From Data to Causes: Perspectives on Causation from Psychology, Physics, and Dynamical Systems скачать в хорошем качестве

From Data to Causes: Perspectives on Causation from Psychology, Physics, and Dynamical Systems

Instats.com now has world-leading statistics and research methods workshops available for livestreaming and on-demand delivery. Head over to Instats.com to see all of their current offerings. This talk by Pascal Deboeck was delivered to the two-day online workshop 'From Data to Causes' sponsored by Humboldt University of Berlin, the University of Melbourne, and the Berlin University Alliance on October 6th and 7th, 2021. Additional information is below. TITLE: From Data to Causes: Perspectives on Causation from Psychology, Physics, and Dynamical Systems ABSTRACT: Causality, by definition, implies change across time. The difficulty making inferences about constructs that change across time are perhaps clearest in the mediation literature. In the mediation literature it has been demonstrated that inferences about longitudinal processes based on cross-sectional data are typically a poor reflection of the underlying processes. The latter is particularly true when it is not possible to implement experimental designs to detangle causes and effects, as is the case in many areas of psychology. Longitudinal data thus becomes essential for understanding the relations in a system of inter-connected components, whether those components consist of differing constructs or people. This presentation will begin by introducing a common longitudinal model for mediation, the cross-lagged panel model, and build to introducing a continuous-time counterpart. Through study of aspects of these models it will be highlighted that when working with longitudinal data it becomes necessary for any inference to carefully consider how time should be treated, explore the relations between components of a system, and consider that causation could imply effects that are not typically expected. BIO: Pascal Deboeck is an associate professor at the University of Utah. Trained as a quantitative psychologist, he works to develop, improve, study and apply statistics to social science and medical data. His interests are focused on the development and application of methods for the analysis of intensive, intraindividual time series. In particular he focuses on the development and application of derivatives, differential equation modeling, and dynamical systems concepts to time series that have characteristics common to behavioral and some physiological measures such as relatively low sampling rates, large amounts of measurement and/or dynamic error, and unequally spaced or missing observations. In analyzing such data, he often focuses on questions related to the role of variability and less-stable change (the “error” in many statistical models). These methods have the potential to inform theories that address how, when and why people change over time. He has worked with a range of applied topics including: resiliency and affect in older adults, health and depression as long-term outcomes of daily stress processing, sustained attention while driving, adult attachment, the coupling of maternal depression with child behavior, modeling of proteins associated with Alzheimer's, mood change in patients with rapid cycling bipolar disorder, and the motion of dancing individuals and dyads. See more: https://psych.utah.edu/people/faculty...