Contrast-Space Projection for Network Meta-Analysis: An Exact and Invariant Study-Based Decomposition of Direct and Indirect Contributions

arXiv:2604.21994 · stat.ME, stat.AP, stat.CO, stat.ML · Submitted 2026-04-23 · Read on arXiv

stat.ME, stat.AP, stat.CO, stat.ML

Submitted: 2026-04-23

Updated: 2026-08-30

Comments: 43 pages, 6 figures. Revised version with expanded theoretical development, clarification of the representation-invariant study-based direct and indirect decomposition, additional results on canonical reduction and path construction, revised generalized Cochran Q diagnostics, and updated empirical illustrations and exposition

Code: https://github.com/chongwangstat/CSP-NMA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 28× in this paper · explained in 3 episodes
• Redundancy — 10× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Pairwise Comparisons — 4× in this paper · explained in 2 episodes
• Aggregation — 3× in this paper · explained in 1 episode
• Diagnostic Tools — 2× in this paper · explained in 2 episodes
• Fisher Information — 2× in this paper · explained in 3 episodes
• Additive Decomposition — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Related papers

• Doubly robust inference via calibration
• Bayesian Empirical Bayes: Simultaneous Inference from Probabilistic Symmetries
• Weak-Form Recovery of Stochastic Generators
• Optimal Watermark Localization in Mixed-Source Large Language Model Texts
• Optimized Conformal Selection: Powerful Selective Inference After Data-Dependent Score Construction
• Small area learning