- â (2021). Incorporating ethics and welfare into randomized experiments. Proceedings of the National Academy of Sciences, 118 (1).
Paper not yet in RePEc: Add citation now
- â and Kolesár, M. (2020). Finite-Sample Optimal Estimation and Inference on Average Treatment Effects Under Unconfoundedness. Econometrica.
Paper not yet in RePEc: Add citation now
â and Rosenbaum, P. R. (2005). Robust, Accurate Confidence Intervals with a Weak Instrument: Quarter of Birth and Education. Journal of the Royal Statistical Society: Series A (Statistics in Society), 168 (1), 109â126.
â and Wager, S. (2019). Optimized Regression Discontinuity Designs. Review of Economics and Statistics, 101 (2), 264â278.
- A Extensions and Discussions A.1 Related Literature: Details In this section, we discuss the related methodological literature on the multidimensional RDD in detail. Imbens and Wager (2019) propose the finite-sample-minimax linear estimator of the form Pn i=1 γiYi and uniform confidence intervals for treatment effects in the multidimensional RDD.
Paper not yet in RePEc: Add citation now
â, â and Sundaram, A. (2015). Investment Decisions of Nonprofit Firms: Evidence from Hospitals. Journal of Finance, 70 (4), 1583â1628.
- â, â, â and Keele, L. (2016). Interpreting Regression Discontinuity Designs with Multiple Cutoffs. Journal of Politics, 78 (4), 1229â1248.
Paper not yet in RePEc: Add citation now
â, Titiunik, R. and Vazquez-Bare, G. (2017). Comparing Inference Approaches for RD Designs: A Reexamination of the Effect of Head Start on Child Mortality. Journal of Policy Analysis and Management, 36 (3), 643â681.
â, Yasui, S. and Yata, K. (2019). Efficient Counterfactual Learning from Bandit Feedback. Proceedings of the 33rd AAAI Conference on Artificial Intelligence, pp. 4634â4641.
- AbdulkadiroÄlu, A. (2013). Instrumental Variable Estimation in School Choice. Private Communication. AbdulkadiroÄlu, A., Angrist, J. D., Narita, Y. and Pathak, P. A. (2017). Research Design Meets Market Design: Using Centralized Assignment for Impact Evaluation. Econometrica, 85 (5), 1373â1432. â, â, â and Pathak, P. A. (Forthcoming). Breaking Ties: Regression Discontinuity Design Meets Market Design. Econometrica.
Paper not yet in RePEc: Add citation now
- Adelino, M., Lewellen, K. and McCartney, W. B. (2021). Hospital Financial Health and Clinical Choices: Evidence from the Financial Crisis. Management Science.
Paper not yet in RePEc: Add citation now
- Agarwal, S., Chomsisengphet, S., Mahoney, N. and Stroebel, J. (2017). Do Banks Pass Through Credit Expansions to Consumers Who Want to Borrow? Quarterly Journal of Economics, 133 (1), 129â190.
Paper not yet in RePEc: Add citation now
- Angrist, J. D. and Pischke, J.-S. (2008). Mostly Harmless Econometrics: An Empiricistâs Companion. Princeton University Press.
Paper not yet in RePEc: Add citation now
Arias, J. E., Rubio-RamÃrez, J. F. and Waggoner, D. F. (2018). Inference Based on Structural Vector Autoregressions Identified with Sign and Zero Restrictions: Theory and Applications. Econometrica, 86 (2), 685â720.
Armstrong, T. B. and Kolesár, M. (2018). Optimal Inference in a Class of Regression Models. Econometrica, 86 (2), 655â683.
Athey, S. and Imbens, G. W. (2017). The State of Applied Econometrics: Causality and Policy Evaluation. Journal of Economic Perspectives, 31 (2), 3â32.
Belloni, A., Chernozhukov, V., Fernández-Val, I. and Hansen, C. (2017). Program Evaluation and Causal Inference with High-Dimensional Data. Econometrica, 85 (1), 233â 298.
- Bonhomme, S., Lamadon, T. and Manresa, E. (2019). Discretizing Unobserved Heterogeneity.
Paper not yet in RePEc: Add citation now
Bornn, L., Shephard, N. and Solgi, R. (2019). Moment conditions and bayesian nonparametrics. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 81 (1), 5â43.
Borusyak, K. and Hull, P. (2020). Non-Random Exposure to Exogenous Shocks: Theory and Applications. NBER Working Paper No. 27845, unpublished Manuscript, University of Chicago.
Brown, D., Kowalski, A. E. and Lurie, I. Z. (2020). Long-Term Impacts of Childhood Medicaid Expansions on Outcomes in Adulthood. The Review of Economic Studies, 87 (2), 729â821.
Bundorf, K., Polyakova, M. and Tai-Seale, M. (2019). How Do Humans Interact with Algorithms? Experimental Evidence from Health Insurance. NBER Working Paper No. 25976.
Calonico, S., Cattaneo, M. D. and Titiunik, R. (2014). Robust Nonparametric Confidence Intervals for Regression-Discontinuity Designs. Econometrica, 82 (6), 2295â2326.
- Cattaneo, M. D., Frandsen, B. R. and Titiunik, R. (2015). Randomization Inference in the Regression Discontinuity Design: An Application to Party Advantages in the US Senate. Journal of Causal Inference, 3 (1), 1â24.
Paper not yet in RePEc: Add citation now
- Certification Number. We have data for 4,705 providers for the 2018 financial year. We focus on 4,648 acute care and critical access hospitals that are either located in one of the 50 states or Washington DC.
Paper not yet in RePEc: Add citation now
Cohen, P., Hahn, R., Hall, J., Levitt, S. and Metcalfe, R. (2016). Using Big Data to Estimate Consumer Surplus: The Case of Uber. NBER Working Paper No. 22627, unpublished Manuscript, University of Chicago.
- Confirmed ICU Patients (d) # Confirmed COVID Patients in ICU Notes: The figure shows the results of estimating our main 2SLS specification about the effect of $1mm of relief funding on weekly hospital outcomes from 07/31/2020 to 04/02/2021. The outcomes record the 7-day sum of the number of hospitalized patients with the specified condition. We compute the Approximate Propensity Score with S = 10, 000 and δ = 0.05. The estimates from the uncontrolled OLS, uncontrolled 2SLS, and 2SLS with the Approximate Propensity Score controls are plotted on the y-axis. Standard error ribbons are given in grey.
Paper not yet in RePEc: Add citation now
- Cowgill, B. (2018). The Impact of Algorithms on Judicial Discretion: Evidence from Regression Discontinuities. Unpublished Manuscript, Columbia Business School.
Paper not yet in RePEc: Add citation now
- Crasta, G. and Malusa, A. (2007). The Distance Function from the Boundary in a Minkowski Space. Transactions of the American Mathematical Society, 359, 5725â5759.
Paper not yet in RePEc: Add citation now
Currie, J. and Gruber, J. (1996). Health Insurance Eligibility, Utilization of Medical Care, and Child Health. Quarterly Journal of Economics, 111 (2), 431â466.
Dong, Y. (2018). Alternative Assumptions to Identify LATE in Fuzzy Regression Discontinuity Designs. Oxford Bulletin of Economics and Statistics, 80 (5), 1020â1027.
Dranove, D., Garthwaite, C. and Ody, C. (2017). How Do Nonprofits Respond to Negative Wealth Shocks? The Impact of the 2008 Stock Market Collapse on Hospitals. RAND Journal of Economics, 48 (2), 485â525.
Duggan, M. G. (2000). Hospital Ownership and Public Medical Spending. Quarterly Journal of Economics, 115 (4), 1343â1373.
- Eckles, D., Ignatiadis, N., Wager, S. and Wu, H. (2020). Noise-induced Randomization in Regression Discontinuity Designs. arXiv preprint arXiv:2004.09458.
Paper not yet in RePEc: Add citation now
- Einav, L., Finkelstein, A., Mullainathan, S. and Obermeyer, Z. (2018). Predictive Modeling of U.S. Health Care Spending in Late Life. Science, 360 (6396), 1462â1465.
Paper not yet in RePEc: Add citation now
- Ernst, D., Geurts, P. and Wehenkel, L. (2005). Tree-Based Batch Mode Reinforcement Learning. Journal of Machine Learning Research, 6, 503â556.
Paper not yet in RePEc: Add citation now
Frölich, M. (2007). Regression Discontinuity Design with Covariates. IZA Discussion Paper No. 3024, unpublished Manuscript, University of St. Gallen.
Frölich, M. and Huber, M. (2019). Including Covariates in the Regression Discontinuity Design. Journal of Business and Economic Statistics, 37 (4), 736â748.
Frandsen, B. R. (2017). Party Bias in Union Representation Elections: Testing for Manipulation in the Regression Discontinuity Design When the Running Variable is Discrete. In Regression Discontinuity Designs: Theory and Applications, Emerald Publishing Limited, pp. 281â315.
- Funding We calculate the projected funding using the formula on the CARES ACT website. Hospitals that do not qualify on any of the three dimensions are not given any funding. Each eligible hospital is assigned an individual facility score, which is calculated as the product of disproportionate patient percentage and number of beds in that hospital. We calculate cumulative facility score as the sum of all individual facility scores in the dataset. Each hospital receives a share of $10 billion, where the share is determined by the ratio of individual facility score of that hospital to the cumulative facility score. The amount of funding received by hospitals is bounded below at $5 million and capped above at $50 million. 43 For the precise definition, see https://www.cms.gov/Medicare/Medicare-Fee-for-Service-Payment/ AcuteInpatientPPS/dsh. 44 The precise definition can be found at https://www.aha.org/fact-sheets/2020-01-06-fact-sheetuncompensated -hospital-care-cost.
Paper not yet in RePEc: Add citation now
- Furthermore, for every x â N(âS, ) \ âS, Î âS(x) is a singleton as shown in the proof of Theorem 4.16 of Crasta and Malusa (2007). Let ÏâS(x) be the unique element in Î âS(x). By Lemma 4.3 of Crasta and Malusa (2007), for every x â N(âS, ) \ âS, âds S(x) = νS(ÏâS(x)) ÏK(νS(ÏâS(x))) = νS(ÏâS(x)) kνS(ÏâS(x))k = νS(ÏâS(x)), where the last equality follows since νS(ÏâS(x)) is a unit vector. It then follows that kâds S(x)k = kνS(ÏâS(x))k = 1 for every x â N(âS, ) \ âS.
Paper not yet in RePEc: Add citation now
- Gulshan, V. et al. (2016). Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. Journal of the American Medical Association, 316 (22), 2402â2410.
Paper not yet in RePEc: Add citation now
Hahn, J., Todd, P. and van der Klaauw, W. (2001). Identification and Estimation of Treatment Effects with a Regression-Discontinuity Design. Econometrica, 69 (1), 201â209.
- Hoffman, M., Kahn, L. B. and Li, D. (2017). Discretion in Hiring. Quarterly Journal of Economics, 133 (2), 765â800.
Paper not yet in RePEc: Add citation now
Horton, J. J. (2017). The Effects of Algorithmic Labor Market Recommendations: Evidence from a Field Experiment. Journal of Labor Economics, 35 (2), 345â385.
- Hull, P. (2018). Subtracting the Propensity Score in Linear Models. Unpublished Manuscript, MIT.
Paper not yet in RePEc: Add citation now
- νS(x0) kνS(x0)k = νS(x0), where the last equality follows since νS(x0) is a unit vector. It then follows that kâds S(x0)k = kνS(x0)k = 1 for every x0 â âS. Also, it is obvious that, for every x0 â âS, Î âS(x0) = {x0} and x0 = x0 + ds S(x0)νS(x0), since ds S(x0) = 0. In addition, as stated in the proof of Theorem 4.16 of Crasta and Malusa (2007), is chosen so that (4.7) in Proposition 4.6 of Crasta and Malusa (2007) holds for every x0 â âS and every t â (â, ). That is, Î âS(x0 + tâÏK(νS(x0))) = {x0} for every x0 â âS and every t â (â, ). Since âÏK(νS(x0)) = νS(x0) kνS(x0)k = νS(x0), Î âS(x0 + tνS(x0)) = {x0} for every x0 â âS and every t â (â, ).
Paper not yet in RePEc: Add citation now
Imbens, G. and Kalyanaraman, K. (2012). Optimal Bandwidth Choice for the Regression Discontinuity Estimator. The Review of Economic Studies, 79 (3), 933â959.
Imbens, G. W. and Angrist, J. D. (1994). Identification and Estimation of Local Average Treatment Effects. Econometrica, 62 (2), 467â475.
- It then follows from Theorem 4.16 of Crasta and Malusa (2007) that ds S is twice continuously differentiable on N(âS, ) for some > 0, and for every x0 â âS, âds S(x0) = νS(x0) ÏK(νS(x0)) =
Paper not yet in RePEc: Add citation now
- Kakani, P., Chandra, A., Mullainathan, S. and Obermeyer, Z. (2020). Allocation of COVID-19 Relief Funding to Disproportionately Black Counties. Journal of the American Medical Association (JAMA), 324 (10), 1000â1003.
Paper not yet in RePEc: Add citation now
Keele, L. J. and Titiunik, R. (2015). Geographic Boundaries as Regression Discontinuities. Political Analysis, 23 (1), 127â155.
- Khullar, D., Bond, A. M. and Schpero, W. L. (2020). COVID-19 and the Financial Health of US Hospitals. Journal of the American Medical Association (JAMA), 323 (21), 2127â2128.
Paper not yet in RePEc: Add citation now
Kleinberg, J., Lakkaraju, H., Leskovec, J., Ludwig, J. and Mullainathan, S. (2017). Human Decisions and Machine Predictions. Quarterly Journal of Economics, 133 (1), 237â293.
- Krantz, S. G. and Parks, H. R. (2008). Geometric Integration Theory. Birkhäuser Basel.
Paper not yet in RePEc: Add citation now
- Li, L., Chu, W., Langford, J. and Schapire, R. E. (2010). A Contextual-Bandit Approach to Personalized News Article Recommendation. Proceedings of the 19th international conference on World Wide Web (WWW), pp. 661â670.
Paper not yet in RePEc: Add citation now
- Li, S. (2011). Concise Formulas for the Area and Volume of a Hyperspherical Cap. Asian Journal of Mathematics and Statistics, 4, 66â70.
Paper not yet in RePEc: Add citation now
Mahoney, N. (2015). Bankruptcy as Implicit Health Insurance. American Economic Review, 105 (2), 710â46.
Mullainathan, S. and Spiess, J. (2017). Machine Learning: An Applied Econometric Approach. Journal of Economic Perspectives, 31 (2), 87â106.
Narita, Y. (2020). A Theory of Quasi-Experimental Evaluation of School Quality. Management Science.
- One version of their approach constructs a linear estimator by choosing the weight (γi)n i=1 greedily to make the inference as precise as possible. Although their estimator is favorable in terms of precision, it is not obvious what estimand the estimator estimates, without assuming a constant treatment effect. The other version of Imbens and Wager (2019)âs approach and some other existing approaches (Zajonc, 2012; Keele and Titiunik, 2015) consider nonparametric estimation of the conditional average treatment effect E[Yi(1)âYi(0)|Xi = x] for a specified boundary point x. The estimand has a clear interpretation, but âwhen curvature is nonnegligible, equation (6) can effectively make use of only data near the specified focal point c, thus resulting in relatively long confidence intervalsâ (Imbens and Wager, 2019, p. 268), where equation (6) defines their estimator.
Paper not yet in RePEc: Add citation now
Papay, J. P., Willett, J. B. and Murnane, R. J. (2011). Extending the RegressionDiscontinuity Approach to Multiple Assignment Variables. Journal of Econometrics, 161 (2), 203â207.
- Precup, D. (2000). Eligibility Traces for Off-Policy Policy Evaluation. Proceedings of the Seventeenth International Conference on Machine Learning, pp. 759â766.
Paper not yet in RePEc: Add citation now
- Proof. We apply results from Crasta and Malusa (2007). Let K = {x â Rp : kxk ⤠1}. K is nonempty, compact, convex subset of Rp with the origin as an interior point. The polar body of K, defined as K0 = {y â Rp : y x ⤠1 for all x â K}, is K itself. The gauge functions ÏK, ÏK0 : Rp â [0, â] of K and K0 are given by ÏK(x) â¡ inf{t ⥠0 : x â tK} = kxk, ÏK0 (x) â¡ inf{t ⥠0 : x â tK0} = kxk. Given ÏK0 , the Minkowski distance from a set S â Rp is defined as δS(x) â¡ inf yâS ÏK0 (x â y), x â Rp . Note that we can write ds S(x) = ( δâS(x) if x â cl(S) âδâS(x) if x â Rp \ cl(S).
Paper not yet in RePEc: Add citation now
- Qiao, W. (2021). Nonparametric Estimation of Surface Integrals on Level Sets. Bernoulli, 27 (1), 155â191.
Paper not yet in RePEc: Add citation now
- Rosenbaum, P. R. and Rubin, D. B. (1983). The Central Role of the Propensity Score in Observational Studies for Causal Effects. Biometrika, 70 (1), 41â55.
Paper not yet in RePEc: Add citation now
- Saito, Y., Aihara, S., Matsutani, M. and Narita, Y. (2021). Open bandit dataset and pipeline: Towards realistic and reproducible off-policy evaluation. Unpublished Manuscript, Tokyo Institute of Technology.
Paper not yet in RePEc: Add citation now
Sekhon, J. S. and Titiunik, R. (2017). On Interpreting the Regression Discontinuity Design as a Local Experiment. In Regression Discontinuity Designs: Theory and Applications, Emerald Publishing Limited, pp. 1â28.
- Stein, E. M. and Shakarchi, R. (2005). Real Analysis: Measure Theory, Integration, and Hilbert Spaces. Princeton Lectures in Analysis, Princeton, NJ: Princeton Univ. Press.
Paper not yet in RePEc: Add citation now
- The data is available from financial year 1996 to 2019. As the coverage is higher for 2018 (compared to 2019), we utilize the data corresponding to the 2018 financial year. Hospitals are uniquely identified in a financial year by their CMS (Center for Medicaid and Medicare Services) 41 We use the RAND cleaned version of this dataset, which can be accessed https://www.hospitaldatasets. org/ 42 We use the methodology detailed in the CARES ACT website to project funding based on 2018 financial year cost reports.
Paper not yet in RePEc: Add citation now
- Voelker, A. R., Gosmann, J. and Stewart, T. C. (2017). Efficiently Sampling Vectors and Coordinates from the n-Sphere and n-Ball. Centre for Theoretical Neuroscience - Technical Report.
Paper not yet in RePEc: Add citation now
- Zajonc, T. (2012). Regression Discontinuity Design with Multiple Forcing Variables. Essays on Causal Inference for Public Policy, pp. 45â81.
Paper not yet in RePEc: Add citation now