Video: MP4; File size: 707 MB; Duration: 01:08:00
The talk will explore a conundrum related to policy/intervention focused system dynamics models. Although making predictions is fraught with risk, in order to compare alternative policies or interventions we must run our models into the future. Before doing so, I believe we must test the capability of our model to calculate credible future trajectories. This means we must hold back some of the available data or wait for the future to manifest. The latter we might have to wait for years before putting our model to use. The former is almost as difficult because we nearly always claim that the recent past includes the best clues about what is about to happen next. But isn’t the thing we need to know the most about our model is whether or not it contains sufficient endogenous logic so as not to depend too heavily on the most recent data points? I assert that we absolutely must hold back at least a few of the recent data points, by which I mean we must fully blind ourselves to that data, and then calibrate our model without any knowledge of the most recent data points. Initially when doing manual calibration, and also when using optimization-based calibrations or machine learning techniques. We must then measure the capability of our model with respect to the held back data points.
Wayne Wakeland is Professor and Systems Science Program Chair at Portland State University. He earned a B.S. and a Master of Engineering at Harvey Mudd College (1973); and a Ph.D. in Systems Science at Portland State U. (1977). His current research focuses on recovery from concussion; health policy related to drug diversion, abuse and treatment; applied data mining; and environmental/ecological sustainability..
Speculative Realism -- Problem Solving, Systems Science, Forecasting -- Simulation methods
© 2023 Wayne Wakeland
© Copyright the author(s) IN COPYRIGHT: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
DISCLAIMER: The purpose of this statement is to help the public understand how this Item may be used. When there is a (non-standard) License or contract that governs re-use of the associated Item, this statement only summarizes the effects of some of its terms. It is not a License, and should not be used to license your Work. To license your own Work, use a License offered at https://creativecommons.org/
Wakeland, Wayne, "Prediction and Policy/Intervention Analysis" (2023). Systems Science Friday Noon Seminar Series. 129.