Showing papers in "Journal of Productivity Analysis in 2003"
TL;DR: This paper summarizes the main results of Cazals et al. (2002) on robust nonparametric frontier estimators and proposes a methodology implementing the tool and shows how this tool can be used for detecting outliers when using the classical DEA/FDH estimators or any parametric techniques.
Abstract: In frontier analysis, most of the nonparametric approaches (DEA, FDH) are based on envelopment ideas which suppose that with probability one, all the observed units belong to the attainable set. In these "deterministic'' frontier models, statistical theory is now mostly available (Simar and Wilson, 2000a). In the presence of superefficient outliers, envelopment estimators could behave dramatically since they are very sensitive to extreme observations. Some recent results from Cazals et al. (2002) on robust nonparametric frontier estimators may be used in order to detect outliers by de. ning a new DEA/FDH "deterministic'' type estimator which does not envelop all the data points and so is more robust to extreme data points. In this paper, we summarize the main results of Cazals et al. (2002) and we show how this tool can be used for detecting outliers when using the classical DEA/FDH estimators or any parametric techniques. We propose a methodology implementing the tool and we illustrate through some numerical examples with simulated and real data. The method should be used in a first step, as an exploratory data analysis, before using any frontier estimation.
356 citations
TL;DR: In this article, the authors use DEA to model DMUs that produce in two stages, with output from the first stage becoming input to the second stage, and apply the model to Major League Baseball, demonstrating its advantages over a standard DEA model.
Abstract: We show how to use DEA to model DMUs that produce in two stages, with output from the first stage becoming input to the second stage. Our model allows for any orientation or scale assumption. We apply the model to Major League Baseball, demonstrating its advantages over a standard DEA model. Our model detects inefficiencies that standard DEA models miss, and it can allow for resource consumption that the standard DEA model counts towards inefficiency. Additionally, our model distinguishes inefficiency in the first stage from that in the second stage, allowing managers to target inefficient stages of the production process.
323 citations
TL;DR: In this article, the authors evaluate alternative decompositions of the partially oriented Malmquist productivity index, and obtain a new decomposition of the simultaneously oriented one, which leads them to conclude that the latter index is deserving of greater attention than it has received to date.
Abstract: Two different Malmquist productivity indexes have been proposed. One I call partially oriented because it is either output- or input-oriented, and the other is simultaneously output- and input-oriented. The partially oriented Malmquist index owes some of its popularity to the fact that it has been decomposed to isolate various sources of productivity change. Conversely, the simultaneously oriented Malmquist index has not achieved popularity in part because it has not been decomposed. In this paper I evaluate alternative decompositions of the partially oriented Malmquist index, and I obtain a new decomposition of the simultaneously oriented Malmquist index. This new decomposition leads me to conclude that the latter index is deserving of greater attention than it has received to date.
318 citations
TL;DR: In this paper, data envelopment analysis (DEA) is extended to a dynamic framework so that investment behavior can be modelled with the efficient production frontier, based on the work of Nemoto and Goto.
Abstract: The purpose of this paper is to measure productive efficiencies when a firm employs quasi-fixed inputs that cannot be instantaneously adjusted to their optimal levels. To this end, data envelopment analysis (DEA) is extended to a dynamic framework so that investment behavior can be modelled with the efficient production frontier. Based on the work of Nemoto and Goto (1999), we show how the efficiencies of quasi-fixed inputs and their adjustment processes are evaluated. An application to Japanese electric utilities over the 1981–1995 period delivers empirically plausible results and proves the usefulness of the procedure.
229 citations
TL;DR: A brief history of the Malmquist productivity index and its decomposition is given in this paper, along with theoretical and empirical issues related to the index along with directions for future research.
Abstract: This paper provides a brief history of the Malmquist productivity index and its decomposition. Theoretical and empirical issues related to the index are discussed along with directions for future research.
213 citations
TL;DR: This paper focuses on non-oriented efficiency measures (which assume that production units are able to control, and thus change, inputs and outputs simultaneously) both measured in relation to a Free Disposal Hull (FDH) technology and in connection to a convex technology.
Abstract: This paper draws attention for the fact that traditional Data Envelopment Analysis (DEA) models do not provide the closest possible targets (or peers) to inefficient units, and presents a procedure to obtain such targets. It focuses on non-oriented efficiency measures (which assume that production units are able to control, and thus change, inputs and outputs simultaneously) both measured in relation to a Free Disposal Hull (FDH) technology and in relation to a convex technology. The approaches developed for finding close targets are applied to a sample of Portuguese bank branches.
168 citations
TL;DR: In this paper, the authors apply both the standard DEA methodology with contemporaneous frontiers and DEA with sequential frontiers to study changes in productivity and efficiency in manufacturing for a sample of eleven OECD countries over a twenty-year period.
Abstract: The paper applies both the standard DEA methodology with contemporaneous frontiers and DEA with sequential frontiers to study changes in productivity and efficiency in manufacturing for a sample of eleven OECD countries over a twenty-year period. It uses a decomposition of the industrial Malmquist productivity indices to locate the sources of productivity growth: 'technical progress' and 'catching up.' The alternative indices are interrelated in a unifying framework that provides an interpretation to their difference. We argue that for manufacturing industries, in which technological regress is unlikely to occur, DEA with sequential frontiers provides a more adequate measure for the contribution of technical changes than standard DEA.
146 citations
TL;DR: In this paper, a nonparametric dynamic dual cost approach to production analysis is developed, which recovers technological information from intertemporal cost minimizing behavior without imposing a parametric functional form on the firm's technology.
Abstract: While the dynamic theory of production provides little insight towards identifying a specific functional form for the firm's technology, dynamic production analysis has been explored traditionally in a parametric framework. A nonparametric dynamic dual cost approach to production analysis is developed in this article. Recovering technological information from intertemporal cost minimizing behavior is possible without imposing a parametric functional form on the firm's technology. Nonparametric tests to analyze the structure of a dynamic technology are presented from a dynamic cost minimizing perspective. The empirical implementation of these tests is illustrated for a balanced panel data set of Pennsylvania dairy operators during the time period 1986–1992.
115 citations
TL;DR: The normal-gamma stochastic frontier model was proposed in Greene and Beckers and Hammond (1987) as an extension of the normal-exponential model as mentioned in this paper, which has the virtue of providing a richer and more flexible parameterization of the inefficiency distribution than either of the canonical forms, normal-half normal and normalexponential.
Abstract: The normal-gamma stochastic frontier model was proposed in Greene (1990) and Beckers and Hammond (1987) as an extension of the normal-exponential proposed in the original derivations of the stochastic frontier by Aigner, Lovell and Schmidt (1977). The normal-gamma model has the virtue of providing a richer and more flexible parameterization of the inefficiency distribution in the stochastic frontier model than either of the canonical forms, normal-half normal and normal-exponential. However, several attempts to operationalize the normal-gamma model have met with very limited success, as the log likelihood is possesed of a significant degree of complexity. This note will propose an alternative approach to estimation of this model based on the method of maximum simulated likelihood estimation as opposed to the received attempts which have approached the problem by direct maximization.
115 citations
TL;DR: In this paper, the authors analyzed the determinants of ICT investment and the impact of information technology on productivity and efficiency on a representative sample of small and medium sized Italian firms.
Abstract: We analyze the determinants of ICT investment and the impact of information technology on productivity and efficiency on a representative sample of small and medium sized Italian firms. In order to test the most relevant theoretical predictions from the ICT literature we evaluate the impact of investment in software, hardware and telecommunications of these firms on a series of intermediate variables and on productivity. Among intermediate variables we consider the demand for skilled workers, the introduction of new products and processes and the rate of capacity utilization. Among productivity measures we include total factor productivity, the productivity of labor, and the distance from the “best practice” by using a stochastic frontier approach. Our results show that the effect of ICT investment on firm efficiency can be more clearly detected at firm level data by decomposing it into software and telecommunications investment. We find that telecommunications investment positively affects the creation of new products and processes, while software investment increases the demand for skilled workers, average labor productivity and proximity to the optimal production frontier. We interpret these results by arguing that ICT investment modifies the trade-off between scale and scope economies. While software investment increases the scale of firm operations, telecommunications investment creates a “flexibility option” easing the switch from a Fordist to a flexible network productive model in which products and processes are more frequently adapted to satisfy consumers’ taste for variety.
110 citations
TL;DR: In this paper, the authors discuss the basic accounting model as well as the various measurement problems one gets involved in, and a number of methods for decomposing productivity change and productivity differences, whether at the individual firm level or at aggregate level, into partial measures relating to technological change and efficiency change.
Abstract: Productivity is an important component of profitability, and therefore an important variable for monitoring and benchmarking exercises. This survey discusses the basic accounting model as well as the various measurement problems one gets involved in. By virtue of its structural features, this model is applicable to individual firms and aggregates such as industries or economies.Though the measurement of productivity change and productivity differences is important, still more important is their explanation. Thus, first, this article reviews recent results relating to the decomposition of aggregate productivity change into components due to firm dynamics and intra-firm productivity change, results which were obtained by studying longitudinal enterprise microdata sets. Second, this article reviews a number of methods for decomposing productivity change and productivity differences, whether at the individual firm level or at aggregate level, into partial measures relating to technological change and efficiency change. The combination of both research strategies seems to be a promising undertaking.
TL;DR: In this paper, a decomposition of the facet generation process followed by the use of one of the available (exponential) convex hull algorithms allows for an explicit identification of the facial structure of the possibility set in fairly large DEA data sets.
Abstract: This paper provides an outline of possible uses of complete information on the facial structure of a polyhedral empirical production possibility set obtained by DEA. It is argued that an identification of all facets can be used for a characterization of basic properties of the empirical production frontier. Focus is on the use of this type of information for (i) the specification of constraints on the virtual multipliers in a cone-ratio model, (ii) a characterization of the data generation process for the underlying observed data set, and (iii) the estimation of isoquants and relevant elasticities of substitution reflecting the curvature of the frontier. The relationship between the so-called FDEF approach and the cone-ratio model is explored in some detail. It is demonstrated that a decomposition of the facet generation process followed by the use of one of the available (exponential) convex hull algorithms allows for an explicit identification of the facial structure of the possibility set in fairly large DEA data sets. It is a main point to be made that the difficulties encountered for an identification of all facets in a DEA-possibility set can be circumvented in a number of empirical data sets and that this type of information can be used for a characterization of the structural properties of the frontier.
TL;DR: In this article, the authors explored the definitions and properties of total factor productivity growth (TFPG) indexes, focusing especially on the Paasche, Laspeyres, Fisher, and implicit Tornqvist ones.
Abstract: This paper explores the definitions and properties of total factor productivity growth (TFPG) indexes, focusing especially on the Paasche, Laspeyres, Fisher, Tornqvist, and implicit Tornqvist ones. These indexes can be evaluated from observable price and quantity data, and certain of these are shown to be measures of TFPG concepts and theoretical indexes that have been proposed in the literature. The mathematical relationships between these and quantity aggregates, financial measures, and price and quantity indexes are explored. Decompositions of the productivity growth indexes are also given. The paper concludes with a brief overview of some limitations on our analysis.
TL;DR: In this paper, the potential improvements inefficiency index is reexamined and a DEA-like approach for its determination is suggested, called Multi-directional Efficiency Analysis (MEA).
Abstract: In a recent paper Bogetoft and Hougaard (1999) suggest the use of a new potential improvements approach to efficiency evaluation which has the advantage of separating the issue of benchmark selection from the issue of efficiency measurement. In the present paper the potential improvements inefficiency index is reexamined and a DEA-like approach for its determination is suggested. The approach is called Multi-directional Efficiency Analysis (MEA). An empirical example on Danish dairy farms is used for illustrative purposes and comparisons with various versions of DEA.
TL;DR: In this article, the role of convexity in duality theory is asymmetric and non-convexity should not stop one from applying the Duality Theory, and the authors discuss two alternative approaches: recovering inexact outer-bound approximations; and enriching standard economic models by additional quantity/financial constraints.
Abstract: Duality Theory of production imposes a number of simplifying assumptions regarding the production technology, including various maintained convexity assumptions. Emphasizing the technological information content of alternative models, this paper challenges some widely held views on the role of convexity. The role of convexity in Duality Theory is asymmetric. While convexity is of importance in recovering technology information from economic models, cost functions are concave and profit functions are convex irrespective of convexity of the underlying technology. For recovering technology information from economic models and data, we discuss two alternative approaches: recovering inexact outer-bound approximations; and enriching standard economic models by additional quantity/financial constraints. The main conclusion is that non-convexities should not stop one from applying the Duality Theory.
TL;DR: In this paper, the authors adapted productivity analysis to the case of a cost model using a quadratic cost function and discrete data, and the main theoretical result is a productivity index that can be decomposed into modified versions of the contribution of technical change and the effect of the variations in the scale of production.
Abstract: In this article we have adapted productivity analysis to the case of a cost model using a quadratic cost function and discrete data. The main theoretical result is a productivity index that can be decomposed into modified versions of the contribution of technical change and the effect of the variations in the scale of production. This framework has been applied to the study of the Spanish electric sector from 1985 to 1996, during which relevant regulatory changes were introduced in order to increase productivity. For this, a normalized quadratic cost function was estimated. The results show important productivity gains with both technical change and scale effect playing important roles.
TL;DR: The results show that the use of radial projection for target setting is too restrictive, and the decision making units (DMUs) are free to choose their own target values on the efficient frontier.
Abstract: Radial projection is a standard technique applied in data envelopment analysis (DEA) to calculate efficiency scores for input and/or output variables. In this paper, we have studied the appropriateness of radial projection for target setting. We have created a situation where the decision making units (DMUs) are free to choose their own target values on the efficient frontier and then compared the results to those of radial projection. In practice, target values are primarily used for future goal attainment; hence, not only preferences but also, and on the whole, change in time frame, affect the choice of target values. Based on that, we conducted an empirical experiment with an aim to study how the DMUs choose their most preferred target values on the efficient frontier. The subjects, who all were students of the Helsinki School of Economics, were given the freedom to explore their personalized efficient frontiers by using a multiple objective linear programming (MOLP) approach. To study various and relevant scenarios, the personalized efficient frontiers for all students were constructed in such a way that the current position of each student in relation to the frontier made him/her inefficient, efficient, or super-efficient. The results show that the use of radial projection for target setting is too restrictive.
TL;DR: In this paper, the authors investigated the relation between RD and public research effort in Italian agriculture and derived plausible estimates of its internal rate of return, and the results provided interesting information about the economic structure of public research efforts.
Abstract: The search for an appropriate methodology to investigate the relation between RD the results provide interesting information about the economic structure of public research effort in Italian agriculture and plausible estimates of its internal rate of return.
TL;DR: In this paper, the authors developed a methodology for assessing the efficiency of job placement services based on the matching function and found that counseling is more effective than other active labor market measures or disciplining actions in increasing matching efficiency.
Abstract: This study develops a methodology for assessing the efficiency of job placement services based on the matching function. Unlike most previous estimates of the matching function, based on aggregate time-series regressions and parametric functional forms, this study employs micro cross-sectional data and uses nonparametric frontier estimation techniques (DEA). The methodology is applied to 126 regional placement offices operating in Switzerland in the period 1997–98. In contrast to time-series regressions, our results point to sizable increasing returns-to-scale. Our findings also suggest that counseling is more effective than other active labor market measures or disciplining actions in increasing matching efficiency.
TL;DR: In this article, nonparametric tests of independence were surveyed for non-parametric models of productive efficiency, with the independence condition implicitly assumed in Simar and Wilson (1998).
Abstract: Bootstrap methods for inference in nonparametric models of productive efficiency can be simplified, reducing computational burden, when the independence condition implicitly assumed in Simar and Wilson (1998) holds. This paper surveys nonparametric tests of independence that might be useful in this context.
TL;DR: In this paper, the authors extend the recent work by Frei and Harker on projections onto efficient frontiers (1999) in three ways: first, they provide a formal definition of the production set as the intersection of a finite number of closed halfspaces, and then they introduce a relevant weighting scheme for inputs and outputs so that the Holder distance function respects the commensurability axiom defined by Russell.
Abstract: This paper extends the recent work by Frei and Harker on projections onto efficient frontiers (1999) in three ways First, we provide a formal definition of the production set as the intersection of a finite number of closed halfspaces We emphasize the necessity of a complete enumeration of the supporting hyperplanes to define the production set properly We focus on the problem of exhaustive enumeration of the supporting hyperplanes to characterize the production set Second, we consider the problem of an arbitrary-norm projection on the boundary of the production set We use the concept of the Holder distance function and we derive the necessary mathematics to calculate distances and projections of inefficient DMUs onto the efficient frontier Third, we introduce a relevant weighting scheme for inputs and outputs so that the Holder distance function respects the commensurability axiom defined by Russell (1988) Finally, we present an illustration using the same data set as Frei and Harker (1999) to highlight some of the extensions proposed in the paper
TL;DR: Estimation of a stochastic production frontier model within a Bayesian framework to obtain the posterior distribution of single-input-oriented technical efficiency at the firm level improves the understanding of the dynamics of technical efficiency over the first years of transition in the former Soviet Union.
Abstract: We propose estimation of a stochastic production frontier model within a Bayesian framework to obtain the posterior distribution of single-input-oriented technical efficiency at the firm level. All computations are carried out using Markov chain Monte Carlo methods. The approach is illustrated by applying it to production data obtained from a survey of Ukrainian collective farms. We show that looking at the changes in single-input-oriented technical efficiency in addition to the changes in output-oriented technical efficiency improves the understanding of the dynamics of technical efficiency over the first years of transition in the former Soviet Union.
TL;DR: This research takes the initial step of evaluating system performance in a dynamic environment, by relating the factors that effect system performance to the policies that govern it by extending the concepts of the static production axioms into a dynamic realm, where inputs are not instantaneously converted into outputs.
Abstract: Realistically, organizational and/or system performance is dynamic and non-linear. However, in the efficiency literature, system performance is frequently evaluated considering linear combinations of the input/output variables and without explicitly taking into account the causes of efficiency behavior nor the dynamic behavior of systems. Policy decisions based on these results may be sub-optimized because the non-linear relationships among variables, causal relationships, and feedback mechanisms are ignored. This research takes the initial step of evaluating system performance in a dynamic environment, by relating the factors that effect system performance to the policies that govern it. To accomplish this, this paper extends the concepts of the static production axioms into a dynamic realm, where inputs are not instantaneously converted into outputs. The relationships of these new dynamic production axioms to the basic behaviors associated with system dynamics structures are explored.
TL;DR: The authors explored the recent shifts in employment arrangements away from long-term employment contracts and internal labor markets towards outside contracting of labor in OECD countries, focusing on the relationship with another important trend of the last few decades, namely the labor productivity slowdown.
Abstract: This paper explores the recent shifts in employment arrangements away from long-term employment contracts and internal labor markets towards outside contracting of labor in OECD countries. It examines the driving forces behind this phenomenon, focusing on the relationship with another important trend of the last few decades, namely the labor productivity slowdown. A comparison of U.S. and European institutional arrangements shows how very different labor markets have recently displayed similar patterns in the use of contracted out labor. This paper explains these similarities and reconciles them with very different patterns in hiring, firing, and quitting behavior observed in the two regions.
TL;DR: This paper develops a mathematical programming model for obtaining a best set of sites for planned facilities, wherein the ratio of aggregate outputs to inputs for the selected set is maximal among all possible sets that could be chosen.
Abstract: This paper develops a mathematical programming model for obtaining a best set of sites for planned facilities. The model is concerned with those situations where resource constraints are present. The specific setting for the paper involves the selection of sites for a set of retail outlets, wherein the ratio of aggregate outputs to inputs for the selected set is maximal among all possible sets that could be chosen. At the same time, the model guarantees that the only sets of stores allowable are those for which the available resources are used to the maximum extent possible.
TL;DR: In this paper, a balanced panel of data is used to estimate technical efficiency, employing a fixed-effects stochastic frontier specification for wool producers in Australia, and both point estimates and confidence intervals for technical efficiency are reported.
Abstract: A balanced panel of data is used to estimate technical efficiency, employing a fixed-effects stochastic frontier specification for wool producers in Australia. Both point estimates and confidence intervals for technical efficiency are reported. The confidence intervals are constructed using the multiple comparisons with the best (MCB) procedure of Horrace and Schmidt (1996, 2000). The confidence intervals make explicit the precision of the technical efficiency estimates and underscore the dangers of drawing inferences based solely on point estimates. Additionally, they allow identification of wool producers that are statistically efficient and those that are statistically inefficient. The data reveal at the 95% level that twenty-one of the twenty-six wool farms analyzed may be efficient.
TL;DR: In this paper, the authors overview some studies in the literature on food system economic performance, to emphasize the potential to empirically represent a more complex web of technological and market phenomena than in standard productivity analyses, to enhance the measures' interpretability and relevance for policy guidance.
Abstract: Interpreting and using productivity and efficiency measures requires establishing the determinants and implications of observed performance. This is not a simple task, however, given the complex interactions among economic entities in modern markets. Identifying and quantifying performance drivers often involves parametric estimation of models with explicit performance factors build into functions representing technology and behavior. Here I overview some such studies in the literature on food system economic performance, to emphasize the potential to empirically represent a more complex web of technological and market phenomena than in standard productivity analyses, to enhance the measures' interpretability and relevance for policy guidance.
Journal Article•
TL;DR: In this article, the authors introduce a simple, yet rich, measure of efficiency changes based on the revenue-generating-ability (RGA) principle and explain the connections between efficiency changes and the variables, such as pretax profits, interest expense, non-interest expense, profit margins, loan loss provision, and asset quality.
Abstract: This paper introduces a simple, yet rich, measure of efficiency changes based on the revenue-generating-ability (RGA) principle. Using this principle, we explain the connections between efficiency changes and the variables, such as pretax profits, interest expense, non-interest expense, profit margins, loan loss provision, and asset quality. These connections are used to explain earnings differences between small and large commercial banks.
TL;DR: This paper describes a website, http://www.etm.pdx.edu/dea/dataset/, focused on Data Envelopment Analysis and DEA researchers, which aims to provide a single resource for DEA researchers to query and assess the quality of their data.
Abstract: Website databases provide the opportunity to fundamentally change the way research and knowledge are advanced and disseminated. This paper describes a website, http://www.etm.pdx.edu/dea/dataset/, focused on Data Envelopment Analysis and DEA researchers.