David Dranove

Dranove, David, Subramaniam Ramanarayanan and Yasutora Watanabe. 2012. Delivering Bad News: Market Responses to Obstetricians' Negligence. Journal of Law and Economics. 55(1): 1-25.

One of the goals of the legal liability system is to ensure that sellers provide appropriate care. In addition to direct punishment by the legal system, reputation effects may work to deter negligence. The little available evidence suggests that such effects are minimal, however. Focusing on medical malpractice, we examine this effect using a micro-level dataset in an environment in which sellers are of heterogeneous quality and face two types of demand, private consumers who exhibit downward sloping demand (i.e., private health insurance) and government consumers who exhibit perfectly elastic demand at a fixed price (i.e., Medicaid insurance). We find that high quality sellers who are sued may see their caseloads shift from private to government patients. Combining individual patient-level data from Florida for the years 1994-2003 with physician-level litigation data, we find evidence that physicians experience large reputation effects that differ across patient segments in accordance with the theory.

Dranove, David, Cory Capps and Leemore S. Dafny. 2010. A Competitive Process for Procuring Health Services: A Review of Principles with an Application to Cataract Services. SPP Research Paper: The Health Series. The School of Public Policy, University of Calgary 2(5)

Government agencies employ a variety of mechanisms for securing goods and services from the private sector. These include posting prices, reimbursing for costs, and soliciting competitive bids. Procurement of healthcare services offers several unique challenges. The supplier can influence the quantity of services provided. It is often difficult to even specify in advance exactly what services are to be purchased. Lastly, quality is difficult to measure. Healthcare purchasers have deployed a variety of payment mechanisms to cope with these challenges. We apply the theory of procurement to the case of cataract surgery. We recommend implementing a system that combines a gatekeeper with competitive bidding among operating physicians who must perform all necessary services, including treatment for complications, within a global fee. We conclude by discussing the strengths and limitations of this proposal.

Dafny, Leemore S. and David Dranove. 2009. Regulatory Exploitation and Management Changes: Upcoding in the Hospital Industry. Journal of Law and Economics. 52(2): 223-250.

This paper investigates whether management teams that fail to exploit regulatory loopholes are vulnerable to replacement. We use the U.S. hospital industry in 1985-96 as a case study. A 1988 change in Medicare rules widened a preexisting loophole in the Medicare payment system, presenting hospitals with an opportunity to increase operating margins by 5 or more percentage points simply by upcoding patients to more lucrative codes. We find that having room to upcode is a statistically and economically significant predictor of whether a hospital replaces its management with a new team of for-profit managers. We also find evidence that hospitals that replace their management subsequently upcode more than a sample of similar hospitals whose management did not change.

Dranove, David and Andrew Sfekas. 2008. Start Spreading the News: A Structural Estimate of the Effects of New York Hospital Report Cards. Journal of Health Economics.

Research on the effects of publicly reported hospital quality report cards on patient market shares is mixed. Higher ranking hospitals do not consistently experience increases in market share. We argue that this may be because the report cards do not always convey news about quality; in some cases the rankings conform with prior beliefs about quality. We develop a structural model of the news in report cards and estimate the model using data from New York State in 1989-1991. We show hospitals with positive news in the original 1990 report cards experienced a gain in market share, but that a misspecified model might continue to find no report card effect.

Nakamura, Sayaka, Cory Capps and David Dranove. 2007. Patient Admission Patterns and Acquisitions of Feeder Hospitals. Journal of Economics & Management Strategy. 16(4): 995-1030.

In the past fifteen years, there have been numerous instances in which a tertiary care hospital acquires a nearby community hospital. One possible motive is to increase referrals from the target's market area. The acquirer might even try to alter the types of patients it admits from the target's market, concentrating on more profitable referrals. We test these hypotheses by comparing changes in referrals of patients from the target market area to changes in a matched set of control markets, using data on 26 acquisitions in Florida and New York. The results vary substantially across acquisitions, with no significant change in admissions being the most common outcome. Nevertheless, 25% of the acquisitions were followed by a significant increase in CABG and PTCA referrals to the acquirer, and 44% lead to increases in referrals of patients from a broader set of tertiary DRGs. In contrast, only one acquisition reduced CABG and PTCA referrals, while two lowered overall tertiary referrals. We also find weak evidence that some acquirers engage in cherry-picking, increasing admissions of low-severity patients from the target market, post-acquisition. Yet a number of acquirers also increased referrals of the most severely ill patients, possibly due to outlier and stop loss payments, or perhaps a reflection of physicians Epreferences for more complex cases. On balance, our results are consistent with recent studies (Burns and Pauly, 2002; Conrad, 2004) indicating that vertical acquisitions that lead to enhanced performance are more commonly the exception than the rule.

Dranove, David and Kathryn E. Spier. 2003. A Theory of Utilization Review. Contributions to Economic Analysis & Policy. 2(1): 1146.

Through utilization review (UR), managed care organizations (MCOs) monitor and alter physician treatment decisions. We show that the value of UR depends on physician incentives. Not surprisingly, when physicians have incentives to significantly overtreat patients, UR can improve social welfare by eliminating unnecessary utilization. More surprisingly, UR can also improve welfare when physicians have incentives to significantly undertreat patients. In this case, UR filters out the least valuable cases, encouraging physicians to recommend more treatments. We also show that the effectiveness of UR depends on MCO precommitment to a treatment approval threshold. Ex ante optimal precommitment can make it appear that the MCO is inappropriately withholding care ex post.

Dranove, David and William D. White. 1998. Medicaid-Dependent Hospitals and Their Patients: How Have They Fared?. Health Services Research. 33(2): 163-185.

Objective. To examine how private hospitals dependent on Medicaid for a large proportion of their revenues have fared in the face of substantial Medicaid (and more modest Medicare) reimbursement cutbacks and growing managed care. We specifically test three hypotheses regarding Medicaid-dependent hospitals: (1) that they are more likely to "cost-shift" cutbacks to private patients; (2) that they are more likely to cut services for Medicaid (and other) patients; and (3) that they are more likely to close. Data/Study Setting. Private short-term hospitals in California, a state that has experienced a rapid growth in managed care since the early 1980s. Data are drawn from the California Office of Statewide Health Planning and Development (OSHPD) Hospital Disclosure Files for fiscal years 1983 and 1992. Study Design. We compare changes in net prices and the provision of services, proxied by list price-adjusted charges, at hospitals for Medicaid, Medicare, and privately insured patients between fiscal years 1983 and 1992 controlling for hospital and market characteristics, case mix, and the proportion of revenues from Medicaid patients. We also examine the probability that a hospital closed during the study period as a function of hospital and market characteristics and payer mix. Although the growth of managed care is hypothesized to reduce opportunities for "cost shifting," it may also confound our analysis of price changes if Medicaid-dependent hospitals are unattractive to managed care patients and respond by offering lower prices to plans. Principal Findings. We find no evidence that Medicaid-dependent hospitals raised prices to private patients in response to Medicaid (or Medicare) cutbacks; ff anything, they lowered them. However, we find that service levels fell for Medicaid (and Medicare) patients relative to those for privately insured patients and that reductions were greater at Medicaid-dependent hospitals. In addition, our findings suggest that service levels also fell for private patients at Medicaid-dependent hospitals, although reductions were smaller for these patients, suggesting that quality may be a public good at hospitals. Finally, Medicaid-dependent hospitals were more likely to close. Conclusions. It been suggested that private hospitals may respond to public reimbursement cutbacks by simply "shifting" costs to privately insured patients, limiting overall cost savings but insulating public patients and hospitals from the effects of cutbacks. We find no evidence of cost shifting. Rather, our results suggest that patients and hospitals bore the brunt of cutbacks; service levels fell at Medicaid-dependent hospitals and such hospitals were more likely to go out of business. This suggests that the consequences of proposed Medicare and Medicaid cutbacks could be severe for public patients and the hospitals that care for them.

Dranove, David and Mark Satterthwaite. 1992. Monopolistic Competition when Price and Quality are not Perfectly Observable. RAND Journal of Economics. 23(4): 518-534.

Consider the symmetric equilibrium of a monopolistically competitive industry in which manufacturers select price and quality to maximize expected profit and consumers maximize utility by conducting costly search among sellers using an optimal sequential search rule. Consumers search among sellers because (i) each consumer idiosyncratically evaluates each seller's quality and (ii) a retailing sector generates variation in the prices consumers pay. Consumers are handicapped in their search because their observations of firms' price and quality levels are noisy. An improvement in price information is represented by an increase in the precision with which consumers observe sellers' prices. Similarly, an improvement in quality information is represented by an increase in precision with which consumers observe sellers' quality levels. An improvement of either type of information may increase or decrease welfare. The perverse case in which improved price information decreases welfare occurs when price competition among firms becomes so intense relative to quality competition that firms select severely suboptimal levels of quality.

Dranove, David. 1990. Information Spillovers, Incumbency, and Conservatism. International Journal of Industrial Organization. 8(4): 575-585.

This paper studies the relationship between the existing ventures of a firm and its incentives to undertake new ventures. We argue that whenever a firm undertakes a new venture, it does so with the risk that information associated with that venture will reflect on all of the firm's products. If the costs of bad news exceed the benefits of good news, the firm will be less likely to undertake the venture. This is the case in our model, in which an incumbent risks losing monopoly status in an established market should its new venture fail. Thus, incumbency can breed conservatism.

Dranove, David. 2012. Practical Regression: Time Series and Autocorrelation. Case 7-112-012 (KEL646).

This is the twelfth in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This technical note discusses time-series data. The note explains the concept of a time trend and how to capture the trend using regression. Most of the note is devoted to the problem of autocorrelation. The note concludes by discussing the use of leads and lags as predictor variables.

Dranove, David. 2012. Practical Regression: Introduction to Endogeneity: Omitted Variable Bias. Case 7-112-004 (KEL638).

This is the fourth in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This technical note introduces the concept of endogeneity bias with specific coverage of omitted variable bias. Students who read this note will understand why omitting key predictors can sometimes bias the coefficients of included variables. The note illustrates omitted variable bias by means of an extended example and offers practical advice for model building that balances the desire for parsimony developed in a previous note with the need to limit omitted variable bias.

Dranove, David. 2012. Practical Regression: Convincing Empirical Research in Ten Steps. Case 7-112-001 (KEL635).

This is the first in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.

This technical note introduces students to the essential elements of convincing empirical research using regression. Students who read this note will be prepared to perform an unstructured research project. The note presents ten essential steps in research, starting with model development and ending with presentation of results. Coverage is given to important subjects such as identification and model robustness.

Dranove, David. 2012. Practical Regression: Causality and Instrumental Variables. Case 7-112-010 (KEL644).

This is the tenth in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This note uses the theory of "supplier-induced demand" from health economics to illustrate key issues including reverse causality, the role of instrumental variables in establishing causality, and the characteristics of good instruments.

Dranove, David. 2012. Practical Regression: From "Stylized Facts" to Benchmarking . Case 7-112-011 (KEL645).

This is the eleventh in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
Using an extended example on hospital lengths of stay, the note explains how to "deconstruct" a regression in order to parse out how each variable contributes to the overall result. Regression is viewed as an exercise in "benchmarking"—explaining why some observations in the data "outperform" or "underperform" others. The residual is viewed as a potential measure of managerial effectiveness, albeit one that must be treated with caution. The note provides step-by-step instructions for using regression for benchmarking.

Dranove, David. 2012. Practical Regression: Noise, Heteroskedasticity, and Grouped Data. Case 7-112-006 (KEL640).

This is the sixth in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This note begins by describing the problems that arise when variables are measured with noise. The note progresses to explain how to test for and correct heteroskedasticity. It also explains why it is necessary to adjust standard errors when working with grouped data.

Dranove, David. 2012. Practical Regression: Regression Basics. Case 7-112-002 (KEL636).

This is the second in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This technical note reviews the basic elements of regression analysis. Students who read this note will be able to explain the fundamental principals of regression, including (1) regression as an alegbraic equation; (2) dummy variables and nonlinear terms; (3) R-squared and goodness of fit; and (4) reporting the significance and economic importance of regression coefficients. Having completed this note, students will be prepared to study the special topics in regression that are covered in other notes in this series.

Dranove, David. 2012. Practical Regression: Fixed Effects Models. Case 7-112-005 (KEL639).

This is the fifth in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This technical note discusses fixed effects models. Though a unified example, the note shows how omitted variable bias can plague estimates in cross-section regressions and how focusing attention on intragroup ("within") variation over time can allow for identification of regression coefficients that are free of potential bias. The note demontrates the mathematical principles behind fixed effects modeling and also explains why, in some cases, it may be preferable not to include fixed effects.

Dranove, David. 2012. Practical Regression: Maximum Likelihood Estimation. Case 7-112-008 (KEL642).

This is the eighth in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.This technical note discusses maximum likelihood estimation (MLE). The note explains the concept of goodness of fit and why MLE is a powerful alternative to R-squared. The note follows a simple example that develops the intuition of MLE as well as the computation of the likelihood score and the algorithm used to estimate coefficients in MLE models.

Dranove, David. 2012. Practical Regression: Log vs. Linear Specification. Case 7-112-007 (KEL641).

This is the seventh in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This note explains how to choose between log and linear specification. The note emphasizes the economic interpretation of a log model and how to interpret coefficients in a log regression. The note concludes by explaining how to choose between log and linear specifications on econometric grounds, including an explanation of the Box-Cox test.

Dranove, David. 2012. Practical Regression: Discrete Dependent Variables. Case 7-112-009 (KEL643).

This is the ninth in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This note returns to the topic of endogeneity, explaining how a predictor variable can be endogenous (and therefore its coefficient can be biased) if causality is in doubt. Through an extended example of the learning curve in medicine, the note introduces the concept of instrumental variables (IV), provides an intuitive explanation for why instruments solve the causality problem, and explains how to estimate IV and two-stage least squares regressions. The note describes statistical tests for the validity of instruments.

Dranove, David. 2012. Practical Regression: Building Your Model: What Variables to Include. Case 7-112-003 (KEL637).

This is the third in a series of lecture notes which, if tied together into a textbook, might be entitled “Practical Regression.” The purpose of the notes is to supplement the theoretical content of most statistics texts with practical advice based on nearly three decades of experience of the author, combined with over one hundred years of experience of colleagues who have offered guidance. As the title “Practical Regression” suggests, these notes are a guide to performing regression in practice.
This technical note explains how to choose predictor variables to include in regression. The note begins by explaining the many virtues of parsimony. Sometimes analysts include predictors simply because they are in the available data. Including such "junk" predictors increases the chances of obtaining confusing or misleading results. The note also explores multicollinearity, a favorite topic in some statistics classes that is rarely a problem in real world empirical work. The note concludes by explaining how to work with groups of related variables and describes how to implement the partial F test for joint significance.