Dynamic Treatment Effects Research Articles

Consumption responses to sweetened beverage taxes by household income in four U.S. cities.

Taxes on sweetened beverages have become an important policy response to growing obesity rates and the prevalence of type 2 diabetes in the U.S. and other nations. Since 2015, eight U.S. cities have implemented these taxes, but so far direct evidence of their impacts on household purchasing behavior is scarce. Of particular interest to many researchers and policy makers is the response of lower-income consumers to these taxes, both because they have higher sweetened beverage consumption on average and because of concerns that sweetened beverage taxes are regressive. This project investigates the income-stratified household response to SSB taxes using a data set containing the purchasing behavior of approximately 400 households in the cities of Seattle, San Francisco, Oakland, and Philadelphia, all of which have recently introduced beverage taxes. Using doubly-robust estimation of dynamic and heterogeneous treatment effects relative to a propensity-matched set of households in three comparison cities, we find that households in taxed cities experience increased prices and reduce their purchases of those beverages, with no evidence of cross-border shopping. We further find differential tax impacts by income level, with lower-income households (households with income <200% of the federal poverty line for their size) reducing their purchases of taxed beverages by nearly 50% - more than double the 18% reduction found in higher-income households (households with income >400% of the federal poverty line for their size). Our finding that lower-income households decrease their consumption more than twice as much as higher-income households suggests that these taxes may reduce health disparities and promote population health.

The effect of vertical identification card laws on teenage tobacco and alcohol use.

We study the impact of vertical identification card laws, which changed the orientation of driver's licenses and state identification cards from horizontal to vertical for those under 21years, on teenage tobacco and alcohol use. We study this question using four national datasets (pooled national and state Youth Risk Behavior Surveillance System, National Youth Tobacco Survey, Current Population Survey to Tobacco Use Supplements, and Behavioral Risk Factor Surveillance System). We improve previous databases of vertical ID law implementation by using original archival research to identify the exact date of the law change. We estimate models using standard two-way fixed effects and stacked difference-in-differences that avoid bias from dynamic and heterogeneous treatment effects. Using data through 2021, we do not find evidence of reductions in teenage tobacco and alcohol use. While these laws reduce retail-based purchasing, they also increase social sourcing, thus leading to no net impact on use.

High-dimensional inference for dynamic treatment effects

High-dimensional inference for dynamic treatment effects

Targeted Liberalization: China's foreign investment regulation reform and its post‐WTO‐accession export surge

AbstractTo gain membership in the World Trade Organization (WTO) in 2001, China substantially modified its regulation of foreign direct investment. These reforms coincided with rapid changes in the composition of capital inflows, as the dominant entry mode shifted from joint venture to wholly foreign owned affiliate. Foreign‐invested enterprises contributed a rising share of China's rapidly growing exports. We investigate how much China's foreign ownership liberalization contributed to these observed trends in foreign investment flows and Chinese exports. Accounting for both the set of activities from which it removed foreign equity caps and those into which it newly encouraged investment, we estimate the impact of China's reforms on firm entry and exports using a difference‐in‐differences estimator. To eliminate bias resulting from heterogeneous and dynamic treatment effects, we also apply novel dynamic difference‐in‐differences estimators. We find that removal of foreign equity caps induced entry of wholly foreign owned firms, while having no significant effect on entry of new joint ventures. Concurrently, the designation of new activities for investment incentives induced foreign entry, particularly in the form of joint ventures. Reduced‐form calculations imply that FDI policy changes explain almost 9% of the increase in exports from foreign‐invested firms over the decade studied. The effect was larger in sectors identified as “high‐tech industries” by the Chinese government, as they contribute most of the estimated policy‐driven export growth from foreign‐invested firms. Thus, China's FDI regulation reform following WTO entry was targeted liberalization: elimination of equity share limits induced new foreign entry, while investment incentives encouraged formation of joint ventures.

Mandatory seatbelt laws and traffic fatalities: A reassessment

AbstractUsing data from the Fatality Analysis Reporting System for the period 1983–1997, Cohen and Einav (Review of Economics and Statistics 2003; 85[4]: 828–843) found that mandatory seatbelt laws were associated with a 4–6% reduction in traffic fatalities among motor vehicle occupants. After successfully replicating their two‐way fixed effects estimates, we (1) add 22 years of data (1998–2019) to capture additional seatbelt policy variation and observe a longer post‐treatment period, (2) employ the interaction‐weighted estimator proposed by Sun and Abraham (2021) to address potential bias due to heterogeneous and dynamic treatment effects, and (3) estimate event‐study models to investigate pre‐treatment trends and explore lagged post‐treatment effects. Consistent with Cohen and Einav (2003), our updated estimates show that primary seatbelt laws are associated with a 5 to 9% reduction in fatalities among motor vehicle occupants. Estimated effects of secondary seatbelt laws are smaller in magnitude and sensitive to model choice.

Merger and Acquisition in the Banking Industry a Dynamic Treatment Effect Identification with Flexible Panel Difference- in- Differences Approach

Merger and Acquisition in the Banking Industry a Dynamic Treatment Effect Identification with Flexible Panel Difference- in- Differences Approach

An Empirical Research on the Impact of Gasoline Taxes on Consumer-Level Retail Prices

This paper uses provincial-level gasoline retail price data in Canada to study the effect of tax reform on gasoline retail prices. It uses a dynamic difference-in-difference strategy to estimate the dynamic treatment effect of tax reform to see the dynamic changes of treatment effect in post-reform periods. We find that on average, the tax cut tends to be close to or around the full passthrough rate to the gasoline retail price. The treatment effect does not diminish over time and it is immediate after the tax reform. This means that the gasoline tax cut goes directly to consumers, it will work as a great macroeconomic tool in fighting the current inflation. The implications of effective gasoline taxation policy allow governments to adjust the gasoline taxation when needed to fight off inflation knowing that almost full taxation changes would pass down to the retail level. We conducted an additional robustness check to the robustness of our results.

Marijuana legalization and traffic fatalities revisited

AbstractThe legal landscape for marijuana in the United States has changed dramatically over the last three decades. While several studies have examined the relationship between marijuana legalization and traffic fatalities, some of the research is becoming outdated and existing evidence remains mixed. Our research revisits the topic with two updates. First, our study includes states that legalized marijuana more recently and provides updated evidence on the effects of marijuana legalization. Second, considering recent discussions about the limitations of difference‐in‐differences designs, we employ alternative estimators that are robust to heterogeneous and dynamic treatment effects. Overall, our alternative estimators suggest either a smaller reduction (i.e., 3.9% drop in the overall fatality rate) or no change in traffic fatalities associated with legalizing marijuana for medical use, compared to the two‐way fixed‐effect estimator. We find no significant impact on traffic fatalities associated with legalizing marijuana for recreational use.

Causal effects of Renewable Portfolio Standards on renewable investments and generation: The role of heterogeneity and dynamics

Despite a 30-year long history, Renewable Portfolio Standards (RPS) remain controversial and debates continue to surround their efficacy in leading the low-carbon transition in the electricity sector. Contributing to the ongoing debates is the lack of definitive causal evidence on their impact on investments in renewable capacity and generation. This paper provides the most detailed analysis to date of the impact of RPSs on renewable electricity capacity investments and on generation. We use state-level data from 1990–2019 and recent econometric methods designed to address dynamic and heterogeneous treatment effects in a staggered adoption panel data design. We find that, on average, RPS policies increase wind generation capacity by 600–1200 MW, a 44% increase, but have no significant effect on investments in solar capacity. Additionally, we demonstrate that RPSs have slow dynamic effects: most of the capacity additions occur 5 years after RPS implementation. Estimates for wind and solar electricity generation mimic those for capacity investments. We also find similar results using an alternate treatment definition that allows states to meet their RPS requirements with pre-existing renewable generation and renewable generation from nearby states.

How anaerobic treatment is controlling the volatile components and key odorants of purple-colored leaf tea

Special purple-colored leaf tea products rich in γ-aminobutyric acid (GABA) have recently gained popularity. Although anaerobic treatment could effectively increase the GABA content in tea products, it also imparted an unknown unpleasant aroma. This study aimed to elucidate the dynamic effects of anaerobic treatment on volatile components during the purple-colored leaf tea processing and reveal the key aroma-active components. A total of 112 volatile components were identified, and it was found that anaerobic treatment could facilitate the accumulation of 2-heptanol, (E)− 2-hexenal, ethyl salicylate, phenylethyl alcohol, and (E,E)− 2,4-decadienal, but inhibited the formation of (Z)− 3-hexenyl acetate and methyl jasmonate. Moreover, 17 potent odorants including (E)-β-ionone, linalool, hexanal, 2-heptanol, (Z)− 3-nonen-1-ol, and (E,E)− 2,4-decadienal were distinguished as the key odorants of purple-colored leaf tea products rich in GABA based on gas chromatography–olfactometry and odor activity value analysis. These results provide new insights into the effect of anaerobic treatment on tea volatile metabolites.

Instrumental Variable Estimation of Dynamic Treatment Effects on a Duration Outcome

This article considers identification and estimation of the causal effect of the time Z until a subject is treated on a duration T. The time-to-treatment is not randomly assigned, T is randomly right censored by a random variable C, and the time-to-treatment Z is right censored by T ∧ C . The endogeneity issue is treated using an instrumental variable explaining Z and independent of the error term of the model. We study identification in a fully nonparametric framework. We show that our specification generates an integral equation, of which the regression function of interest is a solution. We provide identification conditions that rely on this identification equation. We assume that the regression function follows a parametric model for estimation purposes. We propose an estimation procedure and give conditions under which the estimator is asymptotically normal. The estimators exhibit good finite sample properties in simulations. Our methodology is applied to evaluate the effect of the timing of a therapy for burnout.

High-deductible Health Plans and Nonfatal Opioid Overdose.

Opioid-related overdose is a public health emergency in the United States. Meanwhile, high-deductible health plans (HDHPs) have become more prevalent in the United States over the last 2 decades, raising concern about their potential for discouraging high-need populations, like those with opioid use disorder (OUD), from engaging in care that may mitigate the probability of overdose. This study assesses the impact of an employer offering an HDHP on nonfatal opioid overdose among commercially insured individuals with OUD in the United States. We used deidentified insurance claims data from 2007 to 2017 with 97,788 person-years. We used an intent-to-treat, difference-in-differences regression framework to estimate the change in the probability of a nonfatal opioid overdose among enrollees with OUD whose employers began offering an HDHP insurance option during the study period compared with the change among those whose employer never offered an HDHP. We also used an event-study model to account for dynamic time-varying treatment effects. Across both comparison and treatment groups, 2% of the sample experienced a nonfatal opioid overdose during the study period. Our primary model and robustness checks revealed no impact of HDHP offer on the probability of a nonfatal overdose. Our study suggests that HDHP offer was not associated with an observed increase in the probability of nonfatal opioid overdose among commercially insured person-years with OUD. However, given the strong evidence that medications for OUD (MOUD) can reduce the risk of overdose, research should explore which facets of insurance design may impact MOUD use.

Institutional and macroeconomic stability mediate the effect of auctions on renewable energy capacity

Renewable energy (RE) auctions have become an increasingly popular policy instrument for decarbonizing the global energy matrix, and have been rapidly adopted by several countries worldwide. Previous research has used data from higher-income countries and two-way fixed effects models to estimate the impact of auctions on RE capacity, mostly with favorable results. However, these studies did not account for heterogeneous treatment effects across units to explore whether auctions are also effective in countries with unstable business environments. We analyze whether auctions also foster RE in countries experiencing macroeconomic instability or poor institutional quality. For this purpose, this study has drawn from multiple publicly available databases to build a dataset comprising 98 countries from 2000 to 2020. Our definition of RE includes solar, wind, and biomass sources. We first cluster countries by the quality of their business environment and then perform a differences-in-differences analysis considering staggered treatment adoption. We find that auctions positively affect RE capacity, yet the average treatment effects are higher for countries with better business environments. Thus, governments should exercise caution in adopting this instrument, especially in countries that experience macroeconomic or institutional instability. At the same time, dynamic treatment effects suggest that the policy needs time to show results.

An Introductory Guide to Event Study Models

The event study model is a powerful econometric tool used for the purpose of estimating dynamic treatment effects. One of its most appealing features is that it provides a built-in graphical summary of results, which can reveal rich patterns of behavior. Another value of the picture is the estimated pre-event pseudo-“effects,” which provide a type of placebo test. In this essay I aim to provide a framework for a shared understanding of these models. There are several (sometimes subtle) decisions and choices faced by users of these models, and I offer guidance for these decisions.

A Local Projections Approach to Difference-in-Differences Event Studies

Many of the challenges in the estimation of dynamic heterogeneous treatment effects can be resolved with local projection (LP) estimators of the sort used in applied macroeconometrics. This approach provides a convenient alternative to the more complicated solutions proposed in the recent literature on Difference in-Differences (DiD). The key is to combine LPs with a flexible ‘clean control’ condition to define appropriate sets of treated and control units. Our proposed LP-DiD estimator is clear, simple, easy and fast to compute, and it is transparent and flexible in its handling of treated and control units. Moreover, it is quite general, including in its ability to control for pre-treatment values of the outcome and of other time-varying covariates. The LP-DiD estimator does not suffer from the negative weighting problem, and indeed can be implemented with any weighting scheme the investigator desires. Simulations demonstrate the good performance of the LP-DiD estimator in common settings. Two recent empirical applications illustrate how LP-DiD addresses the bias of conventional fixed effects estimators, leading to potentially different results.

On event studies and distributed‐lags in two‐way fixed effects models: Identification, equivalence, and generalization

SummaryWe discuss three important properties of panel data event study designs. First, assuming constant treatment effects before and/or after some event time, also known as binning, is a natural restriction, which identifies dynamic treatment effects in the absence of never‐treated units. Second, event study designs with binned endpoints and distributed‐lag models are numerically identical. Third, classic dummy variable event study designs can be generalized to models that account for multiple treatments of different signs and varying intensities. We demonstrate the practical relevance of our methodological points in an application studying the effects of unemployment benefit duration on job search effort.

Dynamic effects of prognostic factors and individual survival prediction for amyotrophic lateral sclerosis disease.

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease affecting motor neurons, with broad heterogeneity in disease progression and survival in different patients. Therefore, an accurate prediction model will be crucial to implement timely interventions and prolong patient survival time. A total of 1260 ALS patients from the PRO-ACT database were included in the analysis. Their demographics, clinical variables, and death reports were included. We constructed an ALS dynamic Cox model through the landmarking approach. The predictive performance of the model at different landmark time points was evaluated by calculating the area under the curve (AUC) and Brier score. Three baseline covariates and seven time-dependent covariates were selected to construct the ALS dynamic Cox model. For better prognostic analysis, this model identified dynamic effects of treatment, albumin, creatinine, calcium, hematocrit, and hemoglobin. Its prediction performance (at all landmark time points, AUC ≥ 0.70 and Brier score ≤ 0.12) was better than that of the traditional Cox model, and it predicted the dynamic 6-month survival probability according to the longitudinal information of individual patients. We developed an ALS dynamic Cox model with ALS longitudinal clinical trial datasets as the inputs. This model can not only capture the dynamic prognostic effect of both baseline and longitudinal covariates but also make individual survival predictions in real time, which are valuable for improving the prognosis of ALS patients and providing a reference for clinicians to make clinical decisions.

Agri-food trade resilience among food-deficit countries during the COVID-19 pandemic

This paper examines the trade resilience of low-income and food-deficit countries (LIFDCs) during the COVID-19 pandemic. Since the pandemic declaration, LIFDCs have faced unique challenges due to their heavy reliance on food imports. This paper identifies the differential trade effects of COVID-19 lockdowns on agri-food exports to LIFDCs using a dynamic treatment effects model and monthly product-level agri-food trade data. The baseline results show a sharp decrease in agri-food exports to LIFDCs in the first three months after the pandemic declaration and a gradual recovery afterward. Additional analyses at the product and country levels show that LIFDCs focused on securing cereal products from foreign sources and that imports of other agri-food products contracted considerably relative to the counterfactual. The foreign supply chains of LIFDCs were less resilient in the first quarter after the treatment than those of other low-income countries, but their recovery was also faster than in those other countries. The paper provides the empirical underpinning for concerns raised by international organizations regarding the resilience of agri-food supply chains and COVID-19 containment measures, revealing the differential impact that lockdowns had on agri-food trade resilience in the developing world.

Terrorism, banking, and informal savings: Evidence from Nigeria

Conflict-affected societies have lower levels of economic growth. The financial development literature argues that one mechanism behind this is conflict increasing instability, lowering savings. However, the development studies literature highlights that conflict increases precautionary savings. I address this ambiguity arguing that savings do not necessarily fall, rather people opt for informal over formal savings channels as the latter are perceived as vulnerable to conflict. Informal savings are not recorded, explaining why some studies find that savings fall. The analysis uses data from the Nigerian General Household Survey Panel and the Global Terrorism Database with a dose response difference-in-difference model, exploiting variation in terrorism events within 500 5-km-squared locations over 2010–2018. The results confirm my intuition and are robust to several exercises, including to potential bias from heterogeneous time-dependent and dynamic treatment effects. Mechanism analysis suggest that post-conflict changes in risk aversity plays a role. The study ends with policy insights.

Workers' Job Mobility in Response to Severance Pay Generosity

This paper studies the impact of severance pay generosity on workers' voluntary mobility decisions. The identification strategy exploits a major labor market reform in Spain in February 2012 together with the exposure of some workers to a layoff shock. I rely on rich administrative data to estimate a discrete time duration model with dynamic treatment effects. The results show that a decrease in mobility costs induced by a reduction in severance pay made workers who expected to be displaced in the near future more likely to voluntarily leave their employers. The results indicate that policies targeting employers may also affect workers' behavior. They further reveal the relevance of taking into account interactions between employment protection and unemployment insurance.