This is a Preprint and has not been peer reviewed. This is version 2 of this Preprint.

Validating causal inference in time series models with conditional-independence tests
Downloads
Authors
Abstract
Ecologists often use time-series models to approximate dynamics arising from density dependence, species interactions, community synchrony, and other processes. Dynamic structural equation models can represent simultaneous and lagged interactions among variables with missing data, and therefore encompasses a wide family of analyses (linear regression, vector autoregressive models, and dynamic factor analysis). However, their interpretation as structural causal models (i.e., counterfactual analysis) requires validating that the assumed dynamics are consistent with available data. In site-replicated and phylogenetic contexts, ecologists ... more
DOI
https://doi.org/10.32942/X29627
Subjects
Ecology and Evolutionary Biology, Environmental Sciences, Marine Biology, Natural Resources and Conservation, Population Biology, Sustainability
Keywords
structural causal model, autoregressive, Time-series, directional separation, d-sep, conditional independence, dynamic structural equation model
Dates
Published: 2025-03-17 11:33
Older Versions
License
CC-BY Attribution-NonCommercial-ShareAlike 4.0 International
Additional Metadata
Conflict of interest statement:
None
Data and Code Availability Statement:
Data for the pollock spawning phenology case study are from Rogers et al. (2025), available online at https://github.com/larogers123/spawn_timing_catchability. Data for the Isle Royale are from https://www.isleroyalewolf.org/, and we use the copy available in package dsem. Code to reproduce case studies and the simulation experiment are available via GitHub (https://github.com/James-Thorson-NOAA/dsep_in_dsem).
Language:
English
There are no comments or no comments have been made public for this article.