the different Curricular Practical Training (CPT) while you are in school, Optional Practical Training (OPT) and its extensions after graduation, and the H1B visa. Universities sponsor H1B for their faculty as is done at GWU.
There are many aspects to consider in the visa and sponsorship process. How to check if the company is willing to do sponsorships? When to bring this up? What can employers legally ask you in an interview? How do you track your sponsorship process? What about changing jobs and traveling outside the U.S.?
We will have 1) GWU International Student Office talk about GWU services; 2) An immigration lawyer, Hiba M. Anver, to cover the legal aspects; 3) two alumni to share their journeys; 4) a discussion of the employer perspective; and 5) questions and answers.
Other webinar series:
TIES Webinar Series (Environmental Statistics and Data Science)
American Statistical Association (ASA) Webinars
ASA's Committee on Career Development (CCD) Webinars
International Statistical Institute (ISI) Webinars