[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-455656-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-455656-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","locally-robust-inference-for-non-gaussian-svar-models","Locally robust inference for non-Gaussian SVAR models","","Locally robust semiparametric inference is developed for structural vector autoregressive (SVAR) models with independent, non-Gaussian structural shocks. Standard procedures that exploit non-Gaussian identification may fail to deliver correct coverage for structural functions when deviations from Gaussianity are small. The proposed method fully uses non-Gaussianity when present while preserving correct size and coverage for local-to-Gaussian densities. Empirical reexaminations of two macroeconomic SVAR studies show robust confidence sets for the oil price model but not for the labor supply–demand model.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/locally-robust-inference-for-non-gaussian-svar-models/455656/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/locally-robust-inference-for-non-gaussian-svar-models/455656.png","ImageObject",300,407,{"name":42,"@type":43},"Nguyễn Văn Học","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-08","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",7,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the core identification strategy for SVAR models in this paper?","Question",{"text":63,"@type":64},"The paper uses independent component analysis ideas: when structural shocks are independent and at least K−1 are non-Gaussian, the contemporaneous matrix A can be recovered up to sign and permutation.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Why do standard non-Gaussian SVAR inference methods fail in some cases?",{"text":68,"@type":64},"They are not robust when the shock distributions are too close to Gaussian, which causes coverage distortions for confidence sets of structural functions such as impulse responses.",{"name":70,"@type":61,"acceptedAnswer":71},"What is the main contribution of the proposed approach?",{"text":72,"@type":64},"It provides locally robust semiparametric hypothesis tests and confidence sets that exploit non-Gaussianity when available but still achieve correct size/coverage for local-to-Gaussian densities.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},455656,1790974533,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145},1374402739827,"https://ap-avatar.wpscdn.com/avatar/14000c97e7351f1a627?x-image-process=image/resize,m_fixed,w_180,h_180&k=1787885694763230660","Quantitative Economics 15 (2024), 523–570 1759-7331/20240523  \nLocally robust inference for non-Gaussian SVAR models  \nLukas Hoesch  \nDepartment of Econometrics and Data Science, Vrije Universiteit Amsterdam and Tinbergen Institute  \nAdam Lee  \nDepartment of Data Science and Analytics, BI Norwegian Business School  \nGeert Mesters  \nDepartment of Economics and Business, Universitat Pompeu Fabra, Barcelona School of Economics, and  \nCREI  \nAll parameters in structural vector autoregressive (SVAR) models are locally identified when the structural shocks are independent and follow non-Gaussian distributions. Unfortunately, standard inference methods that exploit such features of the data for identification fail to yield correct coverage for structural functions of the model parameters when deviations from Gaussianity are small. To this extent, we propose a locally robust semiparametric approach to conduct hypothesis tests and construct confidence sets for structural functions in SVAR models. The methodology fully exploits non-Gaussianity when it is present, but yields correct size/coverage for local-to-Gaussian densities. Empirically, we revisit two macroeconomic SVAR studies where we document mixed results. For the oil price model of Kilian and Murphy (2012), we find that non-Gaussianity can robustly identify reasonable confidence sets, whereas for the labor supply–demand model of Baumeister and Hamilton (2015) this is not the case. Moreover, these exercises highlight the importance of using weak identification robust methods to assess estimation uncertainty when using non-Gaussianity for identification.  \nKeywords. Weak identification, semiparametric inference, hypothesis testing, impulse responses, independent component analysis.  \nJEL classification. C32, C39, C51 .  \n1. Introduction  \nIn this paper, we develop locally robust inference methods for non-Gaussian structural vector autoregressive (SVAR) models. To outline our contribution, consider the SVAR  \n[Lukas Hoesch:](Lukas Hoesch: l.hoesch@vu.nl)[ l.hoesch@vu.nl](Lukas Hoesch: l.hoesch@vu.nl)  \n[Adam Lee:](Adam Lee: adam.lee@bi.no)[ adam.lee@bi.no](Adam Lee: adam.lee@bi.no)  \n[Geert Mesters:](Geert Mesters: geert.mesters@upf.edu)[ geert.mesters@upf.edu](Geert Mesters: geert.mesters@upf.edu)  \nWe thank Majid Al-Sadoon, Regis Barnichon, Christian Brownlees, Saskia ter Ellen, Juan Carlos Escanciano, Kirill Evdokimov, Eleonora Granziera, Katerina Petrova, Barbara Rossi, and Piotr Zwiernik, as well as seminar and conference participants from different institutions for helpful comments. Mesters acknowledges financial support from the European Research Council via Starting Grant 101041145—POLICYMETRICS, and from the Spanish Agencia Estatal de Investigación (AEI), through the Severo Ochoa Programme for Centres of Excellence in R&D (Barcelona School of Economics CEX2019-000915-S) .  \n© 2024 The Authors. Licensed under the Creative Commons Attribution-NonCommercial License 4 .0. Available at [http://qeconomics.org](http://qeconomics.org). [https://doi.org/10.3982/QE2274](https://doi.org/10.3982/QE2274)  \n524 Hoesch, Lee, and Mesters Quantitative Economics 15 (2024)  \nmodel  \nYt = c + B1 Yt−1 + · · · + BpYt−p + A−1􀀂 t , (1)  \nwhere Yt is a K × 1 vector of variables, c is an intercept, B 1 , 􀀃􀀃􀀃 , Bp are the autoregressive matrices, A is the invertible contemporaneous effect matrix, and 􀀂 t is the K × 1 vector of structural shocks with mean zero and unit variance.  \nIt is well known that, without further restrictions, the first and second moments of { Yt} are insufficient to identify all parameters in A (e.g., Kilian and Lütkepohl (2017)) . Instead, higher-order moments or non-Gaussian distributions can be exploited to (locally) identify A. The most well-known result follows from the Darmois–Skitovich theorem and is central to the literature on independent components analysis (ICA): if the components of 􀀂 t are independent and at least K − 1 have a non-Gaussian distribution, then A can be recove","cbCaitCWRB8AEOsj","https://ap.wps.com/l/cbCaitCWRB8AEOsj","pdf",739862,48,"English","# 1. Introduction\n## SVAR structure and identification via non-Gaussianity\n## Local-to-Gaussian robustness and inference goals\n## Empirical motivation and study comparisons","[{\"question\":\"What is the core identification strategy for SVAR models in this paper?\",\"answer\":\"The paper uses independent component analysis ideas: when structural shocks are independent and at least K−1 are non-Gaussian, the contemporaneous matrix A can be recovered up to sign and permutation.\"},{\"question\":\"Why do standard non-Gaussian SVAR inference methods fail in some cases?\",\"answer\":\"They are not robust when the shock distributions are too close to Gaussian, which causes coverage distortions for confidence sets of structural functions such as impulse responses.\"},{\"question\":\"What is the main contribution of the proposed approach?\",\"answer\":\"It provides locally robust semiparametric hypothesis tests and confidence sets that exploit non-Gaussianity when available but still achieve correct size/coverage for local-to-Gaussian densities.\"}]","Locally robust inference for non-Gaussian SVAR models | PDF",1790743784,121]