[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290354-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290354-en":131},{"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","double-machine-learning-for-static-panel-models-with-fixed-effects","Double Machine Learning for Static Panel Models with Fixed Effects","","Paper develops double machine learning (DML) procedures for panel data with fixed effects, using machine learning to approximate high-dimensional, nonlinear nuisance functions of covariates. The proposed methods extend correlated random effects, within-group, and first-difference estimators from linear to nonlinear panel settings, building on Robinson’s partially linear regression with fixed effects and unspecified nonlinear confounding. Simulations evaluate performance across multiple ML algorithms, and the framework is applied to re-estimate the impact of the minimum wage on UK voting behavior.",{"@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/double-machine-learning-for-static-panel-models-with-fixed-effects/290354/",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/double-machine-learning-for-static-panel-models-with-fixed-effects/290354.png","ImageObject",300,407,{"name":42,"@type":43},"Eliana","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-01","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",11,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the paper address in panel data causal inference?","Question",{"text":63,"@type":64},"It develops DML procedures to estimate treatment (causal) effects from panel data with fixed effects, where nuisance functions are high-dimensional and nonlinear.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How do the proposed methods relate to existing estimators?",{"text":68,"@type":64},"They extend correlated random effects, within-group, and first-difference estimators from linear to nonlinear models, based on an extension of Robinson’s partially linear regression to panel data.",{"name":70,"@type":61,"acceptedAnswer":71},"What do the simulations and empirical application evaluate?",{"text":72,"@type":64},"The simulations assess estimator performance using different machine learning algorithms, and the empirical study re-estimates the minimum wage’s impact on UK voting behavior, recommending first-differencing and ensemble learning.","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},290354,1789641450,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"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":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":80,"read_time":145,"preview_page_count":4},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","arXiv :2312 .08174v5 [ econ .EM] 30 Dec 2024  \nManuscript accepted at The Econometrics Journal (December 2024), pp. 1–31.  \nDouble Machine Learning for Static Panel Models  \nwith Fixed E􀀋ects  \nPaul S. Clarke† and Annalivia Polselli‡  \n† Institute for Social and Economic Research, University of Essex, Colchester CO4 3SQ, UK.  \nE-mail: [pclarke@essex.ac.uk](pclarke@essex.ac.uk)  \n‡Institute for Analytics and Data Science, University of Essex, Colchester CO4 3ZL, UK.  \nE-mail: [annalivia.polselli@essex.ac.uk](annalivia.polselli@essex.ac.uk)  \nSummary Recent advances in causal inference have seen the development of methods which make use of the predictive power of machine learning algorithms. In this paper, we develop novel double machine learning (DML) procedures for panel data in which these algorithms are used to approximate high-dimensional and nonlinear nuisance functions of the covariates. Our new procedures are extensions of the well-known correlated random e􀀋ects, within-group and 􀀌rst-di􀀋erence estimators from linear to nonlinear panel models, speci􀀌cally, Robinson (1988)’s partially linear regression model with 􀀌xed e􀀋ects and unspeci􀀌ed nonlinear confounding. Our simulation study assesses the performance of these procedures using di􀀋erent machine learning algorithms. We use our procedures to re-estimate the impact of minimum wage on voting behaviour in the UK. From our results, we recommend the use of 􀀌rst-di􀀋erencing because it imposes the fewest constraints on the distribution of the 􀀌xed e􀀋ects, and an ensemble learning strategy to ensure optimum estimator accuracy.  \nKeywords: CART, homogeneous treatment e􀀋ect, hyperparameter tuning, LASSO, random forest.  \n1. INTRODUCTION  \nRecent advances in the econometric literature on Machine Learning (ML) use the power of ML algorithms, widely used in data science for solving prediction problems, to enhance existing estimation procedures for treatment and other kinds of causal e􀀋ect. Notable developments include novel ML algorithms for causal analysis such as Causal Trees by Athey and Imbens (2016), Causal Forests by Wager and Athey (2018) and Generalised Random Forests by Athey et al. (2019) . However, the key development, as far as this paper is concerned, is Double/Debiased Machine Learning (DML) by Chernozhukov et al.(2018) wherein ML is used to learn nuisance functions with ex ante unknown functional forms, and the predicted values of these functions used to construct (orthogonalized) scores for the interest parameters from which consistent and asymptotically normal estimators can be obtained. DML is a very general estimation framework but there are limited examples of its application to panel data, notable examples of which include Chang (2020), Klosin and Vilgalys (2023), and Semenova et al. (2023) .  \nIn this paper, we develop and assess novel DML procedures for estimating treatment (or causal) e􀀋ects from panel data with 􀀌xed e􀀋ects. The procedures we propose are extensions of the correlated random e􀀋ects (CRE), within-group (WG) and 􀀌rst-di􀀋erence (FD) estimators commonly used for linear models to scenarios where the underlying model is non-linear. Speci􀀌cally, these are based on an extension of the partially linear regression (PLR) model proposed by Robinson (1988) to panel data through the inclusion of time-varying predictors and unobserved individual heterogeneity (i.e. individual 􀀌xed e􀀋ects) .  \n2 P. S. Clarke and A. Polselli  \nOur methodological contribution is twofold and complementary to the recent work on causal panel data estimation using DML by Chang (2020) on di􀀋erence-in-di􀀋erences, Klosin and Vilgalys (2023) and Semenova et al. (2023) on high-dimensional treatment heterogeneity in model with 􀀌xed e􀀋ects.  \nA 􀀌rst contribution is that the procedures we develop are not based on ex ante taking the nuisance functions or 􀀌xed e􀀋ects to be accurately approximated by high-dimensional sparse functions. Thus, we do not focus solely on the Least Absolute Shrinka","cbCaib3WW756c0z8","https://ap.wps.com/l/cbCaib3WW756c0z8","pdf",424314,31,"English","# Summary\n# Keywords\n# 1. Introduction\n# 2. Methodological contributions","[{\"question\":\"What problem does the paper address in panel data causal inference?\",\"answer\":\"It develops DML procedures to estimate treatment (causal) effects from panel data with fixed effects, where nuisance functions are high-dimensional and nonlinear.\"},{\"question\":\"How do the proposed methods relate to existing estimators?\",\"answer\":\"They extend correlated random effects, within-group, and first-difference estimators from linear to nonlinear models, based on an extension of Robinson’s partially linear regression to panel data.\"},{\"question\":\"What do the simulations and empirical application evaluate?\",\"answer\":\"The simulations assess estimator performance using different machine learning algorithms, and the empirical study re-estimates the minimum wage’s impact on UK voting behavior, recommending first-differencing and ensemble learning.\"}]","Double Machine Learning for Static Panel Models with Fixed Effects | PDF",78]