Relevant Performance Measures Research Articles

The Stochastic Economic Lot Scheduling Problem: Cyclical Base-Stock Policies with Idle Times

In this paper we discuss stochastic Economic Lot Scheduling Problems (ELSP), i.e., settings where several items need to be produced in a common facility with limited capacity, under significant uncertainty regarding demands, production times, setup times, or combinations thereof. We propose a class of production/inventory strategies for stochastic ELSPs and describe how a strategy which minimizes holding, backlogging, and setup costs within this class can be effectively determined and evaluated. The proposed class of strategies is simple but rich and effective: when the facility is assigned to a given item, production continues until either a specific target inventory level is reached or a specific production batch has been completed; the different items are produced in a given sequence or rotation cycle, possibly with idle times inserted between the completion of an item's production batch and the setup for the next item. An optimal strategy within the class can be determined, and all relevant performance measures can be evaluated in just a few CPU seconds, using a 486-based PC. We also derive a number of easily computable lower bounds for the optimal cost value and establish a comparison with deterministic ELSPs.

Uncertainty about probability: a reconciliation with the subjectivist viewpoint

The use of probability distributions to represent uncertainty about probabilities (rather than events) has long been a subject of controversy among theorists. Many have concluded that it is inherently meaningless to be uncertain about a probability, because this appears to violate the subjectivists' assumption that individuals can develop unique and precise probability judgments. Others have found the concept of uncertainty about probability to be both intuitively appealing and potentially useful. This paper presents a resolution of this question, indicating that at least one type of uncertainty about probabilities (that arising from uncertainty about the underlying events on which those probabilities are conditioned) is consistent with the subjective theory of probability. Another type of uncertainty (namely, that arising from cognitive imprecision) appears not to be consistent with the axioms of subjective probability as they are currently formulated, Distinguishing between these two sources of uncertainty is an important step in resolving the persistent theoretical controversy over uncertainty about probability. We also show that uncertainty about probability will be potentially relevant to decision-making whenever the expected value of the relevant performance measure is nonlinear in the probability in question.

Source modelling, queueing analysis, and bandwidth allocation for VBR MPEG-2 video traffic in ATM networks

The authors propose a mini-source based discrete-time Markov modulated deterministic process (D-MMDP) to model the macro-frame smoothed VBR MPEG-2 traffic. It is shown that such a modelling technique is sufficiently accurate and implies the involved queueing analysis for relevant system performance measures. It also provides a simple and accurate solution to the bandwidth allocation problem for VBR MPEG-2 video traffic.

Modeling and simulation of pedestrian traffic flow

Questions about the efficiency and safety of pedestrian traffic systems are of major importance in the planning and design of such systems. As the use of functional—or performance-based—requirements becomes more popular, there is also an increasing need for methods and tools which can be used to evaluate if these functional requirements are met. This article presents a stochastic model based on the following assumptions: Any pedestrian facility can be modeled as a network of walkway sections. Pedestrian flow in this network can be modeled as a queueing network process, where each pedestrian is treated as a separate flow object, interacting with the other objects. Such a microscopic model is useful because it makes detailed modeling of human behavior possible. This article also presents a simulation tool, of which the main objective is to estimate the relevant performance measures of the pedestrian traffic system. The article includes two examples.

Decision analysis in the evaluation of diagnostic tests

Summary Decision analysis was used to evaluate the clinical usefulness of 2 diagnostic tests: one for canine heartworm disease and the other for bovine traumatic reticuloperitonitis. Several clinically relevant measures of test performance are introduced, including expected utility, risk profile, testing band, threshold analysis, and the relative cost of misdiagnosis. One of the principal benefits of decision analysis of diagnostic tests is that the technique can be used to determine how changes in underlying assumptions will affect clinical decisions. If clinicians can identify and assign values to relevant variables, then decision analysis can provide clinically meaningful guidelines for interpreting the results of diagnostic tests. To take advantage of these techniques, clinicians must become comfortable with quantitative expressions for test performance, risk, and prognosis.

Measuring the performance of emerging businesses: A validation study

To identify and substantiate the correlates and antecedents of new venture performance, it is requisite to identify the most relevant performance dimensions and move toward the use of common measures of performance. Relevant, reliable, and valid measures of new venture performance are essential to explore vital relationships between independent variables and venture success and develop sound venture performance theory. In this paper we discuss three of the most common measurement approaches used in new venture performance research when only self-report data are available, and present a comparison of these approaches: (1) measuring firm performance in broadly defined categories, (2) the use of subjective measures of executive or owner satisfaction with firm performance, and (3) the use of subjective measures of firm performance relative to competitors. After discussing the relevance and potential benefits and drawbacks of each approach we use empirical data to examine and compare the availability, reliability, and relative validity of measures developed using these approaches. The sample consisted of manufacturing businesses (SIC codes 20–39) started or reorganized in the corporate form between 1980 and 1991 in nine counties in northwestern Pennsylvania's identified by a major marketing research service. Questionnaires were returned by primary respondents in 120 companies; complete matching firm performance data from a second respondent were returned for 45 of the firms. The pattern of results favors the use of two dimensions of venture performance: growth and business volume. The growth and business volume measures operationalized in this research have good availability and internal consistency and are superior to the satisfaction with performance and performance relative to competitors' scales in terms of content validity. Evidence of the external validity of the measures is provided by regression analysis showing independent variables identified and substantiated by previous research to be related to performance in the hypothesized manner. The satisfaction with performance index had a high disclosure rate, strong internal consistency, and relatively strong inter-rater reliability. There is little evidence supporting its external validity. With the exception of its negative relationship with the level of competition, none of the predicted relationships are substantiated. The performance relative to competitors' disclosure rate was somewhat lower as was the inter-rater reliability; however, it emerged as a strong independent construct with a high level of internal consistency. There was evidence for the external validity of this measure. The independent variables related to the performance relative to competitors' index are similar to those related to both the growth and business volume dimensions as predicted from previous theoretical work and research findings. In summary, this research makes several contributions to the new venture performance literature. First, when researchers are required to use self-reported measures of venture performance, growth and business volume are the dimensions of performance most familiar to and most commonly referenced by the founders. Second, it provides additional evidence for the accuracy and reliability of founder reported performance data. Third, it provides examples of specific measures with evidence that supports their relevance, availability, reliability, and validity. We believe this research can provide a base for future venture performance research. We hope that these findings will be used to help better our understanding of the dynamics impacting new venture performance and lead to improved managerial practice in emerging firms.

Corporate Financial Policy, Taxation, and Macroeconomic Risk

This paper develops a simple model of financial structure intended to formalize the macroeconomic concern over leverage. In particular, we attempt to rationalize why firms designing an optimal capital structure would choose a level of debt that leaves them heavily exposed to macroeconomic risk. Our starting point is a variant of the corporate control model often used to motivate debt as the optimal financial contract. We modify this framework in two ways. First, we include common risks, interpretable as business cycle risks, as well as idiosyncratic risks. Second, we include and investor-level taxes, and consider the implications of a net tax bias against equity finance. The tax distortion confronts firms with a tradeoff ex ante between the costs of equity finance and the costs of increased exposure to macroeconomic risk accompanying debt finance. In this regard, an equilibrium with excessive leverage is possible. Further, despite the possibility of renegotiation, debt is in general less effective than equity in insulating the firm against aggregate risk. Our model leads to the prediction that individual firm dividends may vary with macroeconomic conditions, even after controlling for the effects of relevant firm-specific performance measures, such as earnings. We present some formal econometric evidence in support of this prediction, using a panel of individual corporations. Evidence on some related predictions is also presented.

On performance measures for multistate monotone systems

Abstract This paper gives an overview of relevant performance measures for a multistate monotone system, observed in a time interval J . Flow network systems are an important class of these systems. The computation of these measures are discussed. Some easily computed approximation formulae are established. The accuracy of these formulae are studied by making comparisons with results obtained by Monte Carlo simulation.

A decision support system for simulation modeling

Abstract This paper presents a decision support system for the simulation of a flexible manufacturing cell. The design, construction, development, and structure of the system will be discussed, and a few of its features described. This paper also presents an overview of some popular methods used to develop user-independent simulations and discusses the developed modeling methodologies in this context. Different system configurations are compared using relevant performance measures. Following a comprehensive analysis of the results, we make specific recommendations regarding appropriate courses of action.

Voluntary compliance and the effectiveness of public and non-profit institutions: American philanthropy and taxation

Compared to for-profit organizations, performance evaluation for public and non-profit agencies is more likely to be based on measures such as whether advocated social behaviors are adopted by targeted groups. Further, these behaviors are frequently complex, often resisted, with few immediate or strong rewards. Voluntarism is one such action that is of great concern to many such institutions, not only in matters of conscience but also in conduct involving difficult-to-enforce laws and regulations. Using the construct of voluntary compliance, this paper addresses four objectives: first, to review the need for public and non-profit agencies to identify their relevant measures of performance; second, to outline the similarity between determinants of voluntary support of philanthropy and the American system of taxation; third, to present empirical evidence describing the characteristics associated with such behaviors; and last, to use those findings to develop a general set of postulates for improving the performance of public and non-profit agencies.

Combined coding and modulation: theory and applications

The theoretical aspects of the encoding process are investigated, resulting in a precise definition of linear codes together with theorems that clarify how they can be obtained. A particular subset of linear codes, called superlinear codes, for which the performance analysis is highly simplified is identified. The most relevant performance measures for the analysis of this class of codes are discussed. The minimum Euclidean distance and the event and bit error probabilities are found analytically using the uniform error property (when applicable) or variations on it. This yields accurate upper and lower bounds to the error rate at the price of reasonable computational complexity. The theory is then applied to the search for 'good' codes and to their performance evaluation. The cases of 16- and 32-PSK codes, which are good candidates for use in digital satellite transmission, are considered. Several new results in terms of error event and bit error probabilities are presented, showing considerable gains in terms of SNR with respect to the uncoded case. >

Queueing model of a bi-level Markov service-system and its solution using recursion

The authors present a closed queueing model of a bi-level stochastic service system using a Markov process. The existence of two modes of operation in some real situations such as reliability, inventory, and production problems is outlined. A recursive solution technique is developed for computing steady-state probabilities and the relevant performance measures for such a system. A bi-level system is completely analyzed. The effect of the two modes of operation on the system performance measures is also discussed. The recursive solution technique is consistently superior to other common solution techniques with respect to computation time and memory requirement. A procedure is outlined for extension to a multi-level service system.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Brownian models of open queueing networks with homogeneous customer populations∗

We consider a family of multidimensional diffusion processes that arise as heavy traffic approximations for open queueing networks. More precisely, the diffusion processes considered here arise as approximate models of open queueing networks with homogeneous customer populations, which means that customers occupying any given node or station of the network are essentially indistinguishable from one another. The classical queueing network model of J. R. Jackson fits this description, as do other more general types of systems, but multiclass network models do not.The objectives of this paper are (a) to explain in concrete terms how one approximates a conventional queueing model or a real physical system by a corresponding Brownian model, and (b) to state and prove some new results regarding stationary distributions of such Brownian models. The part of the paper aimed at objective (a) is largely a recapitulation of previous work on weak convegence theorems, with the emphasis placed on modeling intuition. With respect to objective (b), several important foundational issues are resolved here and under certain conditions we are able to express the staionary distribution and related performance measures in explicit formulas. More specifically, it is shown that the stationary distribution of the Brownian model has a separable (product form) density if and only if its data satisfy a certain condition, in which case the stationary density is exponential, and all relevant performance measures can be written out in explicit formulas

On the nonconcavity of throughput in certain closed queueing networks

Analytic queueing network models are being used to analyze various optimization problems such as server allocation, design and capacity issues, optimal routing, and workload allocation. The mathematical properties of the relevant performance measures, such as throughput, are important for optimization purposes and for insight into system performance. We show that for closed queueing networks of m arbitrarily connected single server queues with n customers, throughput, as a function of a scaled, constrained workload, is not concave. In fact, the function appears to be strictly quasiconcave. There is a constraint on the total workload that must be allocated among the servers in the network. However, for closed networks of two single server queues, we prove that our scaled throughput is concave when there are two customers in the network and strictly quasi-concave when there are more than two customers. The mathematical properties of both the scaled throughput and reciprocal throughput are demonstrated graphically for closed networks of two and three single server queues.

Physical design for a random-access file with random insertions and deletions

This paper studies in detail the performance of a database that is subject to random additions and deletions. The relevant performance measures are derived in explicit closed-form. These performance measures are applied to study the problem of optimal physical design.

Analysis of Clocked Schedules-High-Priority Tasks

Clocked schedules are used in a variety of real-time systems to perform tasks in accordance with their delay requirements. A comprehensive overview of various clocked schedules can be found in the accompanying paper by Fredericks et al. For one model of a clocked schedule we can see approximate and exact analysis of the relevant performance measures in the papers by Fredericks et al. and by Ackroyd in this issue of the Journal. These results can also be used to evaluate the long-term delays in the other models. For extremely time-critical (high-priority) tasks, the probability of tasks not getting served in the scheduled interval and the short-term delay distribution are important performance measures that are sensitive to the detail structure of the clocked schedule. In this paper, we show that these performance measures can be obtained in terms of steady-state distribution of an embedded Markov chain. This steady-state distribution is calculated, exactly or approximately, for a number of models, and the results are used to compare, numerically, various scheduling mechanisms.

Analysis of linear probing with buckets

Consider a random-access file which consists of a given number of buckets. Each bucket contains a fixed number of slots. Storage and retrieval of records are performed using linear probing. The probabilities underlying the behavior of this addressing system are determined, and the relevant performance measures are derived.

Wear mechanisms that dominate tool-life in machining

The broad concern of the research described in this paper is to identify which of a number of possible tool wear mechanisms have the dominant influence on tool performance for a given toolwork combination. It is proposed that the commercially relevant measure of tool performance is the volume of material worn away from the noseradius region of the tool. A general equation is presented stating that this is affected by adhesion, abrasion, oxidation/adhesion wear, diffusion and plastic deformation of the edge. Micrographs are presented showing these main forms of wear, and the cutting conditions at which they dominate are discussed. The magnitude of the normal stress acting on the cutting edge and the elevated temperature compressive strength of the tool material are shown to limit the maximum rate of metal removal for a particular toolwork combination.

Performance measures for ordered lists in random-access files

A random-access file with N storage locations ~s consmdered. Records are added to the file from time to tmme A record wroth key ~f ~ ~2 ms hashed to storage location F(,o). A collismon ms resolved by the foUowmg chaining method' All records hashed to the same locatmon are chained to each other to form an ordered list, ordered m ascending order of the keys The first record of a list is stored either at location F(~0) or at an alternative start ff IocaUon F(,o) ms occupied. For thins process the multidimensional ume-dependent generating funcuon is derived, and the expected values of various state variables are calculated. These values are used to obtain formulas for the expected number of I/O operations needed for retrieval, addmon, or updating of a record Two measures of retrieval performance are calculated: (i) The expected number of addiuonal probes needed to find a record m the file This measure ms uniformly bounded by t. (n) The expected number of addmonal probes required to dmscover that a record is not in the file. This performance measure IS always smaller than the first and ms uniformly bounded by I/e. Addmon of a record consists of three steps. (l) checking that a record with the same key does not exmst in the file, (2) finding an empty locatmon, and (3) wrmng the record and updating all the pointers revolved The number of I/O operatmons needed for record addmon depends on the amount of reformation avadable on the occupancy of the file For various mformatmn levels the relevant performance measures are calculated and compared

Performance Measures for Ordered Lists in Random-Access Files

A random-access file with N storage locations ~s consmdered. Records are added to the file from time to tmme A record wroth key ~f ~ ~2 ms hashed to storage location F(,o). A collismon ms resolved by the foUowmg chaining method' All records hashed to the same locatmon are chained to each other to form an ordered list, ordered m ascending order of the keys The first record of a list is stored either at location F(~0) or at an alternative start ff IocaUon F(,o) ms occupied. For thins process the multidimensional ume-dependent generating funcuon is derived, and the expected values of various state variables are calculated. These values are used to obtain formulas for the expected number of I/O operations needed for retrieval, addmon, or updating of a record Two measures of retrieval performance are calculated: (i) The expected number of addiuonal probes needed to find a record m the file This measure ms uniformly bounded by t. (n) The expected number of addmonal probes required to dmscover that a record is not in the file. This performance measure IS always smaller than the first and ms uniformly bounded by I/e. Addmon of a record consists of three steps. (l) checking that a record with the same key does not exmst in the file, (2) finding an empty locatmon, and (3) wrmng the record and updating all the pointers revolved The number of I/O operatmons needed for record addmon depends on the amount of reformation avadable on the occupancy of the file For various mformatmn levels the relevant performance measures are calculated and compared