Lianyan Fu, Rui Wang, Zihan Zhang
arXiv 28 May 2026 · Econometrics
arXiv:2605.29238 · PDF · DOI · OpenAlex · Extracted main text
This paper proposes a generalized Mundlak estimator based on graph neural networks (GME-GNN). The estimator is designed to mitigate bias arising from group-level heterogeneity and to accommodate within-group dependence among individuals. Traditional fixed-effects models handle group heterogeneity via group-specific intercepts, but require overly strict linear additivity and intra-group independence assumptions, and are confined to within-group comparisons. Rather than relying on intercepts, GME-GNN uses aggregated group-level balancing statistics to fully control between-group confounding, enabling valid cross-group comparisons and relaxing linearity constraints. It further employs graph neural network message-passing to adaptively learn nonlinear representations and capture intra-group interaction effects. Theoretical analysis shows that the estimator satisfies double robustness and is asymptotically normal. Simulation and empirical studies confirm its performance.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Leung, Michael P and Loupos, Pantelis (2022) Graph neural networks for causal inference under network confounding | 1.000 | 9 | 3 | 100% |
| 2 | Kojevnikov, D. and Marmer, V. and Song, K (2021) Limit Theorems for Network Dependent Random Variables | 1.000 | 6 | 3 | 100% |
| 3 | Arkhangelsky, Dmitry and Imbens, Guido W (2024) Fixed effects and the generalized Mundlak estimator | 0.874 | 9 | 2 | 100% |
| 4 | Mundlak, Yair (1978) On the pooling of time series and cross section data | 0.644 | 2 | 2 | 100% |
| 5 | Leung, Michael P (2022) Causal inference under approximate neighborhood interference | 0.585 | 3 | 1 | 100% |
| 6 | Wainwright, Martin J and Jordan, Michael I (2008) Graphical models, exponential families, and variational inference | 0.511 | 2 | 1 | 100% |
| 7 | Neyman, J. and Scott, E. L (1948) Consistent Estimates Based on Partially Consistent Observations | 0.405 | 1 | 1 | 100% |
| 8 | Altonji, Joseph G and Elder, Todd E and Taber, Christopher R (2005) Selection on observed and unobserved variables: Assessing the effectiveness of Catholic schools | 0.405 | 1 | 1 | 100% |
| 9 | Barron, Andrew R and Sheu, Chyong-Hwa (1991) Approximation of density functions by sequences of exponential families | 0.405 | 1 | 1 | 100% |
| 10 | Corso, G. and Cavalleri, L. and Beaini, D. and Liò, P. and Veli ckov… (2020) Principal Neighbourhood Aggregation for Graph Nets | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 22 scored citations.