Parametric Frontier Research Articles

Comparison of data envelopment analysis and deterministic parametric frontier approaches: an application in the Norwegian road construction sector

This paper analyzes efficiency in the Norwegian road sector by using two competing methods. The first is Data Envelopment Analysis (DEA), while the second is Deterministic Frontier Analysis (DFA) with a Cobb‐Douglas kernel specification. Both approaches show similarities with respect to efficiency distribution. The rock‐blasting sectors potential for efficiency improvement is in the range 19–59 percent. Both approaches demonstrate decreasing return to scale properties for the average unit. There is a significant correlation between size and efficiency indicating that larger units perform better than smaller ones. Precautionary blasting mainly performed in densely populated areas is also found to explain much of the variations in efficiency scores. Any policy implication should therefore carefully examine exogenous factors. The main difference between the two approaches, which can be explained by the number of parameters to be determined, concerns level of scores rather than their distribution. However, there are arguments that advocate DEA rather than DFA in the rock‐blasting sector.

Productivity change model in the airline industry: A parametric approach

In this paper we construct a general model of the airline competition that incorporates the main variables discussed in different models of the quality of airlines competition. The model is applied to data on the domestic airlines in the Republic of Indonesia, which consists of six airlines. Although we find little evidence in support of endogenous variables, it seems that the estimated variables of all airlines are consistent with the notion that the market shares of the airlines are positively related to the main variables. The parameter results represent weights, which describe the number of appearances in the facet for each particular airline. Then, we attempt to introduce a goal programming model with constraints that are developed for estimating the parametric frontiers using translog form, and the coefficient of its objective function using the above parameter results of an airline competition model. The objective of this paper is to propose a methodology that decomposes total factor productivity change into technological progress and change in technical efficiency. The analysis of methodology provides a useful illustration of the productivity change in the airline industry.

Efficiency of government-supported horticulture: the case of Oman

This paper analyzes technical efficiency in Oman using the stochastic production frontier and the data envelopment analysis (DEA) methods. Different methods are used because the determinants of technical efficiency may be influenced by the method used and also by the assumptions (such as returns to scale) maintained. Results from the stochastic parametric frontier (SPF) and DEA–Charnes, Cooper, Rhodes (CCR) models show that the percentage of farmers that could qualify as technically efficient is as low as 17%. When the DEA–Banker, Charnes, Cooper (BCC) method was used, this percentage increased to about 46%. Factors such as off-farm income and soil quality were found to be positively correlated to productivity. On the other hand, small farm size and farmer's age showed a negative relationship with productivity.

A comparison of parametric and non-parametric distance functions: With application to European railways

In this paper we use multi-output distance functions to investigate technical inefficiency in European railways. The principle aim of the paper is to compare the results obtained from the three alternative methods of estimating multi-output distance functions. Namely, the construction of a parametric frontier using linear programming; data envelopment analysis (DEA) and corrected ordinary least squares (COLS). Input-orientated, output-orientated and constant returns to scale (CRS) distance functions are estimated and compared. The results indicate a strong degree of correlation between the input- and output-orientated results for each of the three methods. There are also significant correlations observed between the results obtained using the alternative estimation methods. The strongest correlations being between the parametric linear programming and the COLS methods. Finally, the paper concludes with the suggestion that a combination of the technical efficiency scores, obtained from the three different methods, be used as the preferred set of scores. This idea is borrowed from the time-series forecasting literature.

Cost efficiency of Belgian local governments: A comparative analysis of FDH, DEA, and econometric approaches

The purpose of this paper is to analyze the efficiency of local governments in Belgium using a broad variety of non-parametric and parametric reference technologies. Specifically, we calculate indices of cost efficiency for five different reference technologies, two non-parametric ones (Free Disposal Hull (FDH) and variable returns to scale Data Envelopment Analysis (DEA)) and three parametric frontiers (one deterministic and two stochastic). We first compare the various alternatives in terms of the efficiency-inefficiency dichotomy, we look at the distributions of the different measures, and we consider the differences in ranking. In a final stage we examine the degree to which the calculated inefficiencies can be explained by a common set of explanatory variables.

Robustly efficient parametric frontiers via Multiplicative DEA for domestic and international operations of the Latin American airline industry

Previous studies of (parametric) aggregate frontiers have attempted to capture stochastic features of the random variables (i.e. inputs and outputs) by assuming a ‘risk’ situation (where the probability distributions of the random variables are known). The purpose of this paper is to present and test a new method invented by Charnes, Semple, Song and Thomas for the usual situations of uncertainty (where the probability distributions of the random variables involved in the technical inefficiencies are unknown) to build up global efficient production functions in the context of operations in the Latin American airline industry. This method develops an empirical efficient production function via a ‘Robustly Efficient Parametric Frontier’ (REPF) in a two-stage approach. As in the Charnes et al. development using a Multiplicative-DEA model, the marginal tradeoffs of the efficient production function are immediately available instead of being harassed by discontinuities of derivatives and numerical instabilities.

Estimating total factor productivity using parametric, nonstochastic cost frontiers

The standard approach to measuring total factor productivity can produce biased results if the data are drawn from a market that is not in long-run competititve equilibrium. This article presents a methodology for adjusting data on output and variable inputs to the values they would have if the market were in long-run competitive equilibrium, given the fixed inputs and input prices. The method uses nonstochastic, parametric translog cost frontiers and calculates equilibrium values for output and varible inputs using an iterative linear programming procedure. Data from seven industries for 1970–1979 are used to illustrate the methodology.

Measurement of Productivity Improvements: An Empirical Analysis

In this paper, we test for productivity gains resulting from the introduction of a productivity-based incentive program in a large manufacturing plant of a Fortune 500 corporation. We develop a methodology based on a stochastic nonparametric frontier estimation technique to evaluate productivity in the postincentive plan period relative to the pre-incentive plan period. We also test for productivity gains using stochastic parametric frontier approaches. The results of both the nonparametric and parametric stochastic frontier analyses indicate that the incentive program has a positive effect on indirect labor, manufacturing services, and materials productivity and relatively little effect on direct labor productivity.