Gary D. Ferrier

Consistency Conditions for Regulatory Analysis of Financial Institutions: A Comparison of Frontier Efficiency Methods

We propose a set of consistency conditions that frontier efficiency measures should meet to be most useful for regulatory analysis or other purposes. The efficiency estimates should be consistent in their efficiency levels, rankings, and identification of best and worst firms, consistent over time and with competitive conditions in the market, and consistent with standard nonfrontier measures of performance. We provide evidence on these conditions by evaluating and comparing efficiency estimates on U.S. bank efficiency from variants of all four of the major approaches -- DEA, SFA, TFA, and DFA -- and find mixed results.

Original ArticlesConsistency Conditions for Regulatory Analysis of Financial Institutions: A Comparison of Frontier Efficiency Methods

We propose a set of consistency conditions that frontier efficiency measures should meet to be most useful for regulatory analysis or other purposes. The efficiency estimates should be consistent in their efficiency levels, rankings, and identification of best and worst firms, consistent over time and with competitive conditions in the market, and consistent with standard nonfrontier measures of performance. We provide evidence on these conditions by evaluating and comparing efficiency estimates on U.S. bank efficiency from variants of all four of the major approaches -- DEA, SFA, TFA, and DFA -- and find mixed results.

Economies of diversification in the banking industry : A frontier approach

Abstract This paper defines a new measure, economies of diversification, to examine the cost effect of product line expansion. This measure is a special case of expansion path subadditivity and contains economies of scope as a special case. A nonparametric frontier technique which isolates the effects of inefficiency and scale is used to measure economies of diversification. Applied to a set of 468 U.S. depository institutions operating in 1984, we find slight diseconomies of diversification. Diseconomies of diversification and inefficiency due to the overutilization of resources are found to be more important determinants of bank costs than is the failure to operate at optimal scale.

Rural hospital performance and its correlates

The cost, technical, allocative and scale efficiencies of a sample of rural U.S. hospitals are calculated via linear programming models. Tobit analysis is used to assess possible correlates of each of the efficiency measures. A large amount of dispersion in operating efficiency is found within our data set; the majority of the dispersion is due to technical inefficiency. In general, for-profit hospitals are found to outperform not-for-profit and public hospitals. Demand characteristics, quality of care, and the mix of services offered are also found to influence performance.

Bootstrapping Confidence Intervals for Linear Programming Efficiency Scores: With an Illustration Using Italian Banking Data

This article suggests a method for introducing a stochastic element into Farrell measures of technical efficiency as calculated via linear programming techniques. Specifically, a bootstrap of the original efficiency scores is performed to derive confidence intervals and a measure of bias for the scores. The bootstrap generates these measures of statistical precision for the “nonstochastic” efficiency measures by using computational power to derive empirical distributions for the efficiency measures.

Comparing French and US hospital technologies: a directional input distance function approach

French and US hospital technologies are compared using directional input distance functions. The aggregation properties of the directional distance function allow comparison of hospital industry-level performance as well as standard firm-level performance with regard to productive efficiency. In addition, the underlying constituents of efficiency – in the short run, congestion and technical inefficiency, and in the long run, scale inefficiency – are analysed by decomposing the overall measure. By virtue of using the directional distance function, it is also possible to obtain an estimate of a lower bound on allocative inefficiency. It is found that French and US hospitals use quite different technologies. Long run scale inefficiencies cause most of the French hospitals’ inefficiency, while short run technical inefficiency is the main source of overall productive inefficiency in the US hospitals.

Radial and Nonradial Technical Efficiency Measures on a DEA Reference Technology : A Comparison using US Banking Data

Technical efficiency measures can be classified as either radial or nonradial. While the theoretical question of which is the better type of measure is unresolved, the radial measures enjoy much greater popularity than the nonradial measures in the empirical literature. To assess the impact of choice of measure, this paper offers an empirical comparison of one radial and three nonradial measures of technical efficiency, relative to a variable returns to scale DEA model with strong disposability. The distributions and rankings of these efficiency scores are examined for a sample of US banks, as is the ability of the radial efficiency measure to approximate its nonradial alternatives.

The technical efficiency of vacuum-pan sugar industry of India: An application of a stochastic frontier production function using panel data

Abstract A stochastic production frontier method is used to examine technical efficiency among Indian vacuum-pan sugar factories over a five-year period. Most factories are close to Indian best practice in terms of technical efficiency. Smaller firms and firms with access to sweeter cane are likely to be more efficient than other firms, while publicly owned firms are less efficient. There are transitory positive effects of a long crushing season on technical efficiency.

Can We Bootstrap DEA Scores

This paper discusses the feasibility of bootstrapping DEA scores in the context of the earlier paper by Ferrier and Hirschberg (1997). A simple experiment is devised to demonstrate that in the one-input, one-output case the bootstrap of the non-modified DEA scores is not a failure of the bootstrap.

Predicting retailer orders with POS and order data: The inventory balance effect

Despite advances in retail point-of-sale (POS) data sharing, retailers’ suppliers struggle to effectively use POS data to improve their fulfillment planning processes. The challenge lies in predicting retailer orders. We present evidence that retail echelon inventory processes translate into a long-run balance or equilibrium between orders and POS, which we refer to as the inventory balance effect, allowing for more accurate order forecasting. Based on the inventory balance effect, this research prescribes a forecasting approach which simultaneously uses both sources of information (retailer order history and POS data) to predict retailer orders to suppliers. Using data from a consumable product category, this approach is shown to outperform approaches based singularly on order or POS data, by up to 125%. The strength of this novel approach – significantly improved forecast accuracy with minimal additional analysis – make it a candidate for widespread adoption in retail supply chain collaborative planning and forecasting initiatives with corresponding impact on fulfillment performance and related operating costs.