“The importance of measurement and modeling for rigorous science”
Hosted by the Cognitive, Computational and Systems Neuroscience Pathway (CCSN)
After registering, you will receive a confirmation email containing information about joining the meeting.
Agenda:
2:30—3:30 pm CDT: Presentation
3:30—4:00 pm CDT: Q & A, prioritizing trainees
Abstract: With the advent of powerful machine learning methods and massive datasets, it is easy for researchers to forget that these data are measurements of an underlying reality and that all measurements are subject to both systematic error (bias) and unsystematic measurement error (noise). Understanding the sources of bias and noise are critical to properly modeling the data in order to ensure valid and reliable inferences. I will discuss the fundamental measurement concepts of reliability and validity, along with a causal framework for developing valid statistical models.
Short Bio: Russell A. Poldrack is the Albert Ray Lang Professor in the Department of Psychology at Stanford University, Director of the Stanford Center for Open and Reproducible Science, and Associate Director of Stanford Data Science. He received his PhD from the University of Illinois at Urbana-Champaign, and did postdoctoral work at Stanford. His research uses neuroimaging to understand the brain systems underlying decision making and executive function. His lab is also engaged in the development of neuroinformatics tools to help improve the reproducibility and transparency of neuroscience, including the Openneuro.org and Neurovault.org data sharing projects and the Cognitive Atlas ontology.
For inquiries contact Dennis Barbour.
