Several computational applications in stochastic operations research are presented, where, for each application, a computational engine is used to achieve results that are otherwise overly tedious by hand calculations, or in some cases mathematically intractable. Algorithms and code are developed and implemented with specific emphasis placed on achieving exact results and substantiated via Monte Carlo simulation. The code for each application is provided in the software language utilized and algorithms are available for coding in another environment. The topics include univariate and bivariate nonparametric random variate generation using a piecewise-linear cumulative distribution, deriving exact statistical process control chart constants for non-normal sampling, testing probability distribution conformance to Benford's law, and transient analysis of M/M/s queueing systems. The nonparametric random variate generation chapters provide the modeler with a method of generating univariate and bivariate samples when only observed data is available. The method is completely nonparametric and is capable of mimicking multimodal joint distributions. The algorithm is "black-box," where no decisions are required from the modeler in generating variates for simulation. The statistical process control chart constant chapter develops constants for select non-normal distributions, and provides tabulated results for researchers who have identified a given process as non-normal The constants derived are bias correction factors for the sample range and sample standard deviation. The Benford conformance testing chapter offers the Kolmogorov-Smirnov test as an alternative to the standard chi-square goodness-of-fit test when testing whether leading digits of a data set are distributed according to Benford's law. The alternative test has the advantage of being an exact test for all sample sizes, removing the usual sample size restriction involved with the chi-square goodness-of-fit test. The transient queueing analysis chapter develops and automates the construction of the sojourn time distribution for the nth customer in an M/M/s queue with k customers initially present at time 0 (k ≥ 0) without the usual limit on traffic intensity, rho < 1, providing an avenue to conduct transient analysis on various measures of performance for a given initial number of customers in the system. It also develops and automates the construction of the sojourn time joint probability distribution function for pairs of customers, allowing the calculation of the exact covariance between customer sojourn times.

With the growing interest in the Marcellus Shale and its natural gas deposits, there are opportunities to purchase and hold land for investment purposes. A robust decision tool is needed to help guide investors towards the most profitable properties. Artificial neural networks have many unique benefits that make them an ideal candidate for this purpose. The artificial neural networks created in this study had nine independent variables. Combinations of these nine variables were created to describe 300 theoretical properties available for purchase. Each of these properties were then evaluated by an expert in the field and given a score from one to five to rate its investment potential, which was the dependent variable. Sixteen different network architectures were used to create over 200 neural networks. However, none of these networks met the criteria established to determine success. This is likely due to the unreliability in the data used to train the network, evidenced by the expert’s inability to reproduce previously assigned scores.

Includes bibliographical references. / Fund managers and investors are confronted with the problem of selecting a single investment portfolio from a large number of possible combinations of available assets. In South Africa the set of possible portfolios has become even larger with the gradual relaxing of the constraints on foreign investment from 1995 to the present day, thereby expanding the investment universe for South African investors. Moreover, portfolio selection in South Africa is being transformed increasingly from being the exclusive domain of high net worth individuals, trustees and their investment managers to being the domain and responsibility of the man on the street. The Unit Trust industry started in South Africa in 1965 and gave the lower net worth individual a vehicle with which to invest in a diverse investment portfolio. This industry has proved very popular and has expanded from only 8 funds in 1980 to 338 funds and 136 billion rands under management in November 2000. Moreover the past two years, 1999 and 2000, has seen a change in the pension fund industry from defined benefit (DB) to defined contribution (DC) pension funds, transferring more of the risk and the responsibility of portfolio selection onto pension fund members. With increasing demand for fund management and investment advice by pension fund members and individual investors alike, the financial services industry in South Africa has also expanded. The consequent competition for assets of all descriptions have led, one hopes, to a more efficient market in equity, fixed income and derivative products. Thus modern portfolio theory has come a long way and will have to go further in meeting the demand to assist investors in their decision making.

Understanding team behaviors and dynamics are important to better understand and foster better teamwork. The goal of this master's thesis was to contribute to understanding and assessing teamwork in small group research, by analyzing motion dynamics and team performance with non-contact sensing and computational assessment. This thesis's goal is to conduct an exploratory analysis of motion dynamics on teamwork data to understand current limitations in data gathering approaches and provide a methodology to automatically categorize, label, and code team metrics from multi-modal data. We created a coding schema that analyzed different teamwork datasets. We then produced a taxonomy of the metrics from the literature that classify teamwork behaviors and performance. These metrics were grouped on whether they measured communication dynamics or movement dynamics. The review showed movement dynamics in small group research is a potential area to apply more robust computational sensing and detection approaches. To enhance and demonstrate the importance of motion dynamics, we analyzed video and transcript data on a publicly available multi-modal dataset. We determined areas for future study where movement dynamics are potentially correlated to team behaviors and performance. We processed the video data into movement dynamic time series data using an optical flow approach to track and measure motion from the data. Audio data was measured by speaking turns, words used, and keywords used, which were defined as our communication dynamics. Our exploratory analysis demonstrated a correlation between the group performance score using communication dynamics metrics, along with movement dynamics metrics. This assessment provided insights for sensing data capture strategies and computational analysis for future small group research studies.

The exposure of companies to turbulence, uncertainty, and vulnerability in their supply chain results in supply chain disruption with an estimate cost of $10 million for each supply chain disruption. The purpose of this case study was to explore the strategies supply chain managers use to mitigate supply chain disruption on business performance in a pharmaceutical company in Maryland. Contingency theory of fit formed the conceptual framework for this study. Participant perceptions were elicited in interviews with 11 supply chain managers regarding strategies to mitigate risks associated with supply chain disruptions. Data from interviews and supporting documents were processed and analyzed using data source triangulation to discern emergent themes. Three main themes emerged: (a) supply chain design, planning, and forecasting; (b) flexible and multiple supplier base; and (c) resource allocation and demand management. The implications for positive social change include the potential of reducing supply chain risk, which could lead to lower prices of products for consumers, increased stakeholder satisfaction, and a higher standard of living.

This thesis describes a research programme which investigates further the models developed by Conway [1] - the dynamic model of the process of operational research and the life cycle of in-house operational research groups. It studies the relationships between the two, and also extends the range of applicability of the models. From this the research develops a useful tool to assist the strategic management of in-house operational research groups. In the prev ious study, the two mode I s had been re I ated in theory only. This study investigates the actual relationships and develops a method of defining an operational research group's position on its life cycle using data about the mix of proj ects of the dynamic mode I project types. This method was developed using data from the Conway study, and tested on data collected in two surveys conducted during the current period of research. In certain circumstances, it was found to be essential that other aspects of the data on operational research projects were used to help define more exactly the current state of health of the operational research group. The level or importance of the project was shown to be significant, as was the approach employed when tackling the project. The validity of the model with respect to other forms of operational research group was also investigated, and external consultancy was chosen for this research. A classification was developed which categorised consultants according to their managerial structure, and consultants from each of the types in the classification were interviewed using Systems Based Interviewing. The interviews showed that the dynamic model of the process of operational research was a valid way to describe external operational research consultancy. Some preliminary concepts involving the life cycle of consultancies were also developed, but could not be tested within the time scale of this study. 1. CONWAY, D.A., (1984), "The Development and Application of a Dynamic Model of the Process of Operational Research". PhD thesis, Hatfield Polytechnic.

No description available.

No description available.

A realist evaluation study researching the impact of feeding back patient reported outcome measures to patients with shoulder pain and the impact on behaviour.

Frequency Domain Experiments (FDEs) were first used in discrete-event simulation to perform system parameter sensitivity analysis for factor screening in stochastic system simulations. FDEs are based on the intuitive assertion that if one or more system parameters are oscillated at fixed frequencies throughout a simulation run, then oscillations at the same frequencies will be induced in the system's response. Spectral (Fourier) analysis of these induced oscillations is then used to characterize and analyze the system. Since their introduction 12 years ago, significant work has been done to extend the applicability of FDEs to regression analysis, simulation optimization and gradient estimation. Two fundamental theoretical and data analysis FDE problems remain, however. Both problems are addressed in this dissertation.;To perform a FDE Fourier analysis, a sampled data sequence of response observations is used; i.e., the selected system response is sampled using a suitable oscillation (sampling) index. The choice of an appropriate oscillation index is an open problem in the literature known as the FDE indexing problem. This dissertation presents a solution to the FDE indexing problem. Specifically, a FDE Fourier data analysis algorithm is developed which uses the simulation clock as the oscillation index. This algorithm is based on the well-established theory of counting (Poisson) processes. The algorithm is implemented and tested on a variety of systems including several networks of nonstationary M/G/1 queues.;To justify the use of Fourier methods, a basic FDE model assumption is that if a particular system response statistic is sensitive to a system parameter, then sinusoidal variation of that system parameter at a fixed frequency will induce similar sinusoidal variations in the response statistic, at the same frequency. There is, however, a lack of theoretical support for this model assumption. This dissertation provides some of that theoretical support; i.e., the FDE Fourier data analysis algorithm developed in this dissertation is used to analyze the frequency response of a M/M/1 queuing system. An equation is derived which accurately characterizes the extent to which the departure process from a M/M/1 queuing system can be modeled as an amplitude-modulated, phase-shifted version of the oscillated arrival process.