Faculty AI Research

This paper establishes connections between two derivative estimation techniques: infinitesimal perturbation analysis (IPA) and the likelihood ratio or score function method. We introduce a systematic way of expanding the domain of the former to include that of the latter, and show that many likelihood ratio derivative estimators are IPA estimators obtained in a consistent manner through a special construction. Our extension of IPA is based on multiplicative smoothing.

Customers, in a Poisson stream at rate A, enter an infinite-server queue. Customer service times are independent and uniformly distributed on [0, s], s > 0. Gated service is performed in stages as follows. A stage begins with all customers transferred from the queue to the servers. The servers then begin serving these customers, all simultaneously. The stage ends when the service of all customers is complete. At this point, the next stage begins if the queue is nonempty.

We consider inventory systems with several distinct items. Demands occur at constant, item specific rates. The items are interdependent because of jointly incurred fixed procurement costs: The joint cost structure reflects general economies of scale, merely assuming a monotonicity and concavity (submodularity) property. Under a power-of-two policy each item is replenished with constant reorder intervals which are power-of-two multiples of some fixed or variable base planning period.

This technical note shows that the determination of the stresses induced in multi-metal beams by temperature changes reduces to solving a linear system of equations. This system of equations has a very particular structure that allows one to obtain a closed form solution easily.

A computer-based system for diagnosing bladder cancer is described. Typically, an object falls into one of two classes: Well or Not-well. The Well class contains the cells that will actually be useful for diagnosing bladder cancer; the Not-well class includes everything else. Several descriptive features are extracted from each object in the image and then fed to a multilayer perceptron, which classifies them as Well or Not-well. The perceptron's superior classification abilities reduces the number of computer misclassification errors to a level tolerable for clinical use.

Only one-fourth of U.S. families own stock. This paper examines whether the consumption of stockholders differs from the consumption of nonstockholders and, if so, whether these differences help explain the empirical failures of the consumption-based CAPM. Household panel data are used to construct time series on the consumption of each group. The results indicate that the consumption of stockholders is more volatile and more highly correlated with the excess return on the stock market.

Infinitesimal perturbation analysis is a technique for estimating derivatives of performance indices from simulation or observation of discrete event systems. Such derivative estimates are useful in performing optimization and sensitivity analysis through simulation. A general formulation of finite-horizon perturbation analysis derivative estimates is given, and then sufficient conditions for their use is presented with a variety of queuing systems.

This article provides estimates of Belgian food consumption in 1812 and 1846 using a national food balance sheet approach. These estimates are then converted into caloric intakes for adult male equivalents. Despite many accounts of an absolute pauperization of the Belgian population during this period, caloric consumption per equivalent adult male is shown to have merely stagnated between 1812 and 1846. There is indirect evidence that inequality in caloric consumption increased at the same time.

When futures contracts are settled with respect to underlying asset prices, received theory suggests that the differences between futures prices and implied forward prices (from the term structure) are strictly due to marking to market, ceteris paribus. Empirical evidence appears to indicate that such differences are small for contracts with short maturities. What happens when the futures contract settles to yields implied by future prices of underlying assets?

For 0<K'<K≤∞, we obtain a K'-capacity queue from a K-capacity queue through a random time change and a truncation, provided arrivals are Poisson or service is exponential. In the case of an M/G/1/K queue, the time change erases service intervals that begin with more than K' customers in the systems. This constructions yields a straightforward sample path proof of Keilson's result on the proportionality of the ergodic queue length probabilities in M/G/1/K queues.

This paper is concerned with the general dynamic lot size model, or (generalized) Wagner-Whitin model. Let n denote the number of periods into which the planning horizon is divided. We describe a simple forward algorithm which solves the general model in 0(n log n) time and 0(n) space, as opposed to the well-known shortest path algorithm advocated over the last 30 years with 0(n²) time.

The authors first attempt to clarify the affect terminology. Then, in an empirical study, they explore the affective reactions prompted by a wide range of consumption situations. For each of them, the authors investigate what preceeds, what happens during and what happens after the situation. 1,436 affective experiences, retrieved by 118 subjects in response to the proposed situations, were content-analyzed. The subjects reported more positive than negative affective reactions. These were essentially feelings, followed by evaluative affects.

This paper examines the allocative role of class shares that pay dividends based upon the performance of the individual activities of multi-activity firms. The firms considered operate under economies of scope and technological uncertainty in an incomplete asset market. Investor unanimity about the choice of production plans and a constrained Pareto optimum are attained when all firms in the economy issue a class of shares for each of their activities.

This article proposes a model that nests both a strict tree model and the Luce choice model. The multiplicative formulation allows for easy estimation using least-squares procedures. The model is shown to be more parsimonious than the hierarchical elimination method and in a small illustration, to significantly out-perform Luce in predicting soft-drink preferences.

In this paper we consider a class of single-server queueing systems with compound Poisson arrivals, in which, at service completion epochs, the server has the option of taking off for one or several vacations of random length. The cost structure consists of holding cost rate specified by a general non-decreasing function of the queue size, fixed costs for initiating and terminating service, and a variable operating cost incurred for each unit of time that the system is in operation.

Demandable-debt finance by banks warrants explanation because it entails costs of bank suspension, liquidation, and idle reserve holdings. An explanation is developed in which demandable debt provides incentive-compatible intermediation where the banker has comparative advantage in allocating investment funds but may act against the interests of uninformed depositors. Demandable debt attracts funds by giving depositors an option to force liquidation. Its usefulness in transacting follows from information-sharing between monitors and nonmonitors.

The traditional pricing methodology in finance values derivative securities as redundant assets that have no impact on equilibrium prices and allocations. This paper demonstrates that when the market is incomplete primary and derivative asset markets, generically, interact: the valuation of derivative and primary securities is a simultaneous pricing problem and primary security prices depend on the contractual characteristics of the derivative assets available.

This article examines the reasons for the observed discrepancy between workers' actual and required levels of schooling and the resulting differences in returns to schooling, "Overeducated" workers are found to be younger and to have lower amounts of on-the-job training than workers with the required level of schooling. They also have higher rates of firm and occupational mobility, characterized by movement of higher-level occupations.

Generalized semi-Markov processes (GSMPs) and stochastic Petri nets (SPNs) are generally regarded as performance models (as opposed to logical models) of discrete event systems. Here we take the view that GSMPs and SPNS are essentially automata (generators) driven by input sequences that determine the timing of events. This view combines the deterministic, logical aspects and the stochastic, timed aspects of the two models.

This article evaluates the role of rate of return (ROE) in assessing cross-sectional differences in prices and price changes of ROE. Accounting ROE is traditionally regarded as the major summary number in financial statement analysis. Findings of the study indicate that ROE is best interpreted as a profitability measure and not as a risk measure and observed ROE indicates future profitability and thus distinguishes market-to-book ratios. The comparison of earnings to book values in the ROE calculation provides information about how earnings project to future earnings.

We analyze a continuous-time, two-stage production/inventory system. In the first stage, a common intermediate product is produced in batches, and possibly stored. In the second phase, the intermediate product is fabricated into n distinct finished products. Several finished products may be included in a single production batch of limited capacity to exploit economies of scale. We propose a planning methodology to address the combined problem of joint setup costs and capacity limits (per setup).

Japan's capital markets have played a crucial role in the recent increase in the globalization of international capital markets. As a result it has become important to understand the similarities and differences in the way Japanese markets operate in comparison to the more familiar Anglo-American environment. One of the major differences that has attracted a great deal of attention is the relatively high average price/earnings [PE] ratio (Viner [1988]) for the stocks listed on the Tokyo Stock Exchange.

We present survey data challenging the assumption implicit in analyses of labor supply that, all else being equal, workers prefer declining over increasing wage profiles.

In this paper we investigate whether the level of earnings divided by price at the beginning of the stock return period is relevant for evaluating earnings/returns associations. The primary model motivating this research relies on the idea that book value (owners' equity) and market value are both "stock" variables indicating the wealth of the firm's equity holders. The related "flow" variables (after adjusting for dividends) are, respectively, earnings divided by price at the beginning of the return period (A/P_-1) and market returns.

Let x(j) be the expected reward accumulated up to hitting an absorbing set in a Markov chain, starting from state j. Suppose the transition probabilities and the one-step reward function depend on a parameter, and denote by y(j) the derivative of x(j) with respect to that parameter. We estimate y(0) starting from the respective Poisson equations that x = [x(0),x(l), . . . ] and y = [y(0),y(l), . . . ] satisfy.

In this paper, a new algorithm for computing optimal (s, S) policies is derived based upon a number of new properties of the infinite horizon cost function c(s, S) as well as a new upper bound for optimal order-up-to levels S* and a new lower bound for optimal reorder levels s*. The algorithm is simple and easy to understand. Its computational complexity is only 2.4 times that required to evaluate a (specific) single (s, S) policy. The algorithm applies to both periodic review and continuous review inventory systems.

Customer orientation is a fine ideal. Making it a reality is difficult for many organizations. Provides a framework to guide management through the process of building a customer-driven philosophy. It is hoped that by means of such a framework it will be possible to evaluate an organization's customer orientation profile, and to provide the basis for a comparison of interorganizational approaches.

In this paper we propose a model for describing consumer decision making among assortments or menus of options from which a single option will be chosen at a later time. Central to the derivation of the model is an assumption that consumers are uncertain about their future preferences. The model captures both the utility of the items within the assortments as well as the flexibility the items offer as a group. We support our model empirically with two laboratory experiments. In the first experiment we test the underlying assumptions.