Networks serve as a fundamental abstraction for characterizing complex dependencies and interaction structures in modern data analysis. In many scientific and applied settings, however, networks are not directly observed but must be inferred from high-dimensional, multimodal, and often incomplete data. This task poses significant statistical challenges regarding identifiability, estimation consistency, and the validity of downstream inferential conclusions.

This Special Issue invites contributions that advance statistically rigorous approaches to network construction and inference. We emphasize model-based formulations, principled estimation strategies, and theoretically grounded frameworks. Rather than treating networks as static or deterministic objects, this issue highlights the statistical nature of network estimation, including the propagation of uncertainty from data to inferred network structures and their implications for subsequent analysis.

We welcome submissions that develop methodological innovations, theoretical insights, or well-founded applications, provided that statistical reasoning and inferential rigor are central. Contributions that demonstrate careful empirical validation, meaningful comparison with existing statistical approaches, or thoughtful consideration of uncertainty, interpretability, and reproducibility are particularly encouraged.

Topics of Interest

Topics of interest include, but are not limited to:

l Statistical models and asymptotic theory for network reconstruction.

l Inference for dynamic, time-varying, or multi-layer network structures.

l Uncertainty quantification and false discovery rate control in network edges.

l Causal discovery and inference within complex interaction systems.

l Sparse and regularized estimation for high-dimensional precision matrices/graphs.

l Network inference under latent confounding, measurement error, or selection bias.

l Statistically grounded applications in biological, social, and environmental sciences.

Guest Editors

Dr. Yu Wang (Beijing Institute of Mathematical Sciences and Applications (BIMSA), China)
Dr. Nan Sun (Beijing Institute of Mathematical Sciences and Applications (BIMSA), China)

Deadline

The deadline for manuscript submissions is October 31st, 2026, but we can accommodate extensions on a case-by-case basis. All papers will be published as open-access articles upon acceptance.

Submission Instructions

Please submit the full manuscript to Statistics Innovation via our Submission System. Additionally, please choose a topic of this special issue when submitting and mention it in your cover letter. For further inquiries, please contact Guest Editor and Statistics Innovation Editorial Office(stati@maxapress.com).

Submissions should present original research or comprehensive reviews that emphasize statistical methodology or rigorous data-driven insights. Manuscripts focusing solely on algorithmic heuristics or visualization without formal statistical guarantees are discouraged.

All submissions will undergo the journal’s standard peer-review process.