Welcome and Plenary Session (8:00-9:00AM)
Peter Parker, NASA Langley
Advancing the spread and practice of statistics enhances an organization’s ability to successfully achieve their mission. While there may be leadership mandates to employ statistical methods, often the spread of statistical concepts flourishes more effectively through the practice of statistical influence. At first glance, the term influence may seem to imply a passive and unenthusiastic posture toward promoting organizational change. However, a classical definition states that, “In a general sense, influence denotes power whose operation is invisible and known only by its effects, or a power whose cause and operation are unseen.” This definition articulates the powerful and yet subtle aspects of influence that embodies the theme of this presentation. Stated plainly, powerful statistical concepts become more widely known and engrained primarily through demonstrated impact; a strategy known only by its effects. In this presentation, elements of statistical influence are exemplified through practice at NASA.
Professor Raymond H. Myers Memorial Session
Douglas Montgomery (Arizona State University) and William Myers (Procter and Gamble)
Ray Myers was a member of the Virginia Tech statistics faculty for 44 Years. He made many contributions in the areas of experimental design, response surface methodology, linear models and generalized linear models, authoring many influential research papers and 6 books. He was honored by the American Society for Quality for his body of work with the Shewhart Medal in 1998. He served as an editorial board member for the Journal of Quality Technology and as an associate editor for Technometrics. He was a Fellow of the American Statistical Association and an elected member of the International Statistical Institute.
Ray is remembered by many as an outstanding, indeed gifted teacher. His classroom lectures were always insightful and brilliant. He received the William E. Wine Award for Teaching Excellence at Virginia Tech in 1980 and was named Virginia Professor of the Year in 1985. He was a member of the Virginia Tech Academy of Teaching Excellence. He was always involved in guiding others in the use of statistics in their own research, serving as the director of the Virginia Tech Statistical Consulting Center.
Ray’s classroom teaching was unequaled in the view of most of his students, but he was also an outstanding mentor. He directly advised 42 doctoral students and served on the dissertation committee for many more. There are five Virginia Tech “Hokies” who have received the Shewhart Medal, including Ray, but he was an important mentor to all of the other four. All of the other four recipients readily acknowledge that they would have never received their Shewhart Medals without him.
Ray Myers was a wonderful teacher, mentor, colleague and friend to many. He will be missed by our community.
Youden Address (4:00-5:00PM)
Latin Squares, Youden Squares, Balanced Incomplete Block Designs (BIBDs) and Extensions for Industrial Application
Bradley Jones, JMP Statistical Discovery LLC
Latin Squares are beautifully symmetric designs employing a given number of symbols in the same number of rows and columns. Each row and each column have all the symbols. A Youden Square, attributed to Jack Youden, is a Latin Square from which a number of rows have been removed. The Youden Square is a special case of a balanced incomplete block design (BIBD). All these designs have been around for decades. They support a single categorical factor and one or two blocking factors. They are commonly used in agriculture where the rows and columns are rows and columns of plants and it is desirable to remove any fertility gradients in a field in the analysis.
In industrial settings it is unusual for experiments to be limited to only one categorical factor and one or two blocking factors. However, it could be very useful to use these designs as building blocks for creating experiments in industry with more factors. This talk will show how to extend the above designs when there are continuous factors to explore.
News from ASA and Partnerships to Establish a System for Wastewater Epidemiology for Houston
Kathy Ensor, ASA President
ABSTRACT: The American Statistical Association is dedicated to the practice and profession of statistics, and I am honored to serve as its 117th President. I will provide updates on ASA and take this opportunity to discuss the expansion of the ASA Leadership Institute, activities in data science and AI, and my vision to promote growth in community analytics. Community analytics requires strong partnerships between local governments and businesses, NGOs, community organizations, and academia. I will embed my community analytics discussion in the story of developing from scratch the wastewater epidemiology program for the City of Houston to aid in the management of the SARS-CoV-2 pandemic. Wastewater surveillance has emerged as a vital tool for city, county, state, and national public health departments and its use will continue beyond the pandemic. For example, by examining SARS-CoV-2 RNA viral load, wastewater provides a strong signal of the extent of the virus present in a community. Measuring and modeling the evolution of the virus in a community is however fraught with many complexities. For Houston, the SARS-CoV-2 viral load is measured weekly at 39 wastewater treatment plants and approximately 100 other locations throughout the city. How to combine all this information into a system that informs decisions is the role that I have played in the multi-disciplinary and multi-institutional team. I will share the concepts behind building the statistical system as well as provide a deep dive into why the partnership succeeded and what is planned for the future.
Reception with SPES Special Panel Session (3:15-5:15PM)
Innovations in Industry 4.0
Panel discussion: Laura Freeman (Virginia Tech), Nathan Wycoff (Georgetown University), Arman Sabbaghi (Purdue University), and Mindy Hotchkiss (Rocketdyne)
ABSTRACT: Industrial manufacturing and logistics have greatly benefited from applications of statistical methodology, particularly experimental design and quality control. Industry 4.0 refers to the fourth industrial revolution sparked by integration of machine learning and artificial intelligence in manufacturing and logistics. Examples of Industry 4.0 include Industrial Internet of Things, cyber physical systems, and cyber manufacturing. The shift towards more automated and fast-paced systems relies on collaborations between experienced data scientists, statisticians, and engineers. This panel represents different perspectives and experiences on the current and future state of Industry 4.0.