[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127402-en":3,"doc-seo-127402-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},127402,962085571259,"Theodora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Public Subsidies and Innovation - A Doubly Robust Machine Learning Approach Leveraging Deep Neural Networks","Economic growth underpins standards of living and welfare, yet diminishing returns to physical capital make knowledge creation and spillovers central. Public subsidies are used to raise firms’ R&D when market imperfections can depress socially desired investment in innovation. Using European firm-level data, the study estimates average treatment effects while accounting for observable and unobserved heterogeneity. Endogeneity in subsidy assignment is handled via double machine learning and a local instrumental variable approach, and results show positive effects on R&D intensity and output.","Special Issue in Honor of Professor Peter Schmidt, 2023, Empirical Economics. Volume 64, Issue 6,  \n3121-3165.  \nPublic Subsidies and Innovation: A Doubly Robust Machine Learning Approach Leveraging Deep Neural Networks  \nKerda Varaku* Robin Sickles†  \nAbstract  \nEconomic growth is crucial to improve standards of living, prosperity and welfare. R&D and knowledge spillovers can offset the diminishing returns to physical capital (machines and labor) and drive long-run growth. Market imperfections can bring R&D below the socially desired level thus, many governments intervene to increase the stock of knowledge, and knowledge spillovers, via subsidies for R&D. We use European frm-level data to explore the effects of public subsidies on frms’ R&D input and output. Average treatment effects are estimated controlling for both observable and unobserved heterogeneity. Possible endogeneityin subsidy assignment is addressed and the local instrumental variable (LIV ) curve is identifed via double machine learning methods. Results indicate that public subsidies increase both R&D intensity and output with more pronounced effects on the R&D intensity of high technology and knowledge intensive frms. The effects of public support remain positive and signifcant even after accounting for treatment endogeneity.  \nJEL Classifcation: H25, C14, C45, C54, C55  \nKeywords: Double Machine Learning, Public Subsidies, Innovation, Non-parametric Estimation, Deep Neural Networks  \n1 Introduction  \nPeter Schmidt has made a number of contributions that speak to the methods and approaches that we undertake in this paper. The effectiveness of government subsidies in expanding the production possibilities of companies and ultimately the countries in which they reside speaks in general to the issue of effciency and productivity. Peter is one of the iconic contributors to the literature on effciency and productivity (Aigner et al. (1977)) . Nonparametric approaches to addressing unobservables in panel  \n* Department of Economics, Rice University, Houston, [TX. Email: kerdava@gmail.com](TX. Email: kerdava@gmail.com)  \n†Department of Economics, Rice University, Houston, TX. Email: [rsickles@rice.edu](rsickles@rice.edu)  \nsettings such as ours have characterized Peter’s work on factor models (Ahn et al. (2013)) . Interestingly, in a direct question posed to Peter in a recent Econometric Theory Interview (Sickles (2022)) on his view of the relevance of big data and machine learning techniques in assessing causal effects, which is the contribution of our paper, Peter’s perspective is rather measured. He says:  \n“I think it’s important to distinguish Big Data from Big Model. With respect to Big Data, more data can’t hurt. With respect to Big Model, remember that you can have big models with little data – you just put in lots of terms...”  \nHe goes on to say:  \n“...I am not a fan of the sparsity assumption and I don’t necessarily understand why it’s better to let the data tell us that there are six variables with non-zero coeffcients than to try to pick them out ourselves. It seems to me if you want to let the computer make these choices what we need is something akin to the short memory assumption in time series – that even if there was an infnite set of variables, the sum of their coeffcients is fnite...”  \nNeedless to say, the sparsity assumption is used in our work, the data does in fact tell us what variables have non-zero coeffcients, and we do not use “something akin” to the short memory assumption in time series. That said, our contribution is motivated by the many contributions that Peter has made over his storied career and, we trust, he will fnd our paper worthy of this special issue.  \nThe focus of this study is to evaluate the treatment effects of public subsidies on R&Dintensity and R&D output. Innovation plays an important role in sustaining economic growth (Aghion and Howitt (1990), Audretsch (1995)), thus many countries invest a considerable amount of pu","cbCaiuzJ6sd7Y4LK","https://ap.wps.com/l/cbCaiuzJ6sd7Y4LK","pdf",1084939,1,38,"English","en",105,"# Introduction\n## Research question and motivation\n## Innovation, growth, and R&D underinvestment\n## Government subsidies and identification strategy","[{\"question\":\"What research question does the paper address?\",\"answer\":\"The paper evaluates the treatment effects of public subsidies on firms’ R\\u0026D input (R\\u0026D intensity) and R\\u0026D output, using European firm-level data.\"},{\"question\":\"How does the study handle endogeneity in subsidy assignment?\",\"answer\":\"Possible endogeneity is addressed with a local instrumental variable curve identified via double machine learning methods.\"},{\"question\":\"What do the results indicate about the impact of subsidies?\",\"answer\":\"Public subsidies increase both R\\u0026D intensity and R\\u0026D output, with stronger effects on high-technology and knowledge-intensive firms, and effects remain positive and significant after accounting for treatment endogeneity.\"}]","Public Subsidies and Innovation - A Doubly Robust Machine Learning Approach Leveraging Deep Neural Networks | PDF",1785938696,96,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"public-subsidies-and-innovation-a-doubly-robust-machine-learning-approach-leveraging-deep-neural-networks","",{"@graph":36,"@context":86},[37,54,69],{"@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/public-subsidies-and-innovation-a-doubly-robust-machine-learning-approach-leveraging-deep-neural-networks/127402/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What research question does the paper address?","Question",{"text":76,"@type":77},"The paper evaluates the treatment effects of public subsidies on firms’ R&D input (R&D intensity) and R&D output, using European firm-level data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the study handle endogeneity in subsidy assignment?",{"text":81,"@type":77},"Possible endogeneity is addressed with a local instrumental variable curve identified via double machine learning methods.",{"name":83,"@type":74,"acceptedAnswer":84},"What do the results indicate about the impact of subsidies?",{"text":85,"@type":77},"Public subsidies increase both R&D intensity and R&D output, with stronger effects on high-technology and knowledge-intensive firms, and effects remain positive and significant after accounting for treatment endogeneity.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]