Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling Choices

Specifying complex time series models typically allows for a wide range of plausible analysis strategies. However, researchers typically perform and report only a single, preferred analysis while ignoring alternatives that could yield different conclusions. As a remedy, we propose multiverse analysi...

Full description

Saved in:
Bibliographic Details
Main Authors: Björn S. Siepe, Daniel W. Heck
Format: Article
Language:English
Published: PsychOpen GOLD/ Leibniz Institute for Psychology 2025-06-01
Series:Methodology
Subjects:
Online Access:https://doi.org/10.5964/meth.15665
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849408290770911232
author Björn S. Siepe
Daniel W. Heck
author_facet Björn S. Siepe
Daniel W. Heck
author_sort Björn S. Siepe
collection DOAJ
description Specifying complex time series models typically allows for a wide range of plausible analysis strategies. However, researchers typically perform and report only a single, preferred analysis while ignoring alternatives that could yield different conclusions. As a remedy, we propose multiverse analysis to investigate the robustness of dynamic network analysis to arbitrary modeling choices. We focus on group iterative multiple model estimation (GIMME), a highly data-driven approach, and re-analyze two datasets (combined n = 199). We vary seven modeling parameters, resulting in 3,888 fitted models. Group-level and to a lesser extent subgroup-level results were mostly stable. Individual-level estimates were more heterogeneous, with some decisions strongly influencing results and conclusions. The robustness of GIMME to alternative modeling choices depends on the level of analysis. For some individuals, results may differ strongly even when changing the algorithm only slightly. Multiverse analysis is a valuable tool for checking the robustness of results from time series models.
format Article
id doaj-art-3f4ef214d2154d80be3c3f4e003af6cd
institution Kabale University
issn 1614-2241
language English
publishDate 2025-06-01
publisher PsychOpen GOLD/ Leibniz Institute for Psychology
record_format Article
series Methodology
spelling doaj-art-3f4ef214d2154d80be3c3f4e003af6cd2025-08-20T03:35:50ZengPsychOpen GOLD/ Leibniz Institute for PsychologyMethodology1614-22412025-06-0121212314310.5964/meth.15665meth.15665Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling ChoicesBjörn S. Siepe0https://orcid.org/0000-0002-9558-4648Daniel W. Heck1https://orcid.org/0000-0002-6302-9252Psychological Methods Lab, Department of Psychology, University of Marburg, Marburg, GermanyPsychological Methods Lab, Department of Psychology, University of Marburg, Marburg, GermanySpecifying complex time series models typically allows for a wide range of plausible analysis strategies. However, researchers typically perform and report only a single, preferred analysis while ignoring alternatives that could yield different conclusions. As a remedy, we propose multiverse analysis to investigate the robustness of dynamic network analysis to arbitrary modeling choices. We focus on group iterative multiple model estimation (GIMME), a highly data-driven approach, and re-analyze two datasets (combined n = 199). We vary seven modeling parameters, resulting in 3,888 fitted models. Group-level and to a lesser extent subgroup-level results were mostly stable. Individual-level estimates were more heterogeneous, with some decisions strongly influencing results and conclusions. The robustness of GIMME to alternative modeling choices depends on the level of analysis. For some individuals, results may differ strongly even when changing the algorithm only slightly. Multiverse analysis is a valuable tool for checking the robustness of results from time series models.https://doi.org/10.5964/meth.15665time seriesnetwork analysismultiverseheterogeneitygimme
spellingShingle Björn S. Siepe
Daniel W. Heck
Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling Choices
Methodology
time series
network analysis
multiverse
heterogeneity
gimme
title Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling Choices
title_full Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling Choices
title_fullStr Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling Choices
title_full_unstemmed Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling Choices
title_short Multiverse Analysis for Dynamic Network Models: Investigating the Influence of Plausible Alternative Modeling Choices
title_sort multiverse analysis for dynamic network models investigating the influence of plausible alternative modeling choices
topic time series
network analysis
multiverse
heterogeneity
gimme
url https://doi.org/10.5964/meth.15665
work_keys_str_mv AT bjornssiepe multiverseanalysisfordynamicnetworkmodelsinvestigatingtheinfluenceofplausiblealternativemodelingchoices
AT danielwheck multiverseanalysisfordynamicnetworkmodelsinvestigatingtheinfluenceofplausiblealternativemodelingchoices