The FTC Webinar Series was held during 2020-2021 in place of the in-person conference due to the COVID-19 pandemic. Below are recordings of the presentations from the 2021 webinar series. Click the link below to see the recorded presentations from the 2020 webinar series.
See the 2020 Webinar Recordings here!
FTC Plenary – Youden Address
Speaker: Michael Hamada (Los Alamos National Laboratory)
Abstract: From reading Youden’s books and papers, Youden (1900-1971), an analytical chemist (1924 PhD), becomes an applied statistician by the time he joins the National Bureau of Standards (NBS) in 1948. This talk traces his transition from chemist to applied statistician and what his body of work mostly at NBS (1948-1965) demonstrates about the practice of statistics and the role that applied statistical research plays in it. There is much we can learn from a master applied statistician.
STAT – Bisgaard Award
Speaker: Nathaniel Stevens (University of Waterloo)
Abstract: In this work, we describe a quantitative approach for comparing the reliability or survival functions for two populations. The Bayesian probability of agreement (BPA) quantifies the similarity of the functions in regions of interest in the covariate space while accounting for a user-specified measure of what constitutes a practically important difference. The BPA method can be flexibly used for relationships with any number of covariates and for a variety of parametric models, including Weibull, lognormal and gamma regression. We provide an R Shiny app that allows practitioners to easily use the method without the need to implement the underlying computational details. Three examples from industrial and medical applications illustrate the implementation of the method as well as how to interpret the results from the analysis.
FTC Plenary – Past ASA President’s Address
Speaker: Wendy Martinez (Bureau of Labor Statistics)
Title: The Importance of Data Ethics
Abstract: I have had the honor of giving talks on data ethics at various events around the world, including the US, Bangladesh, Hong Kong, and Japan. These talks sparked very interesting conversations about the ethical use of data. These conversations made me realize that statisticians and data scientists must be intentional in our application of ethical guidelines for statistical practice. I also learned that data ethics is something we all need to worry about, regardless of where we work and live in the world. I will begin my presentation by offering my definition of data ethics and will then provide a few real-world examples where ethical concerns arose. I will conclude the discussion by providing examples of data ethics frameworks and efforts from around the world.
STAT – Nelson Award
Speaker: V. Roshan Joseph (Georgia Institute of Technology)
Title: Designing computer experiments with multiple types of factors: The MaxPro approach
Abstract: Computer experiments may involve not only continuous input factors but also nominal factors, discrete numeric factors, and ordinal factors. Most existing literature in designing computer experiments focuses only on continuous factors. Some works have further considered nominal factors, but the cases that also contain discrete numeric or ordinal factors are almost overlooked. In this work, we propose a new optimal design criterion that can accommodate all these types of factors. The proposed design is flexible in run size and number of factors, and can also achieve good space-filling properties in the full design space and in all possible low-dimensional projections.
Q&P – Hahn Award
Speaker: Christine Anderson-Cook (Retired, Los Alamos National Laboratory)
Title: Practical Necessity as the Mother of Statistical Innovation
Abstract: Gerry Hahn is a leading voice in applied statistics and was a pioneer at GE who had a great impact on quality and innovation through the development and incorporation of innovative statistical practices. In this talk, I present several examples of applications driving innovative statistical contributions during my career. The need to compare and discuss the predictive performance of alternative designs inspired the development of the Fraction of Design Space plot. The frequency with which experiments presented unexpected surprises drove the need to step back from traditional optimal designs and consider multiple objectives with a Pareto front. Expensive, high consequence experiments motivated the development of new strategies for Sequential Design of Experiments using non-standard space-filling designs capable of incorporating the latest knowledge about the process. Lastly, collaboration with colleagues across many different scientific and engineering disciplines has taught me that only having great statistical expertise is not enough to be an effective collaborator. The ability to connect, lead, persuade and facilitate discussion to reach consensus about how to tackle and solve challenging problems is a game-changer for statisticians to have a larger impact and be accepted as valued members of interdisciplinary teams.
CPID – Youden Prize
Speaker: Chris Nachtsheim (University of Minnesota), Daniel Eck (University of Illinois, Urbana-Champaign), Thomas Albrecht (University of Minnesota)
Title: Multivariate Design of Experiments for Engineering Dimensional Analysis
Abstract: We consider the design of dimensional analysis experiments when there is more than a single response. We first give a brief overview of dimensional analysis experiments and the dimensional analysis (DA) procedure. The validity of the DA method for univariate responses was established by the Buckingham Theorem in the early 20th century. We extend the theorem to the multivariate case, develop basic criteria for multivariate design of DA and give guidelines for design construction. Finally, we illustrate the construction of designs for DA experiments for an example involving the design of a heat exchanger.
STAT – Hunter Award
Speaker: Bradley Jones (JMP)
Title: The Joy of Collaboration
Abstract: One myth about genius is that of the solitary scientist and the “Ah Ha moment”. There is Archimedes and his “Eureka!” in the bathtub. There is Isaac Newton bonked on the head with an apple leading to the laws of gravity. There is Edison and the light bulb. In my view, these apocryphal stories are counterproductive. This is especially true nowadays as most if not all scientific and engineering work is done in teams.
My own work in statistics and design of experiments has almost always been in collaboration. Personally, I vastly prefer this mode of work because I have found that two heads are indeed better than one.
This talk will pay homage to my many collaborators with a goal of empowering others to seek out collaboration as a joyful mode of work.
SPES– SPES Award
Speaker: Jon Stallrich (North Carolina State University)
Title: Optimal EMG Sensor Placement for Robotic Prosthetics with Sequential Adaptive Functional Estimation
Abstract: Robotic hand prostheses are capable of translating multiple forearm electromyography (EMG) signals into finger and wrist movement through a control strategy. Training the control strategy involves an analysis of concurrent, longitudinal movement and EMG data collected across many forearm muscles, producing highly correlated EMG signals. To improve the prosthetic’s prediction accuracy and stability, we want to identify a control strategy that requires as few EMG signals as possible. We develop a control strategy based on a novel EMG-based functional linear model that accounts for the underlying biomechanics of hand movement, leading to natural, continuous movement of the prosthetic. The model is made parsimonious and interpretable through our proposed Sequential Adaptive Functional Estimation (SAFE) procedure motivated by the adaptive and relaxed group LASSO techniques. SAFE is shown to identify clinically important EMG signals with negligible false positive rates for an able-bodied subject.
CPID – Wilcoxon Award
Speaker: Tony Pourmohamad (Genentech)
Title: The Statistical Filter Approach to Constrained Optimization
Abstract: Expensive black box systems arise in many engineering applications but can be difficult to optimize because their output functions may be complex, multi-modal, and difficult to understand. The task becomes even more challenging when the optimization is subject to multiple constraints and no derivative information is available. In this work, we combine response surface modeling and filter methods in order to solve problems of this nature. In employing a filter algorithm for solving constrained optimization problems, we establish a novel probabilistic metric for guiding the filter. Overall, this hybridization of statistical modeling and nonlinear programming efficiently utilizes both global and local search in order to quickly converge to a global solution to the constrained optimization problem. To demonstrate the effectiveness of the proposed methods, we perform numerical tests on a synthetic test problem, a problem from the literature, and a real-world hydrology computer experiment optimization problem.