[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122742-en":3,"doc-seo-122742-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122742,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Estimating Continuous Treatment Effects in Panel Data using Machine Learning with a Climate Application - Abstract and Introduction","This paper presents a semi-parametric estimator for continuous treatment effects in panel data, focusing on the average derivative. It integrates double de-biased machine learning ideas with a first-difference strategy to handle unobserved time-invariant heterogeneity and reduce bias from high-dimensional modeling. Monte Carlo experiments in nonlinear panel settings show low bias and variance relative to alternatives. An application estimates extreme-heat impacts on U.S. corn production, yielding larger damage effects than linear regression and deriving a dose-response pattern.","Estimating Continuous Treatment Effects in Panel Data using Machine Learning with a Climate Application  \nSylvia Klosin∗ and Max Vilgalys†  \narXiv :2207 .08789v2 [ econ .EM] 13 Sep 2023  \nAbstract  \nThis paper introduces and proves asymptotic normality for a new semi-parametric estimator of continuous treatment effects in panel data. Specifically, we estimate the average derivative. Our estimator uses the panel structure of data to account for unobservable time-invariant heterogeneity and machine learning (ML) methods to preserve statistical power while modeling high-dimensional relationships. We construct our estimator using tools from double de-biased machine learning (DML) literature. Monte Carlo simulations in a nonlinear panel setting show that our method estimates the average derivative with low bias and variance relative to other approaches. Lastly, we use our estimator to measure the impact of extreme heat on United States (U.S.) corn production, after flexibly controlling for precipitation and other weather features. Our approach yields extreme heat effect estimates that are 50% larger than estimates using linear regression. This difference in estimates corresponds to an additional $3.17 billion in annual damages by 2050 under median climate scenarios. We also estimate a dose-response curve, which shows that damages from extreme heat decline somewhat in counties with more extreme heat exposure.  \nKeywords: Average derivative, de-biased machine learning, longitudinal data, panel data, semiparametrics, climate change  \n∗ email: [klosins@mit.edu](klosins@mit.edu)  \n†[email: maxvilgalys@gmail.com](email: maxvilgalys@gmail.com)  \n1 Introduction  \nEstimating the effects of continuous treatments in panel data is essential for many applications in natural and social sciences. To estimate a continuous treatment effect, researchers must define a model that connects the outcome variable, unobserved per-unit factors, the treatment variable, and control variables. A widely used approach is the linear fixed effects model, which relies on two main structures: 1) additive unit fixed effects and 2) a linear model of treatment and covariates. However, using a linear model can introduce biases when the true relationship between variables is nonlinear (Hastie et al. 2009) .  \nMany important relationships have been found to be nonlinear, such as those between weather and economic outputs (Burke, Hsiang, and Miguel 2015), physical activity and health outcomes (Aune et al. 2015), and accessibility and car ownership (Zhang et al. 2020) . Current methods for adding flexibility to linear models frequently rely on ad-hoc techniques, such as manually selecting bins or interactions. Machine learning (ML) offers an automatic, data-driven approach to flexibly model these relationships, but current ML methods often fail to include fixed effects and can lead to bias.  \nThis paper introduces a new approach with three appealing features: we use ML to flexibly model relationships in a data-driven way, we allow for classic fixed effects, and we de-bias ML estimates. Our approach preserves statistical power. In practice, we observe standard errors as small as those of classic linear regression. Our method is an unbiased and consistent estimator in panel settings with an unknown and potentially nonlinear relationship between the outcome variable, the treatment variable, and the control variables.  \nOur estimator accounts for fixed effects by using a first-difference approach and addresses bias from standard ML algorithms by adapting the double machine learning (DML) approach from Chernozhukov, Newey, and Singh (2022) . We introduce a first-differenced version of the DML estimator for the average derivative and prove its asymptotic normality. We  \nimplement the estimator using high-dimensional Lasso. We introduce two improvements to their computational approach: (1) we use an optimization method to de-bias the initial estimates, and (2) we find the average ","cbCaim2TE8hxnz2N","https://ap.wps.com/l/cbCaim2TE8hxnz2N","pdf",964251,1,47,"English","en",105,"# Abstract\n# Introduction\n## Problem setting and motivation\n## Limitations of linear fixed effects and ad-hoc flexibility\n## Proposed approach and DML-based first-difference estimator\n## Simulation study and empirical climate application\n## Contributions and literature links","[{\"question\":\"What is the main target estimand in this paper for continuous treatments in panel data?\",\"answer\":\"The method estimates the average derivative of the outcome with respect to the continuous treatment, using a semi-parametric, DML-based construction.\"},{\"question\":\"How does the estimator address unobservable time-invariant heterogeneity in panel data?\",\"answer\":\"It accounts for fixed effects through a first-difference approach, designed to isolate treatment effects despite unit-specific unobservables.\"},{\"question\":\"What does the climate application measure, and how do results compare with linear regression?\",\"answer\":\"It measures the impact of extreme heat on U.S. corn production, with estimates about 50% larger than those from linear regression and associated higher projected damages under median scenarios.\"}]","Estimating Continuous Treatment Effects in Panel Data using Machine Learning with a Climate Application - Abstract and Introduction | PDF",1785812644,118,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"estimating-continuous-treatment-effects-in-panel-data-using-machine-learning-with-a-climate-application-abstract-and-introduction","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/estimating-continuous-treatment-effects-in-panel-data-using-machine-learning-with-a-climate-application-abstract-and-introduction/122742/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main target estimand in this paper for continuous treatments in panel data?","Question",{"text":75,"@type":76},"The method estimates the average derivative of the outcome with respect to the continuous treatment, using a semi-parametric, DML-based construction.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the estimator address unobservable time-invariant heterogeneity in panel data?",{"text":80,"@type":76},"It accounts for fixed effects through a first-difference approach, designed to isolate treatment effects despite unit-specific unobservables.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the climate application measure, and how do results compare with linear regression?",{"text":84,"@type":76},"It measures the impact of extreme heat on U.S. corn production, with estimates about 50% larger than those from linear regression and associated higher projected damages under median scenarios.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]