Search

Firms are increasingly selling through both offline and online channels, allowing customers to experience the touch and feel of product attributes before purchasing those products. Consequently, the selection of products offered offline affects the demand in both channels. We address how firms should select an optimal offline assortment to maximize profits across both channels; we call this the showcase decision problem. We incorporate the impact of physical evaluation on preferences into the consumer demand model. Under this model, we show that the decision problem is NP-hard. Analytically, we derive optimal results for special cases and near-optimal approximations for general cases. Empirically, we use conjoint analysis to identify changes in consumer preferences resulting from physically evaluating products. For this application, we demonstrate gains in expected revenue of up to 40% due to accounting for the impact of offline assortment on the online sales. History: Accepted by Vishal Gaur, operations management. Funding: S. Jagabathula's research was supported in part by the National Science Foundation [Grant CMMI1454310]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2016.2708. Keywords: assortment optimization * omnichannel * choice modeling * conjoint analysis, 1. Introduction A growing number of firms are selling to their customers through both online and offline (or brick-and-mortar) channels. Selling through multiple channels allows the firm to reach customers [...]

Procedures in assessing the impact of serial dependency on performance analysis are usually built on parametrically specified models. In this paper, we propose a robust, nonparametric approach to carry out this assessment, by computing the worst-case deviation of the performance measure due to arbitrary dependence. The approach is based on optimizations, posited on the model space, that have constraints specifying the level of dependency measured by a nonparametric distance to some nominal independent and identically distributed input model. We study approximation methods for these optimizations via simulation and analysis of variance. Numerical experiments demonstrate how the proposed approach can discover the hidden impacts of dependency beyond those revealed by conventional parametric modeling and correlation studies. History: Accepted by Assaf Zeevi, stochastic models and simulation. Funding: The author gratefully acknowledges support from the National Science Foundation [Grants CMMI-1400391 /1542020 and CMMI-1436247/1523453]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2016.2667. Keywords: sensitivity analysis * serial dependency * nonparametric * model uncertainty * robust optimization, 1. Introduction While stylized models in operations and service systems often assume independently generated inputs, studies have pointed to the ubiquity of serial dependency in many real-life applications. Examples include [...]

We consider the problem of choosing, from a set of N potential stock-keeping units (SKUs) in a retail category, K SKUs to be carried at each store to maximize revenue or profit. Assortments can vary by store, subject to a maximum number of different assortments. We view a SKU as a set of attribute levels and also model possible substitutions when a customer's first choice is not in the assortment. We apply maximum likelihood estimation to sales history of the SKUs currently carried by the retailer to estimate the demand for attribute levels and substitution probabilities, and from this, the demand for any potential SKU, including those not currently carried by the retailer. We specify several alternative heuristics for choosing SKUs to be carried in an assortment. We apply this approach to optimize assortments for three real examples: snack cakes, tires, and automotive appearance chemicals. A portion of our recommendations for tires and appearance chemicals were implemented and produced sales increases of 5.8% and 3.6%, respectively, which are significant improvements relative to typical retailer annual comparable store revenue increases. We also forecast sales shares of 1, 11, and 25 new SKUs for the snack cake, tire, and automotive appearance chemical applications, respectively, with mean absolute percentage errors (MAPEs) of 16.2%, 19.1%, and 28.7%, which compares favorably to the 30.7% MAPE for chain sales of two new SKUs reported by Fader and Hardie (1996). Keywords: assortment planning; retailer operations; statistics; estimation History: Received June 16, 2009; accepted November 13, 2013, by Yossi Aviv, operations management. Published online in Articles in Advance July 10, 2014., 1. Introduction A retailer's assortment is the set of products they carry in each store at each point in time. Retailers periodically revise the assortment for each category, deleting some [...]

The main responsibility of resource and delivery managers at Hewlett-Packard (HP) Enterprise Services (HPES) involves matching resources (skilled professionals) with jobs that project opportunities require. The previous Solution Opportunity Approval [...]

The Port of Davisville, located at Quonset Point, Rhode Island, is a former US Navy facility that was turned over to Rhode Island for commercial development when the naval base [...]

IBM uses operations research techniques to plan its enterprise semiconductor supply chain. The scale and complexity of this planning problem make developing robust supply chain optimization tools a challenge. Pure [...]

Energy Education, Inc. (EEI), a US management consulting firm, specializes in implementing energy conservation programs for schools, universities, and large churches. Similar to many consulting firms, travel expenses are among [...]

Cross-town moves, a special type of drayage, occur when intermodal containers require a transfer from one rail ramp to another for continuance of a shipment. The cross-town problem consists of [...]

Under changing market conditions for the hospitality industry, the Carlson Rezidor Hotel Group (CRHG) collaborated with JDA Software Group to use operations research to drive higher revenue for its hoteliers [...]

Planning for a catastrophe involving a disease outbreak with the potential for mass casualties is a significant challenge for emergency managers. Public health experts at the US Centers for Disease [...]

We introduce the pathwise optimization (PO) method, a new convex optimization procedure to produce upper and lower bounds on the optimal value (the 'price') of a high-dimensional optimal stopping problem. The PO method builds on a dual characterization of optimal stopping problems as optimization problems over the space of martingales, which we dub the martingale duality approach. We demonstrate via numerical experiments that the PO method produces upper bounds of a quality comparable with state-of-the-art approaches, but in a fraction of the time required for those approaches. As a by-product, it yields lower bounds (and suboptimal exercise policies) that are substantially superior to those produced by state-of-the-art methods. The PO method thus constitutes a practical and desirable approach to high-dimensional pricing problems. Furthermore, we develop an approximation theory relevant to martingale duality approaches in general and the PO method in particular. Our analysis provides a guarantee on the quality of upper bounds resulting from these approaches and identifies three key determinants of their performance: the quality of an input value function approximation, the square root of the effective time horizon of the problem, and a certain spectral measure of 'predictability' of the underlying Markov chain. As a corollary to this analysis we develop approximation guarantees specific to the PO method. Finally, we view the PO method and several approximate dynamic programming methods for high-dimensional pricing problems through a common lens and in doing so show that the PO method dominates those alternatives. Key words: dynamic programming; optimal control; optimal stopping; American options; Bermudian options History: Received October 5, 2010; accepted December 18, 2011, by Wei Xiong, stochastic models and simulation. Published online in Articles in Advance June 15, 2012., 1. Introduction Consider the following optimal control problem: A Markov process evolves in discrete time over the state space X. Denote this process by {[x.sub.t], t [greater than or equal [...]

This paper deals with a basic issue: How does one approach the problem of designing the 'right' objective for a given resource allocation problem? The notion of what is right can be fairly nebulous; we consider two issues that we see as key: efficiency and fairness. We approach the problem of designing objectives that account for the natural tension between efficiency and fairness in the context of a framework that captures a number of resource allocation problems of interest to managers. More precisely, we consider a rich family of objectives that have been well studied in the literature for their fairness properties. We deal with the problem of selecting the appropriate objective from this family. We characterize the trade-off achieved between efficiency and fairness as one selects different objectives and develop several concrete managerial prescriptions for the selection problem based on this trade-off. Finally, we demonstrate the value of our framework in a case study that considers air traffic management. Key words: programming; nonlinear; theory; decision analysis; multiple criteria; games-group decisions; bargaining; fairness History: Received December 1, 2010; accepted December 21, 2011, by Yossi Aviv, operations management. Published online in Articles in Advance September 11, 2012., 1. Introduction Operations managers are frequently concerned with problems of resource allocation. They must build quantitative decision models for such problems, calibrate these models, and then use a suitable decision [...]

We compare how experienced procurement managers and students solve the newsvendor problem. We find that managers broadly exhibit the same kind of pull-to-center bias as students do. Also, managers use information and task training no better than students. The performance of managers is positively affected by the level of their education and their level in the organizational hierarchy. We discuss implications for theory and for how ordering might be improved in practice. Key words: newsvendor game; laboratory experiment; manager behavior; information usage History: Received May 10, 2011; accepted February 25, 2012, by Teck Ho, decision analysis. Published online in Articles in Advance July 18, 2012., 1. Introduction The newsvendor problem is a foundational model for the study of inventory control and supply chain management. In the problem's most basic form, the newsvendor faces stochastic demand [...]

Recent discoveries in behavioral economics have led to important new insights concerning what can happen in markets. Such gains in knowledge have come primarily via laboratory experiments--a missing piece of the puzzle in many cases is parallel evidence drawn from naturally occurring field counterparts. We provide a small movement in this direction by taking advantage of a unique opportunity to work with a Chinese high-tech manufacturing facility. Our study revolves around using insights gained from one of the most influential lines of behavioral research--framing manipulations--in an attempt to increase worker productivity in the facility. Using a natural field experiment, we report several insights. For example, conditional incentives framed as both 'losses' and 'gains' increase productivity for both individuals and teams. In addition, teams more acutely respond to bonuses posed as losses than as comparable bonuses posed as gains. The magnitude of this framing effect is roughly 1%: that is, total team productivity is enhanced by 1% purely due to the framing manipulation. Importantly, we find that neither the framing nor the incentive effect lose their significance over time; rather, the effects are observed over the entire sample period. Moreover, we learn that repeated interaction with workers and conditionality of the bonus contract are substitutes for sustenance of incentive effects in the long run. Key words: framing effect; natural field experiment; worker productivity; loss aversion History: Received July 6, 2011; accepted February 3, 2012, by Gerard P. Cachon, decision analysis. Published online in Articles in Advance July 18, 2012., 1. Introduction One of the pillars within an entrenched branch of behavioral research is the power of framing: The manner in which a choice set is presented has been found [...]

Probability and time are integral dimensions of virtually any decision. To treat them together, we consider the prospect of receiving outcome x with a probability p at time t. We define risk and time distance, and show that if these two distances are traded off linearly, then preferences are characterized by three functions: a value function, a probability discount rate function, and a psychological distance function. The concavity of the psychological distance function explains the common ratio and common difference effects. A decreasing probability discount rate accounts for the magnitude effect. The discount rate and the risk premium depend on the shape of these three functions. Key words: risk preferences; time preferences; probability discount rate; subendurance; magnitude effect; psychological distance History: Received July 14, 2009; accepted July 19, 2011, by Peter Wakker, decision analysis. Published online in Article in Advance December 2, 2011., 1. Introduction Time and probability are fundamental attributes of virtually any decision. Decisions involving future risky consequences can be found in domains such as investment, saving, consumption, environmental preservation, and [...]

In this paper we distinguish between two types of white lies: those that help others at the expense of the person telling the lie, which we term altruistic white lies, and those that help both others and the liar, which we term Pareto white lies. We find that a large fraction of participants are reluctant to tell even a Pareto white lie, demonstrating a pure lie aversion independent of any social preferences for outcomes. In contrast, a non-negligible fraction of participants are willing to tell an altruistic white lie that hurts them a bit but significantly helps others. Comparing white lies to those where lying increases the liar's payoff at the expense of another reveals important insights into the interaction of incentives, lying aversion, and preferences for payoff distributions. Finally, in line with previous findings, women are less likely to lie when it is costly to the other side. Interestingly though, we find that women are more likely to tell an altruistic lie. Key words: deception; lies; cheap talk; experiments History: Received June 14, 2010; accepted July 1, 2011, by Teck Ho, decision analysis. Published online in Articles in Advance November 4, 2011., 1. Introduction When people communicate, they sometimes lie. Because communication is indispensable in almost any economic and social interaction, understanding when and why people choose to lie is important. A [...]

We develop a model of portfolio choice to nest the views of Keynes, who advocates concentration in a few familiar assets, and Markowitz, who advocates diversification. We use the concepts of ambiguity and ambiguity aversion to formalize the idea of an investor's 'familiarity' toward assets. The model shows that for any given level of expected returns, the optimal portfolio depends on two quantities: relative ambiguity across assets and the standard deviation of the expected return estimate for each asset. If both quantities are low, then the optimal portfolio consists of a mix of familiar and unfamiliar assets; moreover/ an increase in correlation between assets causes an investor to increase concentration in familiar assets (flight to familiarity). Alternatively, if both quantities are high, then the optimal portfolio contains only the familiar asset(s), as Keynes would have advocated. In the extreme case in which both quantities are very high, no risky asset is held (nonparticipation). Key words: investment; portfolio choice; ambiguity; robust control; underdiversification History: Received July 16, 2010; accepted January 17, 2011, by Brad Barber, Teck Ho, and Terrance Odean, special issue editors. Published online in Articles in Advance June 3, 2011., 1. Introduction John Maynard Keynes and Harry Markowitz personify two contrasting schools of thought regarding the process of portfolio selection. On the one hand, Keynes (1983, p. 57) advocates allocating [...]

In many circumstances, evaluations are based on empirical data. However, some observations may be imprecise, meaning that it is not entirely clear what occurred in them. We address the question of how beliefs are formed in these situations. The individual in our model is essentially a 'frequentist' He first makes a subjective judgment about the occurrence of the event for each imprecise observation. This may be any number between zero and one. He then evaluates the event by its 'subjective' frequency of occurrence. Our model connects the method of processing imprecise observations with the individual's attitude toward ambiguity. An individual who in imprecise observations puts low (high) weight on the possibility that an event occurred is ambiguity averse (loving). An experiment supports the main assertions of the model: with precise data, subjects behave as if there were no ambiguity, whereas with imprecise data subjects turn out to be ambiguity averse. Key words: decision analysis; theory; inference; uncertainty History: Received July 7, 2010; accepted August 31, 2011, by Brad Barber, Teck Ho, and Torrance Odean, special issue editors., 1. Introduction 1.1. Motivation Let us suppose you have to undergo some medical treatment. In the first scenario you have the precise information that the treatment was successful in 25 [...]

Science and technology advances drive firms to continually enhance their product's performance and launch sequentially improving offerings. Firms face challenges in marketing such improving products to well-informed, forward-looking consumers who anticipate product improvements and seek to delay their purchase timing. Product design, specifically a modular upgradable architecture in which improving and stable subsystems of a product are separated and selectively upgraded, can be a valuable approach for marketers to alleviate consumer concerns about product obsolescence. However, such an architecture based approach can present new challenges as well, and dealing with them requires carefully coordinated cross functional decision making by the firm. In this paper, we identify and formalize the notion of design inconsistency, which refers to the monopolist firm's inability to commit to future product design architectures. We find that firms experience design inconsistency even when they are able to commit to future prices, and design inconsistency lowers firm profits as well as consumer surplus. We then derive a joint product architecture and pricing approach to solve this problem; this enables an innovating firm to optimally and in a time consistent manner launch modular upgradable products. The modeling and analysis in the paper lends insight into types of markets and products for which modular upgradability is most appropriate and offers guidelines on making pricing and product design decisions jointly for managing sequential innovation Key words: product design and pricing; modular upgradability, sequential innovation History: Received March 22, 2009; accepted April 15, 2011, by Preyas Desai, marketing. Published online in Articles in Advance August 12, 2011., 1. Introduction Innovating firms in several industries offer temporally improving products to attain higher margins and renewed sales for their durable goods. However, in the face of technology-driven product obsolescence, [...]

Aubiquitous feature of even the fastest self-service technology transactions is the wait. Conventional wisdom and operations theory suggest that the longer people wait, the less satisfied they become; we demonstrate that because of what we term the labor illusion, when websites engage in operational transparency by signaling that they are exerting effort, people can actually prefer websites with longer waits to those that return instantaneous results--even when those results are identical. In five experiments that simulate service experiences in the domains of online travel and online dating, we demonstrate the impact of the labor illusion on service value perceptions, demonstrate that perceptions of service provider effort induce feelings of reciprocity that together mediate the link between operational transparency and increased valuation, and explore boundary conditions and alternative explanations. Key words: marketing; channels of distribution; queues; industries; business services; inventory-production; operating characteristics; service operations; service design History: Received February 26, 2010; accepted March 22, 2011, by Pradeep Chintagunta and Preyas Desai, special issue editors. Published online in Articles in Advance July 15, 2011., 1. Introduction Rare is the modern consumer who has not found herself staring at a computer screen as a progress bar advances fitfully toward loading some application or completing some [...]

Label Confusion: The Groucho Effect of Uncertain Standards (p. 1512) Rick Harbaugh, John W. Maxwell, Beatrice Roussillon What does 'organic' mean, exactly? Producers like to use labels to certify that [...]

Numerous theoretical predictions such as precautionary saving or preventive behavior have been derived for prudent decision makers. Further, prudence can be characterized as downside risk aversion and plays a key role in preference for skewness. We use a simple experimental method to test for prudence and skewness preference in the laboratory and compare the two. To this end, we introduce a novel graphical representation of compound lotteries that is easily accessible to subjects and test it for robustness, using a factorial design. Prudence is observed on the aggregate and individual level. We find that prudence does not boil down to skewness seeking. We further provide some theoretical explanations for this result. Key words: decision making under risk; precautionary savings; prudence; downside risk; skewness seeking; laboratory experiment History: Received December 3, 2009; accepted February 28, 2011, by Peter Wakker, decision analysis., 1. Introduction It is well known that risk aversion only partially captures an individual's risk preferences. An example is the following lottery pair defined by Mao (1970). Lottery [M.sub.A] pays [...]

In this paper, we focus on modeling and predicting the loss distribution for credit risky assets such as bonds and loans. We model the probability of default and the recovery rate given default based on shared covariates. We develop a new class of default models that explicitly accounts for sector specific and regime dependent unobservable heterogeneity in firm characteristics. Based on the analysis of a large default and recovery data set over the horizon 1980-2008, we document that the specification of the default model has a major impact on the predicted loss distribution, whereas the specification of the recovery model is less important. In particular, we find evidence that industry factors and regime dynamics affect the performance of default models, implying that the appropriate choice of default models for loss prediction will depend on the credit cycle and on portfolio characteristics. Finally, we show that default probabilities and recovery rates predicted out of sample are negatively correlated and that the magnitude of the correlation varies with seniority class, industry, and credit cycle. Key words: loss distribution; default prediction; recovery rates; Basel II History: Received May 11, 2009; accepted February 10, 2011, by Wei Xiong, finance. Published online in Articles in Advance May 17, 2011., 1. Introduction The predicted loss distribution is a basic input for calculating the loan loss reserves and the economic capital and for computing portfolio risk metrics such as value-at-risk and [...]

This paper highlights the rationale for exclusive territories in a model of repeated interaction between competing supply chains. We show that with observable contracts exclusive territories have two countervailing effects on manufacturers' incentives to sustain tacit collusion. First, granting local monopolies to retailers softens competition in a one-shot game. Hence, punishment profits are larger, thereby rendering deviation more profitable. Second, exclusive territories stifle deviation profits because retailers of competing brands adjust their prices to the wholesale contract offered by a deviant manufacturer, whereas intrabrand competition prevents such 'instantaneous reaction.' We show that the latter effect tends to dominate, thereby making exclusive territories a more suitable organizational mode to cooperate. These insights are robust to endogenous communication between manufacturers. We also consider retailers' service investments. Here, a novel effect emerges that softens the procollusive value of exclusive territories: Retailers of a deviant manufacturer increase investments, which renders deviation more profitable. Key words: exclusive territories; supply chains; tacit collusion; information sharing; vertical restraints History: Received April 16, 2010; accepted March 4, 2011, by Preyas Desai, marketing. Published online in Articles in Advance June 3, 2011., 1. Introduction Distribution networks organized through exclusive territories are widespread in many markets. In industries such as lodging, computer services, or maintenance services, upstream firms use franchise contracts that predominantly [...]

Scholars, practitioners, and students in operations research and management science (OR/MS) often hesitate to use traditional approaches to evaluate journal quality because of the inconsistency of these approaches to perceptions [...]

One of the most important operational challenges faced by emergency departments (EDs) in the United States is patient overcrowding. In periods of overcrowding, an ED can request the emergency medical services (EMS) agency to divert incoming ambulances to neighboring hospitals, a phenomenon known as 'ambulance diversion.' The EMS agency may accept this request provided that at least one of the neighboring EDs is not on diversion. From an operations perspective, properly executed ambulance diversion should result in resource pooling and reduce the overcrowding and delays in a network of EDs. Recent evidence indicates, however, that this potential benefit is not always realized. In this paper, we provide one potential explanation for this discrepancy and suggest potential remedies. Using a queueing game between two EDs that aim to minimize their own waiting time, we find that decentralized decisions regarding diversion explain the lack of pooling benefits. Specifically, we find the existence of a defensive equilibrium, wherein each ED does not accept diverted ambulances from the other ED. This defensiveness results in a depooling of the network and, subsequently, in delays that are significantly higher than when a social planner coordinates diversion. The social optimum is itself difficult to characterize analytically and has limited practical appeal because it depends on problem parameters such as arrival rates and length of stay. Instead, we identify an alternative solution that does not require the exact knowledge of the parameters and may be used by the EMS agencies to coordinate diversion decisions when defensive diversion is present. We show that this solution is approximately optimal for the social planner's problem. Moreover, it is Pareto improving over the defensive equilibrium whereas the social optimum, in general, might not be. Key words: emergency department; ambulance diversion; game theory; queueing networks History: Received May 4, 2010; accepted February 18, 2011, by Yossi Aviv, operations management. Published online in Articles in Advance May 16, 2011., 1. Introduction In many regions of the United States, emergency departments (EDs) can declare 'diversion' status (a request to divert incoming ambulances) if they are overcrowded. The local emergency medical [...]

One of the most important variants of the standard linear assignment problem is the bottleneck assignment problem. In this paper we give a method by which one can find all [...]

This paper introduces a parameter-free method for measuring the weighting functions of prospect theory and rank-dependent utility. These weighting functions capture risk attitudes, subjective beliefs, and ambiguity attitudes. Our method, called the midweight method, is based on a convenient way to obtain midpoints in the weighting function scale. It can be used both for risk (known probabilities) and for uncertainty (unknown probabilities). The resulting integrated treatment of risk and uncertainty is particularly useful for measuring ambiguity, i.e., the difference between uncertainty and risk. Compared to existing methods to measure weighting functions and attitudes toward uncertainty and ambiguity, our method is more efficient and can accommodate violations of expected utility under risk. An experiment demonstrates the tractability of our method, yielding plausible results such as ambiguity aversion for moderate and high likelihoods but ambiguity seeking for low likelihoods, as predicted by Ellsberg. Key words: prospect theory; ambiguity; probability weighting; pessimism History: Received March 11, 2009; accepted September 14, 2010, by George Wu, decision analysis., 1. Introduction Decision under risk relates to cases where known statistical probabilities are available for random events. Since Keynes (1921) and Knight (1921), it has been understood that such probabilities [...]

We investigate firms' competitive behaviors in industries where customers are sensitive to both promised delivery time (PDT) and quality of service (QoS) measured by the on-time delivery rate. To study the competition in PDT at the marketing level, we construct an oligopoly game with an external QoS requirement. We show that there exists a unique Nash equilibrium, and the equilibrium QoS exhibits a switching surface structure with respect to capacities. To study the competition in capacity at the strategic level, we construct a two-stage game in which the firms compete in terms of their capacities in stage 1 and in terms of PDT in stage 2. We show the existence of two different types of pure strategy equilibria and characterize them. This study provides the following insights: an index of time-based competitive advantage (ITCA) and the first-mover advantage determine the positions of the firms in time-based competition; either the well-known prisoner's dilemma or off-equilibrium behaviors due to different preferences for equilibria (when multiple equilibria exist) may lead the firms to overinvest in capacity, but no one may gain a competitive advantage; a uniform improvement in internal efficiency (i.e., a uniform capacity cost reduction) may harm everyone; quality differentiation (i.e., going beyond the QoS benchmark) plays a dual role in time-based competition, either helping a firm with a larger ITCA to compete more effectively, or helping a firm possibly with a smaller ITCA to preempt competitors and protect its market advantage. Key words: time-based competition; consumer choice model; Nash equilibrium; switching surface; quality differentiation; capacity competition; marketing-operations interface History: Received October 8, 2008; accepted November 9, 2010, by Paul H. Zipkin, operations and supply chain management. Published online in Articles in Advance February 15, 2011., 1. Introduction Time-based competition occurs in business in a variety of ways. When it comes to competition in product or service delivery time, a widespread strategy in many industries such [...]

This paper studies the incentive for vertical information sharing in competing supply chains with production technologies that exhibit diseconomies of scale. We consider a model of two supply chains each consisting of one manufacturer selling to one retailer, with the retailers engaging in Cournot or Bertrand competition. For Cournot retail competition, we show that information sharing benefits a supply chain when (1) the production diseconomy is large and (2) either competition is less intense or at least one retailer's information is less accurate. A supply chain may become worse off when making its information more accurate or production diseconomy smaller, if such an improvement induces the firms in the rival supply chain to cease sharing information. For Bertrand retail competition, we show that information sharing benefits a supply chain when (1) the production diseconomy is largo and (2) either competition is less intense or information is more accurate. Under Bertrand competition a manufacturer may be worse off by receiving information, which is never the case under Cournot competition. Information sharing in one supply chain triggers a competitive reaction from the other supply chain and this reaction is damaging to the first supply chain under Cournot competition but may be beneficial under Bertrand competition. Key words: supply chain management; supply chain competition; information sharing History: Received January 8, 2009; accepted September 7, 2010, by Martin Lariviere, operations management. Published online in Articles in Advance February 15, 2011., 1. Introduction In undertaking initiatives such as quick response, continuous replenishment, or vendor-managed inventory, manufacturers and retailers have sought to leverage information sharing to improve supply chain performance. Although the [...]

Prior firm experience, firm capabilities, and the industry environment are known to be important determinants of new-venture performance. We hypothesize that firm experience prior to setting up a new venture influences the ability to learn from experience after start-up (which is a key capability), and that this relationship is moderated by the importance of learning by doing within the new venture's industry (which is a critical aspect of the industry environment). We argue that together, these relationships influence performance differences among new plant ventures of incumbents, diversifying entrants, and entrepreneurial (de novo) entrants. Using data on 47,915 new plant ventures in U.S. manufacturing, we find that incumbents and diversifying entrants establish significantly more productive new plants than de novo entrants, and that this advantage significantly increases with the importance of learning by doing in an industry (industry learning intensity). These productivity differences appear to be driven more by learning subsequent to plant start-up than by initial disparities in productivity. Together, these findings strongly suggest that pre-start-up experience adds to the process of post-start-up learning, and that the industry learning environment plays an important role in whether entrepreneurial firms can achieve a competitive advantage over existing firms. Key words: entrepreneurs; learning environment; pre-start-up experience; dynamic capabilities History: Received November 22, 2007; accepted November 4, 2010, by Lee Fleming, entrepreneurship. Published online in Articles in Advance January 28, 2011., 1. Introduction One of the most important challenges that an entrepreneur must face is that of building and sustaining an advantage over their competitors, most of whom are likely to [...]

This paper presents a new model of probabilistic binary choice under risk. In this model, a decision maker always satisfies first-order stochastic dominance. If neither lottery stochastically dominates the other alternative, a decision maker chooses in a probabilistic manner. The proposed model is derived from four standard axioms (completeness, weak stochastic transitivity, continuity, and common consequence independence) and two relatively new axioms. The proposed model provides a better fit to experimental data than do existing models. The baseline model can be extended to other domains such as modeling variable consumer demand. Key words: probabilistic choice; first-order stochastic dominance; random utility; strong utility History: Received March 8, 2010; accepted October 19, 2010, by Peter Wakker, decision analysis. Published online in Articles in Advance January 28, 2011., 1. Introduction Empirical studies show that decisions under risk are often contradictory (e.g., Hey and Orme 1994). Such decisions are best captured through a model of probabilistic choice. Popular models [...]

Reference-dependent preferences have been well accepted in decision sciences, experimental economics, behavioral finance, and marketing. However, we still know very little about how decision makers form and update their reference points given a sequence of information. Our paper provides some novel experiments in a financial context to advance the understanding of reference-point formation over time. Our subjects' reference price is best described as a combination of the first and the last price of the time series, with intermediate prices receiving smaller and nondecaying weights. Hence, reference prices are not recursive. We provide a parsimonious formula to predict the reference points, which we test out-of-sample. The fit of the model is reasonably good. Key words: reference-point formation; reference-dependent preferences; disposition effect; probability weighting History: Received November 26, 2008; accepted October 22, 2010, by George Wu, decision analysis. Published online in Articles in Advance January 28, 2011., 1. Introduction Empirical research over the past 25 years corroborates that subjects are highly affected by reference points. Reference dependence has a long-standing tradition in psychology and was transferred to [...]

We develop a new goodness-of-fit test for validating the performance of probability forecasts. Our test statistic is particularly powerful under sparseness and dependence in the observed data. To build our test statistic, we start from a formal definition of calibrated forecasts, which we operationalize by introducing two components. The first component tests the level of the estimated probabilities; the second validates the shape, measuring the differentiation between high and low probability events. After constructing test statistics for both level and shape, we provide a global goodness-of-fit statistic, which is asymptotically [X.sup.2] distributed. In a simulation exercise, we find that our approach is correctly sized and more powerful than alternative statistics. In particular, our shape statistic is significantly more powerful than the Kolmogorov--Smirnov test. Under independence, our global test has significantly greater power than the popular Hosmer-Lemeshow's [X.sup.2] test. Moreover, even under dependence, our global test remains correctly sized and consistent. As a timely and important empirical application of our method, we study the validation of a forecasting model for credit default events. Key words: out-of-sample validation; probability calibration; Hosmer-Lemeshow statistic; Bernoulli mixture models; credit risk History: Received August 12, 2009; accepted October 22, 2010, by Wei Xiong, finance. Published online in Articles in Advance January 28, 2011., 1. Introduction In conclusion, at present no really powerful tests of adequate calibration are currently available. Due to the correlation effects that have to be respected there even seems to [...]

Multiservice providers, such as telecommunication and financial service companies, can benefit from understanding how customers' service portfolios evolve over the course of their relationships. This can provide guidance for managerial issues such as customer valuation and predicting customers' future behavior, whether it is acquiring additional services, selectively dropping current services, or ending the relationship entirely. In this research, we develop a dynamic hidden Markov model to identify latent states that govern customers' affinity for the available services through which customers evolve. In addition, we incorporate and demonstrate the importance of separating two other sources of dynamics: portfolio inertia and service stickiness. We then examine the relationship between state membership and managerially relevant metrics, including customers' propensities for acquiring additional services or terminating the relationship, and customer lifetime value. Through a series of illustrative vignettes, we show that customers who have discarded a particular service may have an increased risk of canceling all services in the near future (as intuition would suggest) but also may be more prone to acquire more services, a provocative finding of interest to service providers. Our findings also emphasize the need to look beyond the previous period, as in much current research, and consider how customers have evolved over their entire relationship in order to predict their future actions. Key words: customer relationship management; dynamic hidden Markov model; customer value History: Received June 22, 2009; accepted October 20, 2010, by Pradeep Chintagunta, marketing. Published online in Articles in Advance January 20, 2011., Introduction Among the many questions that multiservice providers frequently ask about their customers are which customers are most at risk for terminating (or enhancing) their relationships and which customers are [...]

We explore substitution patterns across advertising platforms. Using data on the advertising prices paid by lawyers for 139 Google search terms in 195 locations, we exploit a natural experiment in 'ambulance-chaser' regulations across states. When lawyers cannot contact clients by mail, advertising prices per click for search engine advertisements are 5%-7% higher. Therefore, online advertising substitutes for offline advertising. This substitution toward online advertising is strongest in markets with fewer customers, suggesting that the relationship between the online and offline media is mediated by the marketers' need to target their communications. Key words: advertising and media; information systems; IT policy and management; electronic commerce; search engine advertising History: Received March 19, 2010; accepted September 28, 2010, by Pradeep Chintagunta, marketing. Published online in Articles in Advance January 28, 2011., 1. Introduction Online advertising has been one of the few advertising platforms that has shown revenue growth over the past five years. (1) An important question for marketers and policy [...]