HEC Paris

About: HEC Paris is a education organization based out in Jouy-en-Josas, France. It is known for research contribution in the topics: Market liquidity & Entrepreneurship. The organization has 584 authors who have published 2756 publications receiving 104467 citations. The organization is also known as: Ecole des Hautes Etudes Commerciales & HEC School of Management Paris.

Accurate Methods for Approximate Bayesian Computation Filtering

Abstract: The Approximate Bayesian Computation (ABC) filter extends the particle filtering methodology to general state-space models in which the density of the observation conditional on the state is intractable. We provide an exact upper bound for the mean squared error of the ABC filter, and derive sufficient conditions on the bandwidth and kernel under which the ABC filter converges to the target distribution as the number of particles goes to infinity. The optimal convergence rate decreases with the dimension of the observation space but is invariant to the complexity of the state space. We show that the adaptive bandwidth commonly used in the ABC literature can lead to an inconsistent filter. We develop a plug-in bandwidth guaranteeing convergence at the optimal rate, and demonstrate the powerful estimation, model selection, and forecasting performance of the resulting filter in a variety of examples.

Linking Process Quality and Resource Usage: An Empirical Analysis

Abstract: Motivated by an increasing adoption of evidence-based medical guidelines in the delivery of medical care, we examine whether increased adherence to such guidelines (typically referred to as higher process quality) is associated with reduced resource usage in the course of patient treatment. In this study, we develop a sample of US hospitals and use cardiac care as our context to empirically examine our questions. To measure a patient's resource usage, we use the total length of stay, which includes any additional inpatient stay necessitated by unplanned readmissions within thirty days after initial hospitalization. We find evidence that higher process quality, and more specifically its clinical (as opposed to its administrative) dimensions, are associated with a reduction in resource usage. Moreover, the standardization of care that is achieved via the implementation of medical guidelines, makes this effect more pronounced in less focused environments: higher process quality is more beneficial when the cardiac department's patient population is distributed across a wider range of medical conditions. We explore the implications of these findings for process-oriented pay-for-performance programs, which tie the reimbursement of hospitals to their adherence to evidence-based medical guidelines.

A Bounded Rationality Model of Information Search and Choice in Preference Measurement

Abstract: It is becoming increasingly easier for researchers and practitioners to collect eye-tracking data during online preference measurement tasks. The authors develop a dynamic discrete choice model of information search and choice under bounded rationality, which they calibrate using a combination of eye-tracking and choice data. Their model extends Gabaix et al.'s (2006) directed cognition model by capturing fatigue, proximity effects, and imperfect memory encoding and by estimating individual-level parameters and partworths within a likelihood-based hierarchical Bayesian framework. The authors show that modeling eye movements as the outcome of forward-looking utility maximization improves out-of-sample predictions, enables researchers and practitioners to use shorter questionnaires, and allows better discrimination between attributes.

Tradeoffs in Staying Close: Corporate Decision-Making and Geographic Dispersion

Abstract: We document the role of geographic dispersion on corporate decision-making. Our findings include: (i) geographically dispersed firms are less employee friendly; (ii) dismissals of divisional employees are less common in divisions located closer to corporate headquarters; and (iii) firms appear to adopt a "pecking-order" and divest out-of-state entities before in-state. To explain these findings, we consider both information and social factors. We find that firms are more likely to protect proximate employees in soft information industries (i.e. when information is difficult to transfer over long distances). However, employee protection only holds when headquarters is located in a less-populated county suggesting a role for social factors. Additionally, stock markets respond favorably to divestitures of in-state divisions. Our findings suggest that social factors work alongside informational considerations in making geographic dispersion an important factor in corporate decision-making.