scholarly journals Testing the Accuracy of Regression Discontinuity Analysis Using Experimental Benchmarks

2009 ◽  
Vol 17 (4) ◽  
pp. 400-417 ◽  
Author(s):  
Donald P. Green ◽  
Terence Y. Leong ◽  
Holger L. Kern ◽  
Alan S. Gerber ◽  
Christopher W. Larimer
Keyword(s):  
Regression Discontinuity ◽  
Bandwidth Selection ◽  
Risk Of Bias ◽  
Causal Effects ◽  
Model Specification ◽  
Flexible Functional Forms ◽  
Bias Model ◽  
Statistical Precision ◽  
Functional Forms ◽  
Using Data

Regression discontinuity (RD) designs enable researchers to estimate causal effects using observational data. These causal effects are identified at the point of discontinuity that distinguishes those observations that do or do not receive the treatment. One challenge in applying RD in practice is that data may be sparse in the immediate vicinity of the discontinuity. Expanding the analysis to observations outside this immediate vicinity may improve the statistical precision with which treatment effects are estimated, but including more distant observations also increases the risk of bias. Model specification is another source of uncertainty; as the bandwidth around the cutoff point expands, linear approximations may break down, requiring more flexible functional forms. Using data from a large randomized experiment conducted by Gerber, Green, and Larimer (2008), this study attempts to recover an experimental benchmark using RD and assesses the uncertainty introduced by various aspects of model and bandwidth selection. More generally, we demonstrate how experimental benchmarks can be used to gauge and improve the reliability of RD analyses.

scholarly journals Constraints in models of production and cost via slack-based measures

2021 ◽  
Author(s):  
Caroline Khan ◽  
Mike G. Tsionas
Keyword(s):  
Power Generation ◽  
Stochastic Frontier ◽  
Inequality Constraints ◽  
Order Conditions ◽  
Flexible Functional Forms ◽  
Cost Share ◽  
First Order ◽  
Stochastic Frontier Models ◽  
Endogenous Variables ◽  
Functional Forms

AbstractIn this paper, we propose the use of stochastic frontier models to impose theoretical regularity constraints (like monotonicity and concavity) on flexible functional forms. These constraints take the form of inequalities involving the data and the parameters of the model. We address a major concern when statistically endogenous variables are present in these inequalities. We present results with and without endogeneity in the inequality constraints. In the system case (e.g., cost-share equations) or more generally, in production function-first-order conditions case, we detect an econometric problem which we solve successfully. We provide an empirical application to US electric power generation plants during 1986–1997, previously used by several authors.

scholarly journals Deep learning for cephalometric landmark detection: systematic review and meta-analysis

2021 ◽  
Author(s):  
Falk Schwendicke ◽  
Akhilanand Chaurasia ◽  
Lubaina Arsiwala ◽  
Jae-Hong Lee ◽  
Karim Elhennawy ◽  
...  
Keyword(s):  
Systematic Review ◽  
Deep Learning ◽  
Meta Analysis ◽  
High Accuracy ◽  
Risk Of Bias ◽  
Automated Detection ◽  
Reference Test ◽  
Landmark Detection ◽  
Future Studies ◽  
Using Data

Abstract Objectives Deep learning (DL) has been increasingly employed for automated landmark detection, e.g., for cephalometric purposes. We performed a systematic review and meta-analysis to assess the accuracy and underlying evidence for DL for cephalometric landmark detection on 2-D and 3-D radiographs. Methods Diagnostic accuracy studies published in 2015-2020 in Medline/Embase/IEEE/arXiv and employing DL for cephalometric landmark detection were identified and extracted by two independent reviewers. Random-effects meta-analysis, subgroup, and meta-regression were performed, and study quality was assessed using QUADAS-2. The review was registered (PROSPERO no. 227498). Data From 321 identified records, 19 studies (published 2017–2020), all employing convolutional neural networks, mainly on 2-D lateral radiographs (n=15), using data from publicly available datasets (n=12) and testing the detection of a mean of 30 (SD: 25; range.: 7–93) landmarks, were included. The reference test was established by two experts (n=11), 1 expert (n=4), 3 experts (n=3), and a set of annotators (n=1). Risk of bias was high, and applicability concerns were detected for most studies, mainly regarding the data selection and reference test conduct. Landmark prediction error centered around a 2-mm error threshold (mean; 95% confidence interval: (–0.581; 95 CI: –1.264 to 0.102 mm)). The proportion of landmarks detected within this 2-mm threshold was 0.799 (0.770 to 0.824). Conclusions DL shows relatively high accuracy for detecting landmarks on cephalometric imagery. The overall body of evidence is consistent but suffers from high risk of bias. Demonstrating robustness and generalizability of DL for landmark detection is needed. Clinical significance Existing DL models show consistent and largely high accuracy for automated detection of cephalometric landmarks. The majority of studies so far focused on 2-D imagery; data on 3-D imagery are sparse, but promising. Future studies should focus on demonstrating generalizability, robustness, and clinical usefulness of DL for this objective.

Causal effects of corporate taxes on private firms' earnings management: a regression discontinuity analysis

2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Gaowen Kong
Keyword(s):  
Earnings Management ◽  
Regression Discontinuity ◽  
Tax Incentives ◽  
Causal Effects ◽  
Private Firms ◽  
Effective Tax Rate ◽  
Tax Collection ◽  
Content Type ◽  
Tax Rate ◽  
Earnings Information

PurposeThe authors emphasize the information role of earnings management and how it may be used to “mislead some stakeholders about the underlying economic performance of the company or to influence contractual outcomes that depend on reported accounting numbers.” Specifically, the authors examine the causal effect of tax incentives on private firms' earnings management based on a corporate tax reform in China.Design/methodology/approachIn December 2001, China implemented a tax collection reform which moved the collection of corporate income taxes from the local tax bureau to the state tax bureau. This reform results in exogenous variations in the effective tax rate among similar firms established before and after 2002. The authors apply a regression discontinuity design and use the generated variation in the effective tax rate to investigate the impact of taxes on firm earnings management.FindingsThe authors find that tax reduction substantially increases private firms' incentives to manage earnings information, and such effect is particularly pronounced when tax collection intensity and government interventions are low. Further evidence shows that lower tax rates stimulate firms' investment, inventory turnover and recruitment of skilled human capital. A plausible mechanism is that private firms signal a promising outlook by managing earnings to attain greater financing and improve investment/operation levels when financial constraints are removed.Originality/valueFirst, the authors present the causal effects of tax incentives on private firm's earnings management, which deepens the authors’ understanding on the determinants of firm's earnings information production. Second, this study also contributes to the literature on tax-induced earnings management. Third, the authors believe that this topic offers clear policy implications and would be of particular interest to regulators.

scholarly journals Graphical Models for Quasi-experimental Designs

2015 ◽  
Vol 46 (2) ◽  
pp. 155-188 ◽  
Author(s):  
Peter M. Steiner ◽  
Yongnam Kim ◽  
Courtney E. Hall ◽  
Dan Su
Keyword(s):  
Graphical Models ◽  
Instrumental Variable ◽  
Regression Discontinuity ◽  
Experimental Designs ◽  
Causal Effects ◽  
Confounding Bias ◽  
Randomized Controlled ◽  
Quasi Experimental ◽  
Causal Graphs ◽  
Latent Subgroups

Randomized controlled trials (RCTs) and quasi-experimental designs like regression discontinuity (RD) designs, instrumental variable (IV) designs, and matching and propensity score (PS) designs are frequently used for inferring causal effects. It is well known that the features of these designs facilitate the identification of a causal estimand and, thus, warrant a causal interpretation of the estimated effect. In this article, we discuss and compare the identifying assumptions of quasi-experiments using causal graphs. The increasing complexity of the causal graphs as one switches from an RCT to RD, IV, or PS designs reveals that the assumptions become stronger as the researcher’s control over treatment selection diminishes. We introduce limiting graphs for the RD design and conditional graphs for the latent subgroups of compliers, always takers, and never takers of the IV design, and argue that the PS is a collider that offsets confounding bias via collider bias.

scholarly journals A regression discontinuity analysis of the social distancing recommendations for older adults in Sweden during COVID-19

2021 ◽  
Author(s):  
Carl Bonander ◽  
Debora Stranges ◽  
Johanna Gustavsson ◽  
Matilda Almgren ◽  
Malin Inghammar ◽  
...  
Keyword(s):  
Older Adults ◽  
Regression Discontinuity ◽  
Model Specification ◽  
Regression Discontinuity Design ◽  
Sharp Drop ◽  
Social Distancing ◽  
Disease Outcomes ◽  
The Social ◽  
National Register Data ◽  
The Impact

Objectives: To study the impact of non-mandatory, age-specific social distancing recommendations for older adults (70+ years) in Sweden on isolation behaviors and disease outcomes during the first wave of the COVID-19 pandemic. Methods: Our study relies on self-reported isolation data from COVID Symptom Study Sweden (n = 96,053) and national register data on COVID-19 hospitalizations, deaths, and confirmed cases. We use a regression discontinuity design to account for confounding factors, exploiting the fact that exposure to the recommendation was a discontinuous function of age. Results: By comparing individuals just above to those just below the age limit for the policy, our analyses revealed a sharp drop in the weekly number of visits to crowded places at the 70-year-threshold (-13%). Severe COVID-19 cases (hospitalizations or deaths) also dropped abruptly by 16% at the 70-year-threshold. Our data suggest that the age-specific recommendations prevented approximately 1,800 to 2,700 severe COVID-19 cases, depending on model specification. Conclusion: The non-mandatory, age-specific recommendations helped control the COVID-19 pandemic in Sweden.

Provocation and the Strategy of Terrorist and Guerrilla Attacks

2015 ◽  
Vol 70 (1) ◽  
pp. 133-173 ◽  
Author(s):  
David B. Carter
Keyword(s):  
Empirical Model ◽  
Western Europe ◽  
Model Specification ◽  
Terrorist Attacks ◽  
Specification Tests ◽  
State Response ◽  
Target Theory ◽  
Response Groups ◽  
Using Data ◽  
State Responses

AbstractViolent nonstate groups are usually weaker than the states they target. Theory suggests that groups carefully condition their choice of tactics on anticipated state response. Yet scholars know very little about whether and how groups strategically plan attacks in anticipation of state response. Scholars do not know if and under what conditions groups employ violent tactics to provoke or avoid a forceful state response, although extant theory is consistent with both possibilities. Relatedly, there is little systematic evidence about why groups choose terrorist or guerrilla tactics and how this choice relates to anticipated state response. I develop a theoretical and empirical model of the interaction between groups and states that generates unique evidence on all three fronts. Using data on attacks in Western Europe from 1950 to 2004, I show that guerrilla attacks are sometimes associated with provoking forceful state response, whereas terrorist attacks are generally associated with avoiding forceful response. Groups effectively choose their tactics to avoid forceful state responses that are too damaging for themselves but provoke forceful responses that disproportionately harm civilians. These findings survive several robustness and model specification tests.

scholarly journals The Use of Green Coffee Extract as a Weight Loss Supplement: A Systematic Review and Meta-Analysis of Randomised Clinical Trials

2011 ◽  
Vol 2011 ◽  
pp. 1-6 ◽  
Author(s):  
Igho Onakpoya ◽  
Rohini Terry ◽  
Edzard Ernst
Keyword(s):  
Weight Loss ◽  
Clinical Trials ◽  
Methodological Quality ◽  
Meta Analysis ◽  
Risk Of Bias ◽  
Significant Heterogeneity ◽  
Green Coffee ◽  
Significant Difference ◽  
Using Data

The purpose of this paper is to assess the efficacy of green coffee extract (GCE) as a weight loss supplement, using data from human clinical trials. Electronic and nonelectronic searches were conducted to identify relevant articles, with no restrictions in time or language. Two independent reviewers extracted the data and assessed the methodological quality of included studies. Five eligible trials were identified, and three of these were included. All studies were associated with a high risk of bias. The meta-analytic result reveals a significant difference in body weight in GCE compared with placebo (mean difference: kg; 95%CI: , ). The magnitude of the effect is moderate, and there is significant heterogeneity amongst the studies. It is concluded that the results from these trials are promising, but the studies are all of poor methodological quality. More rigorous trials are needed to assess the usefulness of GCE as a weight loss tool.

Sign in / Sign up

Export Citation Format

Share Document