B1390
Title: Incorporating knowledge into structural equation models using auxiliary variables
Authors: Bryant Chen - UCLA (United States) [presenting]
Judea Pearl - UCLA (United States)
Elias Bareinboim - Purdue University (United States)
Abstract: A new framework, called auxiliary variables (AVs), is introduced. It extends graph-based identification methods for linear models by allowing background knowledge in the form of externally evaluated parameters. Such information could be obtained, for example, from a previously conducted randomized experiment, from substantive understanding of the domain, or even from another identification technique. To incorporate such information systematically, AVs are constructed so that certain paths will be conveniently cancelled. This cancellation allows the AVs to help conventional methods of identification (e.g. single-door criterion, instrumental variables, instrumental sets) and model testing (e.g. d-separation, over-identification). Moreover, by iteratively alternating steps of identification and adding AVs, we can improve the power of existing identification and model testing methods, even without additional knowledge. We have operationalized this general approach for instrumental sets (a generalization of instrumental variables) and show that the resulting procedure subsumes the most general identification method for linear systems known to date. We further discuss the application of this new operation in the tasks of model testing and z-identification.
Journal