184,707 research outputs found
Calculating the scale elasticity in DEA models.
No full textIn economics scale properties of a production function is charcterised by the value of the scale elasticity. In the field of efficiency studies this is also a valid approach for the frontier production function. It has no good meaning to talk about scale properties of inefficient observations. In the DEA literature a qualitative characterisation is most common. The contribution of the paper is to apply the concept of scale elasticity from multi output production theory in economics to the piecewise linear frontier production function, and to develop formulas for calculating values of the scale elasticity for radial projections of inefficient observations. Illustrations also on real data are provided, showing the differences between scale elasticity values for the input- and output oriented projections and the range of values for efficient observations.Scale elasticity; DEA, production theory; Farrell efficiency measures
Multi-level DEA Approach in Research Evaluation
No full textIt is well known that the discrimination power of DEA models will be
diminishing if too many inputs or outputs are used. It is a dilemma if the decision makers
want to select comprehensive indicators to present a relatively holistic evaluation using
DEA. In this work we show that by utilizing hierarchical structures of input-output data
DEA can handle quite large numbers of inputs and outputs. We present two approaches in a
pilot evaluation of 15 institutes for basic research in Chinese Academy of Sciences using
DEA models
Fractional regression models for second stage DEA efficiency analyses
No full textData envelopment analysis (DEA) is commonly used to measure the relative efficiency of decision-making units. Often, in a second stage, a regression model is estimated to relate DEA efficiency scores to exogenous factors. In this paper, we argue that the traditional linear or tobit approaches to second-stage DEA analysis do not constitute a reasonable data-generating process for DEA scores. Under the assumption that DEA scores can be treated as descriptive measures of the relative performance of units in the sample, we show that using fractional regression models are the most natural way of modeling bounded, proportional response variables such as DEA scores. We also propose generalizations of these models and, given that DEA scores take frequently the value of unity, examine the use of two-part models in this framework. Several tests suitable for assessing the specification of each alternative model are also discussed.Second-stage DEA; Fractional data; Specification tests; One outcomes; Two-part models.
Indices of innovation: application of Data Envelopment Analysis and Malmquist Index Analysis in the assessment of R&D efficiency in R&D-critical sectors
No full textMaintaining or increasing R&D efficiency and productivity is a constant challenge for R&D-driven businesses, and companies in these sectors often explore strategies seen be effective in related sectors, for example the adoption of ‘open’ innovation by the pharmaceutical sector, based on its observed success in the information technology sector as reported by Chesbrough. The papers in this thesis address two gaps in the research literature: (1) the relative lack of established quantitative measures of the performance of open or other innovation strategies, and (2) the continuing challenge of assessing the effectiveness or otherwise of the OI paradigm outside its original high-tech industry focus. The pharmaceutical industry has been claimed as one of the pioneering industries where the principle of OI has been applied. In view of the limitations of prior research on R&D efficiency and OI in this industry, the question of whether OI is the best or only prescription for innovation in the pharmaceutical industry remains a strategic one. The first paper in the sequence identifies and explores systematic measures of innovation by investigating the adaptation and application of DEA as a candidate technique for analysing the R&D efficiency performance, using data on China’s high-tech industry sectors. The second paper explores how such ‘indices of innovation’ could be used to measure performance in terms of changes in R&D efficiency over time, in a case study of Procter and Gamble, a company widely recognised as an early adopter of OI. The third paper builds on the first two, using DEA and MI as ‘indices of innovation’ to measure whether adopting OI is leading to increased R&D efficiency in the pharmaceutical sector. Taken together, these papers explore (a) the feasibility if DEA and MI as new quantitative econometric ‘indices of innovation’, (b) their correlation with a known case of open innovation, and (c) to test the hypothesis that open innovation is increasing R&D efficiency in the pharmaceutical industr
Extended Utility and DEA Models without Explicit Input
No full textIn this paper, we discuss the relationship between multi-attribute utility theory and data envelopment analysis (DEA) models without explicit inputs (DEA-WEI), including dual models and some theoretical analysis of DEA-WEI models. We then propose generic DEA-WEI models with quadratic utility terms. Finally, we provide illustrative examples to show that DEA-WEI with suitable quadratic utility terms are able to reflect some value judgments that the standard DEA models cannot
Stochastic Nonparametric Envelopment of Data: Combining Virtues of SFA and DEA in a Unified Framework
No full textThe literature of productive efficiency analysis is divided into two main branches: the parametric Stochastic Frontier Analysis (SFA) and nonparametric Data Envelopment Analysis (DEA). This paper attempts to combine the virtues of both approaches in a unified framework. We follow the SFA literature and introduce a stochastic component decomposed into idiosyncratic error and technical inefficiency components imposing the standard SFA assumptions. In contrast to the SFA, we do not make any prior assumptions about the functional form of the deterministic production function. In this respect, we follow the nonparametric route of DEA that only imposes free disposability, convexity, and some specification of returns to scale. From the postulated class of production functions, the proposed method identifies the production function with the best empirical fit to the data. The resulting function will always take a piece-wise linear form analogous to the DEA frontiers. We discuss the practical implementation of the method and illustrate its potential by means empirical examples.Productivity Analysis,
Efficiency of public spending in support of R&D activities
No full textThis study provides an empirical assessment of the level of efficiency of public R&D spending and public R&D support for private R&D. This study aims at assessing the level of efficiency of public R&D spending and public R&D support for private R&D and to compare efficiency scores among OECD countries, in particular EU Member states over the past two decades. The analysis rests on the concept of efficiency which is based on the relationship between public R&D spending and the additional R&D in the business sector induced by such measures.Public, private R&D, (determinants of) efficiency, framework conditions, SFA, DEA.
The use of supply chain DEA models in operations management: A survey
No full textStandard Data Envelopment Analysis (DEA) approach is used to evaluate the efficiency of DMUs and treats its internal structures as a “black box”. The aim of this paper is twofold. The first task is to survey and classify supply chain DEA models which investigate these internal structures. The second aim is to point out the significance of these models for the decision maker of a supply chain. We analyze the simple case of these models which is the two-stage models and a few more general models such as network DEA models. Furthermore, we study some variations of these models such as models with only intermediate measures between first and second stage and models with exogenous inputs in the second stage. We define four categories: typical, relational, network and game theoretic DEA models. We present each category along with its mathematical formulations, main applications and possible connections with other categories. Finally, we present some concluding remarks and opportunities for future research.Supply chain; Data envelopment analysis; Two-stage structures; Network structures
Inferring the Latent Incidence of Inefficiency from DEA Estimates and Bayesian Priors
No full textData envelopment analysis (DEA) is among the most popular empirical tools for measuring cost and productive efficiency. Because DEA is a linear programming technique, establishing formal statistical properties for outcomes is difficult. We show that the incidence of inefficiency within a population of Decision Making Units (DMUs) is a latent variable, with DEA outcomes providing only noisy sample-based categorizations of inefficiency. We then use a Bayesian approach to infer an appropriate posterior distribution for the incidence of inefficient DMUs based on a random sample of DEA outcomes and a prior distribution on the incidence of inefficiency. The methodology applies to both finite and infinite populations, and to sampling DMUs with and without replacement, and accounts for the noise in the DEA characterization of inefficiency within a coherent Bayesian approach to the problem. The result is an appropriately up-scaled, noise-adjusted inference regarding the incidence of inefficiency in a population of DMUs.Data Envelopment Analysis, latent inefficiency, Bayesian inference,Beta priors, posterior incidence of inefficiency
Sensitivity analysis of network DEA illustrated in branch banking
No full textUsers of data envelopment analysis (DEA) often presume efficiency estimates to be robust. While traditional DEA has been exposed to various sensitivity studies, network DEA (NDEA) has so far escaped similar scrutiny. Thus, there is a need to investigate the sensitivity of NDEA, further compounded by the recent attention it has been receiving in literature. NDEA captures the underlying performance information found in a firm?s interacting divisions or sub-processes that would otherwise remain unknown. Furthermore, network efficiency estimates that account for divisional interactions are more representative of a dynamic business. Following various data perturbations overall findings indicate positive and significant rank correlations when new results are compared against baseline results - suggesting resilience. Key findings show that, (a) as in traditional DEA, greater sample size brings greater discrimination, (b) removing a relevant input improves discrimination, (c) introducing an extraneous input leads to a moderate loss of discrimination, (d) simultaneously adjusting data in opposite directions for inefficient versus efficient branches shows a mostly stable NDEA, (e) swapping divisional weights produces a substantial drop in discrimination, (f) stacking perturbations has the greatest impact on efficiency estimates with substantial loss of discrimination, and (g) layering suggests that the core inefficient cohort is resilient against omission of benchmark branches. Various managerial implications that follow from empirical findings are discussed in conclusions.
- …
