Table of contents(20 chapters)
This chapter presents selected multiobjective methods for multiperiod portfolio optimization problem. Portfolio models are formulated as multicriteria mixed integer programs. Reference point method together with weighting approach is proposed. The portfolio selection problem considered is based on a multiperiod model of investment, in which the investor buys and sells securities in successive investment periods. The problem objective is to allocate the wealth on different securities to optimize the portfolio expected return, the probability that the return is not less than a required level. Multiobjective methods were used to find tradeoffs between risk, return, and the number of securities in the portfolio. In computational experiments the data set of daily quotations from the Warsaw Stock Exchange were used.
For certain consumer durables, such as automobiles, warranty policies involve two attributes. These could be the time elapsed since sale of the product and usage of the product at a given point in time. Warranty may be invoked by the consumer if both time and usage are within specified warranty parameters when a product failure occurs. In this chapter, we assume that usage and product age are related through a random variable, the usage rate, which may have a certain probabilistic distribution as influenced by consumer behavior patterns. Additionally, product failure rate is influenced by the usage rate and product age. The integrated model includes expected unit warranty costs, expected unit research and development costs, and expected unit production costs. It is assumed that in production, there is a learning effect with time. A multiobjective model is incorporated with the objectives being market share and proportion of expected warranty costs relative to total manufacturing expenditures per unit. The goals could be conflicting in nature. The problem then is to determine the warranty policy parameters while attaining certain desirable values of the two objectives.
In the wake of the recent accounting and financial scandals that have resulted in significant losses, corporate social responsibility (CSR) is viewed by many investors as an important criterion in their investment selection strategy. In addition, social responsibility is viewed by current employees as an important source of job satisfaction and by potential employees as an attractive feature in their decision process. Corporate governance, in the form of the board of directors, serves as the ultimate internal control mechanism by aligning firm insiders and outsiders. The strength and independence of the board of directors becomes a fundamental concern, as firms with strong boards may be more likely to survive and prosper in the long run. The selection of candidates to the board of directors involves both subjective and objective information. The analytical hierarchy process (AHP) is a multicriteria decision model that can integrate both objective and subjective information. This study applies the AHP methodology to the identification of characteristics of candidates to the board of directors of socially responsible firms. The result is a dynamic model that can be used by socially responsible firms to efficiently select candidates to serve on their board of directors.
Data envelopment analysis (DEA) is a multicriteria technique which can take into account multiple inputs and outputs to produce a single aggregate measure of relative efficiency for a set of comparable units. DEA takes into consideration other objectives by including the appropriate variables as part of the DEA model. However, as we will demonstrate, collapsing all the inputs and outputs of several objectives into one aggregate performance measure weakens DEA's ability to discriminate the individual impact of each of these objectives. In this chapter, we apply a multiple objective extension to DEA, called multiple objective DEA (MODEA), which simultaneously controls the weights assigned to the variables found in more than one objective. This MODEA approach more fully measures the impact of each objective and allows the decision-maker to address trade offs among these objectives. The usefulness of the MODEA approach is demonstrated by applying it to the hypothetical example.
DMUo is efficient if and only if the maximum value of ho is equal to 1. Model (1) is solved for each DMU. Decision makers can use these efficiency ratings to identify those DMUs, which need improvement. A survey of DEA models and applications is available in the work by Charnes, Cooper, Lewin, and Seiford (1995).
This chapter develops a methodology to assist critical facility operators in designing physical protection systems to defend against a single adversary (thief, saboteur, terrorist, etc.) attack. The developed methodology utilizes a multicriteria decision-making approach that balances the competing goals of minimal security system cost and maximum system performance. The methodology utilizes a network-based approach to facility security system design and analysis, which locates physical protection (detection, delay, and response) elements throughout a facility. These elements enable the facility owner to prevent attacks through deterrence and to defeat the adversary if he or she chooses to attack. The developed approach results in the ability for the facility operator to assess relative facility and/or infrastructure safety, and make decisions regarding how to optimally allocate resources for physical protection elements to balance cost and performance. A hypothetical example is discussed which demonstrates the usefulness of the developed methodology.
Public schools in the United States continue their struggle with the divergent goals of improving performance and reducing spending. For almost a decade, they have been challenged to comply with the federal No Child Left Behind Act (NCLB). In many local districts, those goals have been pursued with the reality of funding reductions, and the problem now exacerbated by budget shortfalls due to the global economic crisis. In the present situation, solutions based on efficiency and economy are worthy of renewed examination.
This chapter employs data envelopment analysis (DEA) in a large-scale study of 447 public school districts in the State of Missouri. It develops a baseline DEA model to measure district efficiencies. Then it classifies districts using a relative wealth variable (rich and poor) and attempts to determine the degree to which that classification changes the baseline model.
The study concludes that using a relative wealth variable in the analysis produces more robust results than the baseline model. It further demonstrates that funding allocation decisions may be improved by including a relative wealth variable in the decision-making processes.
The study on output allocative efficiency considering the emission trading is meaningful to allocate emission quota in order to promote production efficiency of industry. This chapter studies the output allocation problem with constraints to profit and pollution goals, and proposes three types of output allocative efficiency measures, including the comprehensive output allocative efficiency, the profit-oriented output allocative efficiency based on pollution constraint, and the pollution-oriented output allocative efficiency based on profit constraint, which aim to maximize the total profit and (or) minimize the total pollution. The proposed measures are used to evaluate the output allocative efficiencies of 32 paper mills along the Huai River in China, and different parameters are tested with sensitivity analysis to examine the changes of optimal output combination. This chapter helps the enterprise to optimize the decision of production and helps the government to formulate a reasonable plan of pollution control and treatment.
This chapter presents a data envelopment analysis (DEA) based relative financial strength (RFS) indicator using accounting data that is predictive of stock market performance of public firms. Such an indicator is indispensable in the fundamental analysis of firms for stock portfolio selections. This methodology requires optimally configuring inputs and outputs for the DEA model such that the strength indicator is maximally correlated with observed stock returns. This optimized RFS indicator providing the maximum predictive strength of stock returns is determined by factors such as asset utilization, leverage, profitability, and growth rates, in addition to the well-known factor, book-to-market ratio. Computational evidence is provided using more than 800 firms covering all major sectors of the U.S. stock market. Using quarterly financial data, we employ the RFS indicator to devise portfolios that yield superior financial performance relative to using portfolios of sector-based funds.
An area of increasing importance has been the use of quality measures in the study of health care. One specific application involves the performance of nursing homes. Previous studies using data envelopment analysis (DEA) methodology to study this problem have revealed several problems, including the selection of quality output measures and the assignment of weights to these measures that result in minimizing their impact. In this chapter, we will use weight restrictions as an effective means of including important quality measures in the DEA model and allowing the DEA results to discriminate among high- and low-quality performing nursing homes.
In this chapter, we illustrate the use of data envelopment analysis, an operations research technique, to analyze the financial performance of the seven largest retailers in the United States by benchmarking a set of financial ratios of a firm against its peers. Data envelopment analysis clearly brings out the firms that are operating more efficiently in comparison to other firms in the industry, and points out the areas in which poorly performing firms need to improve.
The Philippine health care system is comprised of both private and public hospitals, clinics, and health care providers, and public health units serve a huge majority of the population because of their number and accessibility to more people in terms of price and location. It is therefore important to examine the performance of these public health units and see if they could become more efficient in the delivery of health services. This study will apply data envelopment analysis (DEA) to assess the efficiency of provinces in providing health care services in order to assist the Department of Health in identifying the performance level of each province, determining the targets for improvements in securing benefits and using resources, and identifying the peers of provinces in the delivery of health care. The data used in this study are taken from the Field Health Service Information System and Philippine Health Insurance System of the Department of the Health and the Statement of Income and Expenditure of the Department of Finance. The following programs were analyzed in this study: Maternal Health Care, Child Health Care, and Environmental Sanitation. These programs’ outcomes comprise the percentage of the prevalence of contraceptive use and fully immunized children, for maternal and child health care programs; and the percentage of people who have access to potable water and sanitary toilets, for environmental sanitation. As for inputs, expenditure efficiency is analyzed by the health unit budget per capita and technical efficiency includes the number of doctors and midwives per 100,000 population and the percentage of rural health units accredited by the Philippine Health Insurance Corporation. The DEA results for efficiency expenditure shows that only 9 out of 77 provinces are efficient in providing health programs given their budgets and the average input efficiency score is 54 percent and the average output efficiency score is 87 percent. As for the DEA results for technical efficiency, 24 out of 77 provinces are efficient in providing health care programs given the percentage number of doctors, midwives, and accredited health facilities by the Philippine Health Insurance Corporation. The average input efficiency score is 79 percent and the average output efficiency score is 80 percent. This study has shown the importance of DEA in analyzing the efficiency of delivery of public health services in provinces using expenditure, number of available health care providers, and the presence of accredited rural health units vis-à-vis environmental sanitation and maternal and child health care programs. DEA can rationalize the allocation of budgets among similar health units in order to further improve the efficiency in the delivery of health services in provinces. Moreover, benchmarking using DEA results can improve the accountability of provincial health units in the utilization of their budgets in order to further increase the reach of province-based health programs which could lead to a marked improvement in the health of Filipinos.
As a Data Envelopment Analysis (DEA) extension tool, cross-evaluation method was developed to evaluate Decision Making Units’ (DMUs) performances in a competitive situation with limited demand. It identifies DMUs with best performances and rank them by applying peer evaluation mode instead of self-evaluation mode. However, it has limitations in efficiency improvement. That is, it fails to give direct information on how to improve efficiencies of the inefficient DMUs. In this chapter, we propose an alternative way to apply cross-evaluation in efficiency improvement. First, an appropriate and feasible suggestion is proposed to minimize the variation between the weights of a DMU's own optimal Charnes-Cooper-Rhodes (CCR) efficiency and the weights guaranteeing its cross-efficiency score. We exploit several transformations to convert nonlinear programming into a linear one. As a result, an overall optimal set of the weights is obtained, which precisely illustrate the preferences of decision makers and exact characteristics of production process of the evaluated DMU. A further discussion is advanced to examine the existence of non-uniqueness of the weights and to differentiate various sets of the optimal weights by suggesting a unique feasible set of multipliers to best represent the alternative weights selection criterion. Moreover, we develop several models to reallocate the inputs and outputs of inefficient DMUs with minimum amelioration as well as consideration of the preference of decision makers. Finally, we apply our models to evaluate competitive advantages of Chinese cities.
This chapter investigates the financial performance and technical efficiency of the 26 listed firms in the services sector of the Philippine Stock Exchange over the period 1998–2007, using the DuPont system and the super-efficiency data envelopment analysis (SE-DEA). Empirical findings revealed a negative return on equity for the sector and the presence of outliers in the sample. We also verified a robust significant association between the financial and technical performances of the sector.
The chapter offers new significant contributions to knowledge in terms of the multidimensional performance evaluation and the efficiency of the stock market, especially in developing economies, which has not been a well-researched area. Managerial implications are also identified for the improvement of the firms’ management and the usefulness of the SE-DEA model in performance management.
We apply data envelopment analysis to compare the relative efficiency of different forms of microfinance institutions (MFIs): banks, cooperatives, nongovernmental organizations (NGOs), and nonbank financial institutions. We find that MFIs that operate as NGOs are technically more efficient than bank MFIs. Using the same inputs (labor and physical and financial assets), NGOs serve more clients (number of borrowers or depositors) than bank MFIs.