![[On Demand] Knowing What You Don’t Know: Prediction by Itself Is Never Enough](https://predictum.com/wp-content/uploads/2023/03/pexels-linkedin-sales-navigator-2182974-scaled.jpg)
In science and engineering fields, failing to account for uncertainty turns confidence into overconfidence. That’s when mistakes happen.
In this webcast, Predictum’s Philip Ramsey, Ph.D., explores how to recognize and quantify uncertainty in predictive modeling.
This session will further explore the how traditional statistical methods fail to provide experts with accurate predictions regarding complex physical systems found in product and process development, and how advances in small experimental designs with machine learning can restore highly accurate, reliable prediction.
Whether you’re improving product formulations, designing manufacturing processes, or advancing research in applied science, tune in and learn how you can:
- Discover practical tools in SVEM 2.0 for quantifying prediction uncertainty
- Learn how to interpret and act on uncertainty estimates
- Build more reliable models that reflect the real complexity of your system
- Identify why traditional data collection and modeling methods fail to provide reliable uncertainty estimates across design spaces, that improve the accuracy of predictions
Presenters:
In addition, Phil is a Professor in the Department of Mathematics and Statistics at the University of New Hampshire (UNH) where he teaches courses at the undergraduate and graduate levels in design of experiments, machine learning, and statistical methods for quality improvement. He has held the following relevant industrial positions: Senior Engineer for Materials and Processes Development, McDonnell Douglas, St. Louis, MO; Staff Scientist/Statistician, Alcoa Technical Center, Pittsburgh, PA; and Statistician/Senior Engineer, Rohm & Haas Electronic Materials (now Dow), Marlboro, MA.
Phil holds a Ph.D. in statistics from Virginia Polytechnic Institute and State University.
Webinar resources and contact info:
EPISODE LINKS:
Phil Ramsey’s work profile: https://predictum.com/company/#leadership
Predictum SVEM Product Page: SVEM
SVEM Frequently Asked Questions: Frequently Asked Questions about SVEM
Free SVEM Micro-Course: https://courses.predictum.com/courses/build-better-and-faster-with-small-experimental-designs-and-machine-learning
PEER-REVIEWED RESEARCH ON SVEM:
- T. Lemkus, P.J. Ramsey, C. Gotwalt, and M. Weese, “Self-Validated Ensemble Models for Design of Experiments” (research paper, arXiv.org, Cornell University, 2021).
- Eliza Yeung and Philip J. Ramsey, “Optimization of a conventional glycosylation analytical method using machine learning and experimental design.” (research paper, BioProcess J, 2021; 20).
- Danial Mirzaiyanrajeh, Eshan V. Dave, Jo E. Sias, and Philip Ramsey. “Developing a prediction model for low-temperature fracture energy of asphalt mixtures using machine learning approach.” (research paper, International Journal of Pavement, 2022).
CONTACT:
Predictum Inc – Contact Predictum
SOCIAL LINKS:
LinkedIn (Phil Ramsey): https://www.linkedin.com/in/philip-ramsey-a175148/
LinkedIn (Nathaniel Leies): https://linkedin.com/in/nathanielleies
LinkedIn (Predictum Inc.): https://linkedin.com/company/predictum
Try Predictum SVEM for Free (30-Day Evaluation License)
Requires active JMP License. Try JMP for free at jmp.com.
