{"title":"Unconditional Randomization Tests for Interference","authors":"Liang Zhong","doi":"arxiv-2409.09243","DOIUrl":null,"url":null,"abstract":"In social networks or spatial experiments, one unit's outcome often depends\non another's treatment, a phenomenon called interference. Researchers are\ninterested in not only the presence and magnitude of interference but also its\npattern based on factors like distance, neighboring units, and connection\nstrength. However, the non-random nature of these factors and complex\ncorrelations across units pose challenges for inference. This paper introduces\nthe partial null randomization tests (PNRT) framework to address these issues.\nThe proposed method is finite-sample valid and applicable with minimal network\nstructure assumptions, utilizing randomization testing and pairwise\ncomparisons. Unlike existing conditional randomization tests, PNRT avoids the\nneed for conditioning events, making it more straightforward to implement.\nSimulations demonstrate the method's desirable power properties and its\napplicability to general interference scenarios.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"36 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - ECON - Econometrics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.09243","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In social networks or spatial experiments, one unit's outcome often depends
on another's treatment, a phenomenon called interference. Researchers are
interested in not only the presence and magnitude of interference but also its
pattern based on factors like distance, neighboring units, and connection
strength. However, the non-random nature of these factors and complex
correlations across units pose challenges for inference. This paper introduces
the partial null randomization tests (PNRT) framework to address these issues.
The proposed method is finite-sample valid and applicable with minimal network
structure assumptions, utilizing randomization testing and pairwise
comparisons. Unlike existing conditional randomization tests, PNRT avoids the
need for conditioning events, making it more straightforward to implement.
Simulations demonstrate the method's desirable power properties and its
applicability to general interference scenarios.