Results 1 -
9 of
9
Measuring the Sensitivity of Parameter Estimates to Sample Statistics
"... We propose a measure of the dependence of a parameter estimate on specific features of the data. The measure can be computed at negligible cost even for computationally difficult models. It can be interpreted as a measure of sensitivity to model misspecification. The measure delivers satisfactory in ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
We propose a measure of the dependence of a parameter estimate on specific features of the data. The measure can be computed at negligible cost even for computationally difficult models. It can be interpreted as a measure of sensitivity to model misspecification. The measure delivers satisfactory intuitions for pen-and-paper examples. We apply the measure to recent empirical papers in industrial organization. 1
Regulation of insurance with adverse selection and switching costs: Evidence from Medicare Part D
, 2013
"... I take advantage of the evolution of the regulatory and pricing environment in the first years of a large federal prescription drug insurance program for seniors- Medicare Part D- to em-pirically explore interactions among adverse selection, switching costs, and regulation. Using detailed administra ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
(Show Context)
I take advantage of the evolution of the regulatory and pricing environment in the first years of a large federal prescription drug insurance program for seniors- Medicare Part D- to em-pirically explore interactions among adverse selection, switching costs, and regulation. Using detailed administrative data, I document evidence of both adverse selection of beneficiaries across contracts and switching costs for beneficiaries in changing contracts within Medicare Part D. Motivated by this descriptive evidence, I formulate a model of contract choice that al-lows for both switching costs and private information about expected risk. Using this model, I show that switching costs are large and have quantitatively important implications for the sorting of individuals among contracts. How switching costs affect selection over time de-pends on the direction of changes in the contract space relative to the initial conditions. I find that in the present environment, on net, switching costs help sustain an adversely-selected equilibrium with large differences in risks between more and less generous contracts. I then simulate how switching costs could affect regulatory interventions that change the generosity of contracts. For example, I consider the tightening of the minimum standard requirement
Beyond statistics: the economic content of risk scores
, 2015
"... Abstract. In recent years, the increased use of big dataand statistical techniques to score potential transactions has transformed the operation of insurance and credit markets. In this paper, we observe that these widely-used scores are statistical objects that constitute a one-dimensional summary ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract. In recent years, the increased use of big dataand statistical techniques to score potential transactions has transformed the operation of insurance and credit markets. In this paper, we observe that these widely-used scores are statistical objects that constitute a one-dimensional summary of a potentially much richer heterogeneity, some of which may be endogenous to the speci
c context in which they get applied. We demonstrate this point empirically using rich data from the Medicare Part D pre-scription drug insurance program. We show that the risk scores,which are designed to predict an individuals drug spending and are used by Medicare to customize reim-bursement rates to private insurers, do not distinguish between two di¤erent sources of spending: underlying health, and responsiveness of drug spending to the insurance contract. Naturally, however, these two determinants of spending have very di¤erent implications when trying to predict counterfactual spending under alternative contracts. As a result, we illustrate that once we enrich the theoretical framework to allow indi-viduals to have heterogeneous behavioral responses to the contract, strategic incentives for cream skimming still exist, even in the presence of perfect risk scoring under a given contract.
Who Bene ts when the Government Pays More? Pass-Through in the Medicare Advantage Program
, 2014
"... Governments contract with private
rms to provide a wide range of services. While a large body of previous work has estimated the e¤ects of that contracting, surprisingly little has investigated how those e¤ects vary with the generosity of the contract. In this paper we examine this issue in the Med ..."
Abstract
- Add to MetaCart
(Show Context)
Governments contract with private
rms to provide a wide range of services. While a large body of previous work has estimated the e¤ects of that contracting, surprisingly little has investigated how those e¤ects vary with the generosity of the contract. In this paper we examine this issue in the Medicare Advantage (MA) program, through which the federal government contracts with private insurers to coordinate and
nance health care for 16 million Medicare recipients. To do this, we exploit a substantial policy-induced increase in MA reimbursement in metropolitan areas with a population of 250 thousand or more relative to MSAs below this threshold. Our results demonstrate that the additional reimbursement leads more private
rms to enter this market and to an increase in the share of Medicare recipients enrolled in MA plans. Our ndings also reveal that about one-sixth of the additional reimbursement is passed through to consumers in the form of better coverage. A somewhat larger share accrues to private insurers in the form of higher pro
ts and we
nd suggestive evidence of a large impact on advertising expenditures. Our results have implications for a key feature of the A¤ordable Care Act that
McGuire, Erik Schokkaert, Frank Sloan, and participants at the American Society of Health
, 2015
"... Economists and the Risk Adjustment Network for useful comments and insights, although the authors bear full responsibility for any errors or omissions. This research was partially supported by Verisk Health through a grant to Boston University. ..."
Abstract
- Add to MetaCart
Economists and the Risk Adjustment Network for useful comments and insights, although the authors bear full responsibility for any errors or omissions. This research was partially supported by Verisk Health through a grant to Boston University.
credit, including © notice, is given to the source. Prescription Drug Use under Medicare Part D: A Linear Model of Nonlinear Budget Sets
, 2015
"... of Aging. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research. NBER working papers are circulated for discussion and comment purposes. They have not been peer-reviewed or been subject to the review by the NBER Board ..."
Abstract
- Add to MetaCart
of Aging. The views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research. NBER working papers are circulated for discussion and comment purposes. They have not been peer-reviewed or been subject to the review by the NBER Board of Directors that accompanies official NBER publications.
Conversations with Kevin M. Murphy inspired and greatly improved this work. We are grateful also
, 2014
"... for advice and suggestions, and to our dedicated research assistants for important contributions to this project. We thank the following authors for their assistance in working with their code and data: Stefano ..."
Abstract
- Add to MetaCart
for advice and suggestions, and to our dedicated research assistants for important contributions to this project. We thank the following authors for their assistance in working with their code and data: Stefano
Disentangling Moral Hazard and Adverse Selection in Private Health Insurance
, 2016
"... Moral hazard and adverse selection create inefficiencies in private health insurance markets and understanding the relative importance of each factor is critical for policy. We use claims data from a large rm which changed health insurance plan options to isolate moral hazard from plan selection. Us ..."
Abstract
- Add to MetaCart
Moral hazard and adverse selection create inefficiencies in private health insurance markets and understanding the relative importance of each factor is critical for policy. We use claims data from a large rm which changed health insurance plan options to isolate moral hazard from plan selection. Using an instrumental variables quantile re-gression approach, we estimate the differential causal impact of each health insurance plan on the entire distribution of medical expenditures. We account for systematic sample attrition during the sample period by conditioning on a nonseparable sample selection adjustment. Our estimates imply that 54 % of the additional medical spending observed in the most generous plan in our data relative to the least generous is due to moral hazard with the other 46 % due to adverse selection. We also statistically reject that individuals are responding solely to a specic parameterized price in their health insurance plans.
Part D.
, 2015
"... This paper is the first chapter of my MIT dissertation. I am indebted to Amy Finkelstein, Nancy Rose, Jonathan Gruber, and Stephen Ryan for their guidance and support throughout this project. I thank ..."
Abstract
- Add to MetaCart
(Show Context)
This paper is the first chapter of my MIT dissertation. I am indebted to Amy Finkelstein, Nancy Rose, Jonathan Gruber, and Stephen Ryan for their guidance and support throughout this project. I thank
