Integrating spatial models in meta-regression analysis: unveiling network effects
Meta-regression analysis (MRA) has a long-standing history in literature and publication bias. However classical frameworks systematically overlook the network dependencies and spatial-type interactions. This paper addresses this methodological gap by introducing a spatial approach into MRA. Utilising comprehensive datasets from previously published empirical studies, we construct spatial weight matrices, extending from first-order and second-order contiguity networks, to put forth unobserved co-authorship. Methodologically, we apply spatial diagnostics and extensive Monte Carlo simulations. This approach not only enables the analysis of publication bias, as traditionally done, but also investigates whether studies/estimations exhibit a networking effect. The results appear promising regarding the applicability of MRA to spatial models.
Authors
- M. Ensar Yeşilyurt (ORCID: https://orcid.org/0000-0001-5610-3146)
- Filiz Yeşilyurt (ORCID: https://orcid.org/0000-0003-1629-4747)
Publication Details
- Journal
- Figshare
- Published
- 2026-11-17
- DOI
- https://doi.org/10.6084/m9.figshare.35039068
- Primary Topic
- Spatial and Panel Data Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00