Growth-at-Risk has recently become a key measure of macroeconomic tail-risk, which has seen it be researched extensively. Surprisingly, the same cannot be said for Inflation-at-Risk where both tails, deflation and high inflation, are of key concern to policymakers, which has seen comparatively much less research. This paper will tackle this gap and provide estimates for Inflation-at-Risk. The key insight of the paper is that inflation is best characterised by a combination of two types of nonlinearities: quantile variation, and conditioning on the momentum of inflation.
{"title":"Momentum Informed Inflation-at-Risk","authors":"Tibor Szendrei, Arnab Bhattacharjee","doi":"arxiv-2408.12286","DOIUrl":"https://doi.org/arxiv-2408.12286","url":null,"abstract":"Growth-at-Risk has recently become a key measure of macroeconomic tail-risk,\u0000which has seen it be researched extensively. Surprisingly, the same cannot be\u0000said for Inflation-at-Risk where both tails, deflation and high inflation, are\u0000of key concern to policymakers, which has seen comparatively much less\u0000research. This paper will tackle this gap and provide estimates for\u0000Inflation-at-Risk. The key insight of the paper is that inflation is best\u0000characterised by a combination of two types of nonlinearities: quantile\u0000variation, and conditioning on the momentum of inflation.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Financial networks can be constructed using statistical dependencies found within the price series of speculative assets. Across the various methods used to infer these networks, there is a general reliance on predictive modelling to capture cross-correlation effects. These methods usually model the flow of mean-response information, or the propagation of volatility and risk within the market. Such techniques, though insightful, don't fully capture the broader distribution-level causality that is possible within speculative markets. This paper introduces a novel approach, combining quantile regression with a piecewise linear embedding scheme - allowing us to construct causality networks that identify the complex tail interactions inherent to financial markets. Applying this method to 260 cryptocurrency return series, we uncover significant tail-tail causal effects and substantial causal asymmetry. We identify a propensity for coins to be self-influencing, with comparatively sparse cross variable effects. Assessing all link types in conjunction, Bitcoin stands out as the primary influencer - a nuance that is missed in conventional linear mean-response analyses. Our findings introduce a comprehensive framework for modelling distributional causality, paving the way towards more holistic representations of causality in financial markets.
{"title":"Enhancing Causal Discovery in Financial Networks with Piecewise Quantile Regression","authors":"Cameron Cornell, Lewis Mitchell, Matthew Roughan","doi":"arxiv-2408.12210","DOIUrl":"https://doi.org/arxiv-2408.12210","url":null,"abstract":"Financial networks can be constructed using statistical dependencies found\u0000within the price series of speculative assets. Across the various methods used\u0000to infer these networks, there is a general reliance on predictive modelling to\u0000capture cross-correlation effects. These methods usually model the flow of\u0000mean-response information, or the propagation of volatility and risk within the\u0000market. Such techniques, though insightful, don't fully capture the broader\u0000distribution-level causality that is possible within speculative markets. This\u0000paper introduces a novel approach, combining quantile regression with a\u0000piecewise linear embedding scheme - allowing us to construct causality networks\u0000that identify the complex tail interactions inherent to financial markets.\u0000Applying this method to 260 cryptocurrency return series, we uncover\u0000significant tail-tail causal effects and substantial causal asymmetry. We\u0000identify a propensity for coins to be self-influencing, with comparatively\u0000sparse cross variable effects. Assessing all link types in conjunction, Bitcoin\u0000stands out as the primary influencer - a nuance that is missed in conventional\u0000linear mean-response analyses. Our findings introduce a comprehensive framework\u0000for modelling distributional causality, paving the way towards more holistic\u0000representations of causality in financial markets.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Randomized controlled trials (RCTs) have long been the gold standard for causal inference across various fields, including business analysis, economic studies, sociology, clinical research, and network learning. The primary advantage of RCTs over observational studies lies in their ability to significantly reduce noise from individual variance. However, RCTs depend on strong assumptions, such as group independence, time independence, and group randomness, which are not always feasible in real-world applications. Traditional inferential methods, including analysis of covariance (ANCOVA), often fail when these assumptions do not hold. In this paper, we propose a novel approach named textbf{Sp}illtextbf{o}vetextbf{r} textbf{T}ime textbf{S}eries textbf{Causal} (verb+SPORTSCausal+), which enables the estimation of treatment effects without relying on these stringent assumptions. We demonstrate the practical applicability of verb+SPORTSCausal+ through a real-world budget-control experiment. In this experiment, data was collected from both a 5% live experiment and a 50% live experiment using the same treatment. Due to the spillover effect, the vanilla estimation of the treatment effect was not robust across different treatment sizes, whereas verb+SPORTSCausal+ provided a robust estimation.
{"title":"SPORTSCausal: Spill-Over Time Series Causal Inference","authors":"Carol Liu","doi":"arxiv-2408.11951","DOIUrl":"https://doi.org/arxiv-2408.11951","url":null,"abstract":"Randomized controlled trials (RCTs) have long been the gold standard for\u0000causal inference across various fields, including business analysis, economic\u0000studies, sociology, clinical research, and network learning. The primary\u0000advantage of RCTs over observational studies lies in their ability to\u0000significantly reduce noise from individual variance. However, RCTs depend on\u0000strong assumptions, such as group independence, time independence, and group\u0000randomness, which are not always feasible in real-world applications.\u0000Traditional inferential methods, including analysis of covariance (ANCOVA),\u0000often fail when these assumptions do not hold. In this paper, we propose a\u0000novel approach named textbf{Sp}illtextbf{o}vetextbf{r} textbf{T}ime\u0000textbf{S}eries textbf{Causal} (verb+SPORTSCausal+), which enables the\u0000estimation of treatment effects without relying on these stringent assumptions.\u0000We demonstrate the practical applicability of verb+SPORTSCausal+ through a\u0000real-world budget-control experiment. In this experiment, data was collected\u0000from both a 5% live experiment and a 50% live experiment using the same\u0000treatment. Due to the spillover effect, the vanilla estimation of the treatment\u0000effect was not robust across different treatment sizes, whereas\u0000verb+SPORTSCausal+ provided a robust estimation.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We prove that under the condition that the eigenvalues are asymptotically well separated and stable, the normalised principal components of a r-static factor sequence converge in mean square. Consequently, we have a generic interpretation of the principal components estimator as the normalised principal components of the statically common space. We illustrate why this can be useful for the interpretation of the PC-estimated factors, performing an asymptotic theory without rotation matrices and avoiding singularity issues in factor augmented regressions.
我们证明,在特征值渐近分离且稳定的条件下,r-静态因子序列的归一化主成分均方收敛。因此,我们可以将主成分估计器通用地解释为静态公共空间的归一化主成分。我们将说明为什么这有助于解释 PC 估计因子,在没有旋转矩阵的情况下执行渐近理论,并避免因子增强回归的奇异性问题。
{"title":"L2-Convergence of the Population Principal Components in the Approximate Factor Model","authors":"Philipp Gersing","doi":"arxiv-2408.11676","DOIUrl":"https://doi.org/arxiv-2408.11676","url":null,"abstract":"We prove that under the condition that the eigenvalues are asymptotically\u0000well separated and stable, the normalised principal components of a r-static\u0000factor sequence converge in mean square. Consequently, we have a generic\u0000interpretation of the principal components estimator as the normalised\u0000principal components of the statically common space. We illustrate why this can\u0000be useful for the interpretation of the PC-estimated factors, performing an\u0000asymptotic theory without rotation matrices and avoiding singularity issues in\u0000factor augmented regressions.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Corporate social responsibility encourages companies to integrate social and environmental concerns into their activities and their relations with stakeholders. It encompasses all actions aimed at the social good, above and beyond corporate interests and legal requirements. Various international organizations, authors and researchers have explored the notion of CSR and proposed a range of definitions reflecting their perspectives on the concept. In Morocco, although Moroccan companies are not overwhelmingly embracing CSR, several factors are encouraging them to integrate the CSR approach not only into their discourse, but also into their strategies. The CGEM is actively involved in promoting CSR within Moroccan companies, awarding the "CGEM Label for CSR" to companies that meet the criteria set out in the CSR Charter. The process of labeling Moroccan companies is in full expansion. The graphs presented in this article are broken down according to several criteria, such as company size, sector of activity and listing on the Casablanca Stock Exchange, in order to provide an overview of CSR-labeled companies in Morocco. The approach adopted for this article is a qualitative one aimed at presenting, firstly, the different definitions of the CSR concept and its evolution over time. In this way, the study focuses on the Moroccan context to dissect and analyze the state of progress of CSR integration in Morocco and the various efforts made by the CGEM to implement it. According to the data, 124 Moroccan companies have been awarded the CSR label. For a label in existence since 2006, this figure reflects a certain reluctance on the part of Moroccan companies to fully implement the CSR approach in their strategies. Nevertheless, Morocco is in a transitional phase, marked by the gradual adoption of various socially responsible practices.
{"title":"Towards an Inclusive Approach to Corporate Social Responsibility (CSR) in Morocco: CGEM's Commitment","authors":"Gnaoui Imane, Moutahaddib Aziz","doi":"arxiv-2408.11519","DOIUrl":"https://doi.org/arxiv-2408.11519","url":null,"abstract":"Corporate social responsibility encourages companies to integrate social and\u0000environmental concerns into their activities and their relations with\u0000stakeholders. It encompasses all actions aimed at the social good, above and\u0000beyond corporate interests and legal requirements. Various international\u0000organizations, authors and researchers have explored the notion of CSR and\u0000proposed a range of definitions reflecting their perspectives on the concept.\u0000In Morocco, although Moroccan companies are not overwhelmingly embracing CSR,\u0000several factors are encouraging them to integrate the CSR approach not only\u0000into their discourse, but also into their strategies. The CGEM is actively\u0000involved in promoting CSR within Moroccan companies, awarding the \"CGEM Label\u0000for CSR\" to companies that meet the criteria set out in the CSR Charter. The\u0000process of labeling Moroccan companies is in full expansion. The graphs\u0000presented in this article are broken down according to several criteria, such\u0000as company size, sector of activity and listing on the Casablanca Stock\u0000Exchange, in order to provide an overview of CSR-labeled companies in Morocco.\u0000The approach adopted for this article is a qualitative one aimed at presenting,\u0000firstly, the different definitions of the CSR concept and its evolution over\u0000time. In this way, the study focuses on the Moroccan context to dissect and\u0000analyze the state of progress of CSR integration in Morocco and the various\u0000efforts made by the CGEM to implement it. According to the data, 124 Moroccan\u0000companies have been awarded the CSR label. For a label in existence since 2006,\u0000this figure reflects a certain reluctance on the part of Moroccan companies to\u0000fully implement the CSR approach in their strategies. Nevertheless, Morocco is\u0000in a transitional phase, marked by the gradual adoption of various socially\u0000responsible practices.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"178 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andrés Aradillas Fernández, José Luis Montiel Olea, Chen Qiu, Jörg Stoye, Serdil Tinda
We study a class of binary treatment choice problems with partial identification, through the lens of robust (multiple prior) Bayesian analysis. We use a convenient set of prior distributions to derive ex-ante and ex-post robust Bayes decision rules, both for decision makers who can randomize and for decision makers who cannot. Our main messages are as follows: First, ex-ante and ex-post robust Bayes decision rules do not tend to agree in general, whether or not randomized rules are allowed. Second, randomized treatment assignment for some data realizations can be optimal in both ex-ante and, perhaps more surprisingly, ex-post problems. Therefore, it is usually with loss of generality to exclude randomized rules from consideration, even when regret is evaluated ex-post. We apply our results to a stylized problem where a policy maker uses experimental data to choose whether to implement a new policy in a population of interest, but is concerned about the external validity of the experiment at hand (Stoye, 2012); and to the aggregation of data generated by multiple randomized control trials in different sites to make a policy choice in a population for which no experimental data are available (Manski, 2020; Ishihara and Kitagawa, 2021).
{"title":"Robust Bayes Treatment Choice with Partial Identification","authors":"Andrés Aradillas Fernández, José Luis Montiel Olea, Chen Qiu, Jörg Stoye, Serdil Tinda","doi":"arxiv-2408.11621","DOIUrl":"https://doi.org/arxiv-2408.11621","url":null,"abstract":"We study a class of binary treatment choice problems with partial\u0000identification, through the lens of robust (multiple prior) Bayesian analysis.\u0000We use a convenient set of prior distributions to derive ex-ante and ex-post\u0000robust Bayes decision rules, both for decision makers who can randomize and for\u0000decision makers who cannot. Our main messages are as follows: First, ex-ante and ex-post robust Bayes\u0000decision rules do not tend to agree in general, whether or not randomized rules\u0000are allowed. Second, randomized treatment assignment for some data realizations\u0000can be optimal in both ex-ante and, perhaps more surprisingly, ex-post\u0000problems. Therefore, it is usually with loss of generality to exclude\u0000randomized rules from consideration, even when regret is evaluated ex-post. We apply our results to a stylized problem where a policy maker uses\u0000experimental data to choose whether to implement a new policy in a population\u0000of interest, but is concerned about the external validity of the experiment at\u0000hand (Stoye, 2012); and to the aggregation of data generated by multiple\u0000randomized control trials in different sites to make a policy choice in a\u0000population for which no experimental data are available (Manski, 2020; Ishihara\u0000and Kitagawa, 2021).","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abhimanyu Mukerji, Sushant More, Ashwin Viswanathan Kannan, Lakshmi Ravi, Hua Chen, Naman Kohli, Chris Khawand, Dinesh Mandalapu
With recent rapid growth in online shopping, AI-powered Engagement Surfaces (ES) have become ubiquitous across retail services. These engagement surfaces perform an increasing range of functions, including recommending new products for purchase, reminding customers of their orders and providing delivery notifications. Understanding the causal effect of engagement surfaces on value driven for customers and businesses remains an open scientific question. In this paper, we develop a dynamic causal model at scale to disentangle value attributable to an ES, and to assess its effectiveness. We demonstrate the application of this model to inform business decision-making by understanding returns on investment in the ES, and identifying product lines and features where the ES adds the most value.
随着最近网上购物的快速增长,人工智能驱动的 "参与界面"(ES)在零售服务中变得无处不在。这些参与界面可以实现越来越多的功能,包括推荐购买新产品、提醒客户订单以及提供送货通知。了解参与面对客户和企业价值驱动的因果效应仍然是一个未决的科学问题。在本文中,我们开发了一个规模动态因果模型,以厘清 ES 的价值归属并评估其有效性。我们展示了该模型的应用,通过了解 ES 的投资回报,确定 ES 能带来最大价值的产品线和功能,为企业决策提供信息。
{"title":"Valuing an Engagement Surface using a Large Scale Dynamic Causal Model","authors":"Abhimanyu Mukerji, Sushant More, Ashwin Viswanathan Kannan, Lakshmi Ravi, Hua Chen, Naman Kohli, Chris Khawand, Dinesh Mandalapu","doi":"arxiv-2408.11967","DOIUrl":"https://doi.org/arxiv-2408.11967","url":null,"abstract":"With recent rapid growth in online shopping, AI-powered Engagement Surfaces\u0000(ES) have become ubiquitous across retail services. These engagement surfaces\u0000perform an increasing range of functions, including recommending new products\u0000for purchase, reminding customers of their orders and providing delivery\u0000notifications. Understanding the causal effect of engagement surfaces on value\u0000driven for customers and businesses remains an open scientific question. In\u0000this paper, we develop a dynamic causal model at scale to disentangle value\u0000attributable to an ES, and to assess its effectiveness. We demonstrate the\u0000application of this model to inform business decision-making by understanding\u0000returns on investment in the ES, and identifying product lines and features\u0000where the ES adds the most value.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, power grids have seen a surge in large cryptocurrency mining firms, with individual consumption levels reaching 700MW. This study examines the behavior of these firms in Texas, focusing on how their consumption is influenced by cryptocurrency conversion rates, electricity prices, local weather, and other factors. We transform the skewed electricity consumption data of these firms, perform correlation analysis, and apply a seasonal autoregressive moving average model for analysis. Our findings reveal that, surprisingly, short-term mining electricity consumption is not correlated with cryptocurrency conversion rates. Instead, the primary influencers are the temperature and electricity prices. These firms also respond to avoid transmission and distribution network (T&D) charges -- famously known as four Coincident peak (4CP) charges -- during summer times. As the scale of these firms is likely to surge in future years, the developed electricity consumption model can be used to generate public, synthetic datasets to understand the overall impact on power grid. The developed model could also lead to better pricing mechanisms to effectively use the flexibility of these resources towards improving power grid reliability.
{"title":"An Econometric Analysis of Large Flexible Cryptocurrency-mining Consumers in Electricity Markets","authors":"Subir Majumder, Ignacio Aravena, Le Xie","doi":"arxiv-2408.12014","DOIUrl":"https://doi.org/arxiv-2408.12014","url":null,"abstract":"In recent years, power grids have seen a surge in large cryptocurrency mining\u0000firms, with individual consumption levels reaching 700MW. This study examines\u0000the behavior of these firms in Texas, focusing on how their consumption is\u0000influenced by cryptocurrency conversion rates, electricity prices, local\u0000weather, and other factors. We transform the skewed electricity consumption\u0000data of these firms, perform correlation analysis, and apply a seasonal\u0000autoregressive moving average model for analysis. Our findings reveal that,\u0000surprisingly, short-term mining electricity consumption is not correlated with\u0000cryptocurrency conversion rates. Instead, the primary influencers are the\u0000temperature and electricity prices. These firms also respond to avoid\u0000transmission and distribution network (T&D) charges -- famously known as four\u0000Coincident peak (4CP) charges -- during summer times. As the scale of these\u0000firms is likely to surge in future years, the developed electricity consumption\u0000model can be used to generate public, synthetic datasets to understand the\u0000overall impact on power grid. The developed model could also lead to better\u0000pricing mechanisms to effectively use the flexibility of these resources\u0000towards improving power grid reliability.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper considers inference in a linear instrumental variable regression model with many potentially weak instruments and treatment effect heterogeneity. I show that existing tests can be arbitrarily oversized in this setup. Then, I develop a valid procedure that is robust to weak instrument asymptotics and heterogeneous treatment effects. The procedure targets a JIVE estimand, calculates an LM statistic, and compares it with critical values from a normal distribution. To establish this procedure's validity, this paper shows that the LM statistic is asymptotically normal and a leave-three-out variance estimator is unbiased and consistent. The power of the LM test is also close to a power envelope in an empirical application.
{"title":"Inference with Many Weak Instruments and Heterogeneity","authors":"Luther Yap","doi":"arxiv-2408.11193","DOIUrl":"https://doi.org/arxiv-2408.11193","url":null,"abstract":"This paper considers inference in a linear instrumental variable regression\u0000model with many potentially weak instruments and treatment effect\u0000heterogeneity. I show that existing tests can be arbitrarily oversized in this\u0000setup. Then, I develop a valid procedure that is robust to weak instrument\u0000asymptotics and heterogeneous treatment effects. The procedure targets a JIVE\u0000estimand, calculates an LM statistic, and compares it with critical values from\u0000a normal distribution. To establish this procedure's validity, this paper shows\u0000that the LM statistic is asymptotically normal and a leave-three-out variance\u0000estimator is unbiased and consistent. The power of the LM test is also close to\u0000a power envelope in an empirical application.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper extends difference-in-differences to settings involving continuous treatments. Specifically, the average treatment effect on the treated (ATT) at any level of continuous treatment intensity is identified using a conditional parallel trends assumption. In this framework, estimating the ATTs requires first estimating infinite-dimensional nuisance parameters, especially the conditional density of the continuous treatment, which can introduce significant biases. To address this challenge, estimators for the causal parameters are proposed under the double/debiased machine learning framework. We show that these estimators are asymptotically normal and provide consistent variance estimators. To illustrate the effectiveness of our methods, we re-examine the study by Acemoglu and Finkelstein (2008), which assessed the effects of the 1983 Medicare Prospective Payment System (PPS) reform. By reinterpreting their research design using a difference-in-differences approach with continuous treatment, we nonparametrically estimate the treatment effects of the 1983 PPS reform, thereby providing a more detailed understanding of its impact.
{"title":"Continuous difference-in-differences with double/debiased machine learning","authors":"Lucas Zhang","doi":"arxiv-2408.10509","DOIUrl":"https://doi.org/arxiv-2408.10509","url":null,"abstract":"This paper extends difference-in-differences to settings involving continuous\u0000treatments. Specifically, the average treatment effect on the treated (ATT) at\u0000any level of continuous treatment intensity is identified using a conditional\u0000parallel trends assumption. In this framework, estimating the ATTs requires\u0000first estimating infinite-dimensional nuisance parameters, especially the\u0000conditional density of the continuous treatment, which can introduce\u0000significant biases. To address this challenge, estimators for the causal\u0000parameters are proposed under the double/debiased machine learning framework.\u0000We show that these estimators are asymptotically normal and provide consistent\u0000variance estimators. To illustrate the effectiveness of our methods, we\u0000re-examine the study by Acemoglu and Finkelstein (2008), which assessed the\u0000effects of the 1983 Medicare Prospective Payment System (PPS) reform. By\u0000reinterpreting their research design using a difference-in-differences approach\u0000with continuous treatment, we nonparametrically estimate the treatment effects\u0000of the 1983 PPS reform, thereby providing a more detailed understanding of its\u0000impact.","PeriodicalId":501293,"journal":{"name":"arXiv - ECON - Econometrics","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142184185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}