Structural Equation Models as Computation Graphs
Author(s) / Creator(s)
van Kesteren, Erik-Jan
Oberski, Daniel
Abstract / Description
Structural equation modeling (SEM) is a popular tool in the social and behavioural sciences, where it is being applied to ever more complex data types. The high-dimensional data produced by modern sensors, brain images, or (epi)genetic measurements require variable selection using parameter penalization; experimental models combining disparate data sources benefit from regularization to obtain a stable result; and genomic SEM or network models lead to alternative objective functions. With each proposed extension, researchers currently have to completely reformulate SEM and its optimization algorithm -- a challenging and time-consuming task. In this talk, I consider each SEM as a computation graph, a flexible method of specifying objective functions borrowed from the field of deep learning. When combined with state-of-the-art optimizers, our computation graph approach can extend SEM without the need for bespoke software development. I show that both existing and novel SEM improvements follow naturally from our approach. To demonstrate, I discuss least absolute deviation estimation and penalized SEM. By applying computation graphs to SEM, we hope to greatly accelerate the process of developing SEM techniques, paving the way for new applications.
Persistent Identifier
Date of first publication
2019-10-16
Publisher
ZPID (Leibniz Institute for Psychology Information)
Citation
Van Kesteren, E.-J., & Oberski, D. (2019, October 16). Structural Equation Models as Computation Graphs. ZPID (Leibniz Institute for Psychology Information). https://doi.org/10.23668/PSYCHARCHIVES.2634
-
2019Vankesteren16Okt-1.m4vUnknown - 205.73MBMD5: e69a0eb64955e7290ed595f521b8a892
-
There are no other versions of this object.
-
Author(s) / Creator(s)van Kesteren, Erik-Jan
-
Author(s) / Creator(s)Oberski, Daniel
-
PsychArchives acquisition timestamp2019-10-29T14:21:03Z
-
Made available on2019-10-29T14:21:03Z
-
Date of first publication2019-10-16
-
Abstract / DescriptionStructural equation modeling (SEM) is a popular tool in the social and behavioural sciences, where it is being applied to ever more complex data types. The high-dimensional data produced by modern sensors, brain images, or (epi)genetic measurements require variable selection using parameter penalization; experimental models combining disparate data sources benefit from regularization to obtain a stable result; and genomic SEM or network models lead to alternative objective functions. With each proposed extension, researchers currently have to completely reformulate SEM and its optimization algorithm -- a challenging and time-consuming task. In this talk, I consider each SEM as a computation graph, a flexible method of specifying objective functions borrowed from the field of deep learning. When combined with state-of-the-art optimizers, our computation graph approach can extend SEM without the need for bespoke software development. I show that both existing and novel SEM improvements follow naturally from our approach. To demonstrate, I discuss least absolute deviation estimation and penalized SEM. By applying computation graphs to SEM, we hope to greatly accelerate the process of developing SEM techniques, paving the way for new applications.en
-
CitationVan Kesteren, E.-J., & Oberski, D. (2019, October 16). Structural Equation Models as Computation Graphs. ZPID (Leibniz Institute for Psychology Information). https://doi.org/10.23668/PSYCHARCHIVES.2634en
-
Persistent Identifierhttps://hdl.handle.net/20.500.12034/2253
-
Persistent Identifierhttps://doi.org/10.23668/psycharchives.2634
-
Language of contenteng
-
PublisherZPID (Leibniz Institute for Psychology Information)en
-
Is part ofZPID-Kolloquium 2019, Trier, Germany
-
Is related tohttps://doi.org/10.23668/psycharchives.2623
-
Is related tohttps://arxiv.org/abs/1905.04492v2
-
Dewey Decimal Classification number(s)150
-
TitleStructural Equation Models as Computation Graphsen
-
DRO typemovingImageen
-
DRO typeconferenceObjecten
-
Visible tag(s)ZPID video portalen
-
Visible tag(s)ZPID Conferences and Workshops