Regression Discontinuity Research Articles

Impact of Ship Emission Control Area Policies on Port Air Quality—A Case Study of Ningbo Port, China

The implementation effectiveness of ship emission control area (ECA) policies can be effectively evaluated using econometric models. However, existing studies mainly focus on changes in SO2 concentrations in the air. In order to comprehensively assess the impact of ECA policies on air quality, this study takes Ningbo Port in China as an example and uses a regression discontinuity (RD) model to analyze the influence of ship emissions around the wharf on concentrations of SO2, NO2, and particulate matter (PM) in the air. The results indicate that individual ships’ activities within the monitoring area (within 300 m) make a relatively small contribution to the concentration of SO2 in the air and do not form a significant breakpoint. However, there is a noticeable breakpoint in the concentration of NO2 around the monitoring point as the ship approaches. At the same time, the variation range of PM2.5 is significantly greater than that of PM10, which aligns with the characteristics of PM emitted by ships. The experimental results have passed three robustness tests, demonstrating that the current policy on ship ECAs has a positive limiting effect on SO2 emissions and, to some extent, reduces PM emissions. However, further reductions in ship emissions may require more restrictions in nitrogen oxide emissions.

Impact of Urban Air Quality on Total Factor Productivity: Empirical Insights from Chinese Listed Companies

Urban air quality is inextricably linked to the operations of micro-firms. This paper employs the “Qinling-Huaihe” River demarcation as an instrumental variable to construct a regression discontinuity design (RDD) coupled with the two-stage least squares (2SLS) approach. This methodological framework is utilized to investigate the influence of urban air quality on the corporate total factor productivity (CTFP) of publicly listed manufacturing firms from 2015 to 2020. Drawing on the broken windows theory of urban decay and the general equilibrium theory, this research elucidates a significant adverse effect of urban air pollution on CTFP. We rigorously confirm the validity of the RDD by conducting covariate continuity tests and manipulating distributional variables. Furthermore, the robustness of the baseline regression outcomes is substantiated through a series of sensitivity, robustness, and endogeneity checks, employing alternative instrumental variables. The analysis extends to examining the heterogeneity across environmental attributes, regional features, and green branding. The mechanistic investigation reveals that public environmental concerns, financing constraints, and investments in technological innovation serve as mediators in the nexus between urban air pollution and CTFP. Additionally, it is observed that environmental regulation exerts a positive moderating influence, whereas female leadership has a negative impact in this context. The imperative for timely environmental governance is underscored by these findings, which offer crucial insights for policymakers seeking to refine business environment strategies and for corporations aiming to pursue sustainable growth.

Government-to-government peer pressure and air pollution: Causal evidence from an environmental ranking policy in China

This paper estimates the impact of peer governmental pressure on air quality using a regression discontinuity design inherent in China's air quality ranking system. Because air quality rankings are important for political evaluations, local officials who witnessed a decline in air quality ranking are motivated to enforce more stringent environmental standards compared to their counterparts with increased rankings. By exploiting this regulatory discontinuity with monthly air quality ranking data from 2012 to 2020 of 169 cities, we find that cities experiencing a lower air quality ranking in the current month compared to the previous month exhibit a subsequent improvement in air quality during the following month, as evidenced by decreased pollutant concentrations. Furthermore, our analysis reveals that in cities where pollutant rankings decline more sharply, officials are less likely to encounter fewer promotion opportunities. Importantly, we observe that the discontinuity in individual pollutant concentrations is not solely influenced by their respective rankings but is also impacted by the overall Air Quality Index (AQI) ranking. Linking the reduction in air pollutants concentration with the economic benefits, a back-of-the-envelope calculation indicates the decrease in premature deaths due to cardiovascular and respiratory diseases amounts to approximately 200 thousand, resulting in an associated economic saving of more than 600 billion Chinese yuan.

Use and Effectiveness of Academic Supports After Developmental Education Reform in California’s Community Colleges

AB705 is a landmark higher education policy that has changed approaches to developmental/remedial education in the California Community College system. We study one district that implemented reforms by placing most students in transfer-level math/English courses and encouraging enrollment in support courses based on multiple measures of academic preparation (e.g., grade point average [GPA]). We use regression discontinuity designs to examine the impact of these new placement recommendations, finding some benefits to English support course recommendations for low GPA students and increased math support course enrollment. We use matching methods to explore the relationship between support course enrollment and subsequent outcomes; finding enrollment in concurrent math and English support courses was associated with increased likelihood of completing transfer-level math and English.

How culture shapes choices related to fertility and mortality: causal evidence at the Swiss language border

Abstract Results from cultural evolutionary theory often suggest that social learning can lead cultural groups to differ markedly in the same environment. Put differently, cultural evolutionary processes can in principle stabilise behavioural differences between groups, which in turn could lead selection pressures to vary across cultural groups. Separating the effects of culture from other confounds, however, is often a daunting, sometimes intractable challenge for the working empiricist. To meet this challenge, we exploit a cultural border dividing Switzerland in ways that are independent of institutional, environmental, and genetic variation. Using a regression discontinuity design, we estimate discontinuities at the border in terms of preferences related to fertility and mortality, the two basic components of genetic fitness. We specifically select six referenda related to health and fertility and analyse differences in the proportion of yes votes across municipalities on the two sides of the border. Our results show multiple discontinuities and thus indicate a potential role of culture in shaping stable differences between groups in preferences and choices related to individual health and fertility. These findings further suggest that at least one of the two groups, in order to uphold its cultural values, has supported policies that could impose fitness costs on individuals relative to the alternative policy under consideration.

Do government performance signals affect citizen satisfaction?

AbstractPrevious studies have confirmed the causal effect of performance information on citizen satisfaction, but they were primarily conducted in survey experimental settings that featured hypothetical and abstract scenarios and primed respondents to look at certain aspects of performance information. Whether the causal effects hold in the real world, which is a much more complex information environment, is questionable. We address the gaps by employing a regression discontinuity design to identify the impact of public schools’ performance grades on parents’ satisfaction with teachers and overall education in New York City. We find that performance signals have independent and lasting effects on citizens’ satisfaction. However, the effects are nonlinear, depending on the levels of performance signals. Parents’ responses are muted at the A/B performance grade cutoff, but their satisfaction increases significantly at the B/C and C/D cutoffs if their schools earn relatively higher grades.

Regression discontinuity designs in education: a practitioner’s guide

Regression discontinuity designs in education: a practitioner’s guide

Expanding boundaries: The Impact of kindergarten availability on women's employment in China

This paper examines the causal effects of kindergarten availability on female employment outcomes in China. Using a regression discontinuity design based on the eligibility rules for kindergarten attendance, we find that kindergarten eligibility increases the probability of rural mothers working in non-agricultural sectors and their working hours in non-agricultural sectors, mainly by reducing time spent on agricultural and unpaid domestic work. However, we do not find a significant effect for urban mothers, possibly due to the availability of private childcare options. We also show that the impact of kindergarten eligibility on rural mothers' non-agricultural employment is stronger for those from low-income households, nuclear families, and with high exposure to traditional gender norms. Moreover, we provide evidence that kindergarten eligibility increases the non-agricultural employment of co-residing grandmothers in rural areas.

SARS-CoV-2 Test-to-Stay in Daycare.

Test-to-stay concepts apply serial testing of children in daycare after exposure to SARS-CoV-2 without use of quarantine. This study aims to assess the safety of a test-to-stay screening in daycare facilities. 714 daycare facilities and approximately 50 000 children ≤6 years in Cologne, Germany participated in a SARS-CoV-2 Pool-polymerase chain reaction (PCR) screening from March 2021 to April 2022. The screening initially comprised post-exposure quarantine and was adapted to a test-to-stay approach during its course. To assess safety of the test-to-stay approach, we explored potential changes in frequencies of infections among children after the adaptation to the test-to-stay approach by applying regression discontinuity in time (RDiT) analyses. To this end, PCR-test data were linked with routinely collected data on reported infections in children and analyzed using ordinary least squares regressions. 219 885 Pool-PCRs and 352 305 Single-PCRs were performed. 6440 (2.93%) Pool-PCRs tested positive, and 17 208 infections in children were reported. We estimated that during a period of 30 weeks, the test-to-stay concept avoided between 7 and 20 days of quarantine per eligible daycare child. RDiT revealed a 26% reduction (Exp. Coef: 0.74, confidence interval 0.52-1.06) in infection frequency among children and indicated no significant increase attributable to the test-to-stay approach. This result was not sensitive to adjustments for 7-day incidence, season, SARS-CoV-2 variant, and socioeconomic status. Our analyses provide evidence that suggest safety of the test-to-stay approach compared with quarantine measures. This approach offers a promising option to avoid use of quarantine after exposure to respiratory pathogens in daycare settings.

Leading digit bias in hemoglobin thresholds for red cell transfusion.

Leading digit bias is a heuristic whereby humans overemphasize the left-most digit when evaluating numbers (e.g., 9.99 vs. 10.00). The bias might affect the interpretation of hemoglobin results and influence red cell transfusion in hospitalized patients. Adults who received a red cell transfusion while registered at the University Health Network (Toronto, Canada) between January 1, 2016 and January 1, 2022 (n = 6 years) were included. The primary analysis excluded apheresis, red cell disorders, radiology suites, and operating rooms. The primary comparison was a regression discontinuity analysis of transfusion occurrence above and below the hemoglobin threshold of 79 g/L (local units). Additional analyses tested other leading digit and control thresholds (71, 81, and 91 g/L). Secondary analyses explored temporal covariates and clinical subgroups. A total of 211,872 red cell transfusions were identified over the study period (median pre-transfusion hemoglobin 76 g/L; interquartile range = 69-92 g/L), with 107,790 inpatient transfusions in the primary analysis. The 79 g/L threshold showed 815 fewer red cell units above the threshold (95% confidence interval [CI]: -1215 to -415). The 69 g/L threshold showed 2813 fewer transfused units (95% CI: -4407 to -1220), and 89 g/L showed 40 fewer units (95% CI: -408 to 328). The effect was accentuated during daytime, weekday, and May-June months, persisted in analyses including all transfusions, and was absent at control thresholds. Leading digit bias might have a modest influence on the decision to transfuse red cells. The findings may inform practice guidelines and quasi-experimental study design in transfusion research.

The role of household energy consumption behavior in environmental policy outcomes —the case of driving restriction policy in zhengzhou

The evaluation of the environmental effects of the driving restriction policy often sparks widespread discussions in the literature due to its complex and controversial assessment methods. Fewer studies have delved into the exploration of household energy consumption behavior, the role played by the targeted subjects of policy implementation, and the policy's impact on climate change. This paper focuses on the case of Zhengzhou, a city in China, to thoroughly discuss the formulation process of the driving restriction policy. By utilizing publicly available statistical data and conducting surveys among 795 households, this research employs statistical methods such as regression discontinuity, difference-in-differences estimation, and improved causal stepwise regression to quantitatively estimate the environmental consequences of the driving restriction policy. It also examines the impact of changes in residents' consumption behavior on policy effects and climate change under this policy shock. The study aims at bridging the gap between environmental policy effects, individual behavior changes, and climate change research. Our findings indicate that the driving restriction policy is effective in the short term, significantly improving air quality. However, due to the stickiness of residents' household consumption behavior and the adaptive adjustments in long-term travel behavior, the pollution-reducing effects of the policy gradually weaken and even exacerbate air pollution, resulting in an additional increase of approximately 147,950 tons of carbon dioxide emissions after the policy had been implemented for nine months. Therefore, this paper further suggests that implementing environmental policies requires close coordination with adjustments in household energy consumption behavior.

How does air pollution damage residents’ well-being? The evidence from China

ABSTRACT Air pollution is a prevalent environmental problem facing the world, critically threatening the well-being of human beings. Using the China Genuine Progress indicator Survey dataset, we investigate the impact of air pollution on residents’ well-being in China, and discuss the influencing mechanisms based on the theory of hierarchy of needs. As distinct winter heating policies cause different concentrations of air pollutants across the Qinling-Huaihe line in China, we construct a regression discontinuity design to identify the causal relationship. The results show that air pollution significantly damages residents’ well-being. If annual average air quality index increases by 50 units, residents’ happiness will fall by about 1.774 units. The mechanism analysis shows that air pollution reduces individual utility through increasing residents’ daily expenditure to meet their low-level needs while reducing consumptions for higher-level needs, namely the so-called ‘consumption downgrade’. Heterogeneity analysis shows that residents with higher education levels, middle-income level, longer commute time, and stronger public awareness are more affected by air pollution. In sum, policymakers should highlight the impact of the environment on people’s subjective well-being and formulate appropriate intervention policies to alleviate adverse demographic changes that may harm the sustainable development.

Extended Postpartum Medicaid In Colorado Associated With Increased Treatment For Perinatal Mood And Anxiety Disorders.

Perinatal mood and anxiety disorders (PMAD), a leading cause of perinatal morbidity and mortality, affect approximately one in seven births in the US. To understand whether extending pregnancy-related Medicaid eligibility from sixty days to twelve months may increase the use of mental health care among low-income postpartum people, we measured the effect of retaining Medicaid as a low-income adult on mental health treatment in the postpartum year, using a "fuzzy" regression discontinuity design and linked all-payer claims data, birth records, and income data from Colorado from the period 2014-19. Relative to enrolling in commercial insurance, retaining postpartum Medicaid enrollment was associated with a 20.5-percentage-point increase in any use of prescription medication or outpatient mental health treatment, a 16.0-percentage-point increase in any use of prescription medication only, and a 7.3-percentage-point increase in any use of outpatient mental health treatment only. Retaining postpartum Medicaid enrollment was also associated with $40.84 lower out-of-pocket spending per outpatient mental health care visit and $3.24 lower spending per prescription medication for anxiety or depression compared with switching to commercial insurance. Findings suggest that extending postpartum Medicaid eligibility may be associated with higher levels of PMAD treatment among the low-income postpartum population.

Ridesourcing regulation and traffic speeds: A New York case

Since 2019, New York City has enacted laws restricting ridesourcing services. This study investigates these regulations' impact on traffic using street-level speed records. We used a regression discontinuity design to compare weekly traffic speeds immediately before and after regulations. We find that the for-hire-vehicle driver application freeze, implemented in April 2019, significantly boosted street speeds in the immediate run. The effect varied widely across boroughs, road types, and built environment characteristics. Further evidence suggests a post-policy reduction in ridesourcing supply, indicating that the policy primarily impacted ridesourcing companies' scale and operations. However, the speed improvement appears to be temporary. Our findings offer valuable insights for crafting regulations targeting new urban mobility forms.

The effect of regime change on entrepreneurship: A real options approach with evidence from US gubernatorial elections

Although political turnover is said to be a healthy component of the business environment, the literature is equivocal about the effects of regime change on early-stage entrepreneurial activity. I present incumbent displacement—the electoral defeat of an incumbent political party's candidate—as a source of regime change, and I analyze how this affects business formation through the lens of real options theory. I test my theory using US gubernatorial elections from 2004 to 2022, leveraging a Regression Discontinuity design to compare changes in business formation trends following elections where a challenger party candidate wins or loses by a close margin. I find that regime change reduces venture creation activity for growth-oriented ventures specifically. I also find evidence of a partial rebound in subsequent months—suggestive that some entrepreneurs delay entry while others permanently abandon their ventures.

Reduced disclosure and default risk: analysis of smaller reporting companies

AbstractWe examine the causal effect of reduced disclosure levels on the risk of default. Employing regression discontinuity (RD) design as our main identification strategy and the smaller reporting company rule (SRC rule) as the exogenous source of variation, we show that smaller reporting companies (SRCs), which are permitted to provide scaled disclosures in their 10-Ks, experience significantly and economically higher default risk. We demonstrate that, while there is no effect of information loss if a smaller reporting company voluntarily maintains its disclosure level by continuing to report its financial performance in full, there is an increase in its default risk due to the loss of commitment to mandatory disclosure. We also find that, compared to previously qualified SRCs, newly qualified smaller reporting companies face steeper increases in bankruptcy risk during their first year of eligibility. Our analysis indicates that strong external oversight mechanisms, better corporate governance, and credible audit quality attenuate the negative impact of reduced disclosure levels on the risk of default. Our results are robust to alternative model specifications, RD design assumptions, and measures of default risk.

Impact of higher capital buffers on banks’ lending and risk-taking in the short- and medium-term: Evidence from the euro area experiments

We study the impact of higher capital buffers on bank lending and risk-taking behaviour, at different time horizons following the initial policy decision. Employing a regression discontinuity design and confidential centralised supervisory data for euro area banks from 2014 to 2017, our research uniquely explores the effects of the EU policy on other systemically important institutions (O-SIIs) through a quasi-randomised experiment, exploiting the induced policy change and discontinuity of the O-SII identification process. Our findings show that the introduction of the O-SII buffers resulted in a short-term reduction in credit supply to households and financial sector, followed by a medium-term shift towards less risky borrowers, particularly in the household sector. We find a temporary cut in loan growth post-capital hikes, succeeded by a rebound in the medium-term. Our results substantiate the hypothesis that higher capital buffers can positively discipline banks by reducing risk-taking in the medium-term. At the same time, evidence suggests a limited adverse impact on the real economy, characterised by a temporary reduction in credit supply restricted to instances of macroprudential policy tightening.

Firms as tax collectors

We show that delegating tax collection duties to large firms can bolster tax capacity in weak-enforcement settings. We exploit two reforms in Argentina that dramatically expanded and subsequently reduced turnover tax withholding by firms. Combining firm-to-firm data with regression discontinuity and difference-in-differences methods centered on revenue eligibility thresholds, we find that: (i) appointing large firms as collection agents (CAs) does not hinder their economic activity, (ii) it leads to a significant increase in self-reported sales and tax payments among CAs’ business partners, (iii) these effects are primarily concentrated among downstream firms that lack a traceable paper trail, and (iv) reductions in withholding lead to a decrease in self-reported sales, albeit to a lesser extent. Tax-collecting firms can thus help boost tax compliance and revenue.

The Spillover Effects of the Spouse's Retirement on Depression: Evidence From Chinese Middle-Aged and Older Adult Couples.

The present study expands on previous research by examining whether the spouse's retirement affects individual depression both directly, by the changes in individual health investment, and indirectly, through the social interaction effect of the couples' depression. Using the panel data from the 2010-2018 China Family Panel Studies, we investigate the direct and indirect spillover effects of the spouse's retirement on depression among Chinese urban-worker couples (men aged 50-70, women aged 40-60; n = 10,466). To address the potential endogeneity and reflect the social interaction effect of the couples' depression, we combine the Fuzzy Regression Discontinuity method with simultaneous equations. Overall, a spouse's retirement would improve an individual's depression, with the direct spillover dominating compared to the indirect spillover. Gender heterogeneity indicates that husbands' depression is improved by wives' retirement mainly because husbands might receive more healthcare and companionship provided by their retired wives, while wives' depression is aggravated by husbands' retirement because of the decline in household income and the lesser health investment. This difference is more evident when wives retire earlier and both spouses retire in the same year. With the spouse's retirement years increasing, husbands' depression improves and wives' depression declines each year. Moreover, spouses' depression is significantly interactive, and wives' depression is more vulnerable to husbands' depression. The results highlight that the health spillover effects of the spouse's retirement need greater attention in future research and retirement reform.

Effectiveness of an Artificial Intelligence–Enabled Intervention for Detecting Clinical Deterioration

Inpatient clinical deterioration is associated with substantial morbidity and mortality but may be easily missed by clinicians. Early warning scores have been developed to alert clinicians to patients at high risk of clinical deterioration, but there is limited evidence for their effectiveness. To evaluate the effectiveness of an artificial intelligence deterioration model-enabled intervention to reduce the risk of escalations in care among hospitalized patients using a study design that facilitates stronger causal inference. This cohort study used a regression discontinuity design that controlled for confounding and was based on Epic Deterioration Index (EDI; Epic Systems Corporation) prediction model scores. Compared with other observational research, the regression discontinuity design facilitates causal analysis. Hospitalized adults were included from 4 general internal medicine units in 1 academic hospital from January 17, 2021, through November 16, 2022. An artificial intelligence deterioration model-enabled intervention, consisting of alerts based on an EDI score threshold with an associated collaborative workflow among nurses and physicians. The primary outcome was escalations in care, including rapid response team activation, transfer to the intensive care unit, or cardiopulmonary arrest during hospitalization. During the study, 9938 patients were admitted to 1 of the 4 units, with 963 patients (median [IQR] age, 76.1 [64.2-86.2] years; 498 males [52.3%]) included within the primary regression discontinuity analysis. The median (IQR) Elixhauser Comorbidity Index score in the primary analysis cohort was 10 (0-24). The intervention was associated with a -10.4-percentage point (95% CI, -20.1 to -0.8 percentage points; P = .03) absolute risk reduction in the primary outcome for patients at the EDI score threshold. There was no evidence of a discontinuity in measured confounders at the EDI score threshold. Using a regression discontinuity design, this cohort study found that the implementation of an artificial intelligence deterioration model-enabled intervention was associated with a significantly decreased risk of escalations in care among inpatients. These results provide evidence for the effectiveness of this intervention and support its further expansion and testing in other care settings.