Showing papers by "Andrew L. Johnson published in 2011"

One-stage estimation of the effects of operational conditions and practices on productive performance: asymptotically normal and efficient, root-n consistent StoNEZD method

Abstract: Understanding the effects of operational conditions and practices on productive efficiency can provide valuable economic and managerial insights. The conventional approach is to use a two-stage method where the efficiency estimates are regressed on contextual variables representing the operational conditions. The main problem of the two-stage approach is that it ignores the correlations between inputs and contextual variables. To address this shortcoming, we build on the recently developed regression interpretation of data envelopment analysis (DEA) to develop a new one-stage semi-nonparametric estimator that combines the nonparametric DEA-style frontier with a regression model of the contextual variables. The new method is referred to as stochastic semi-nonparametric envelopment of z variables data (StoNEZD). The StoNEZD estimator for the contextual variables is shown to be statistically consistent under less restrictive assumptions than those required by the two-stage DEA estimator. Further, the StoNEZD estimator is shown to be unbiased, asymptotically efficient, asymptotically normally distributed, and converge at the standard parametric rate of order n −1/2. Therefore, the conventional methods of statistical testing and confidence intervals apply for asymptotic inference. Finite sample performance of the proposed estimators is examined through Monte Carlo simulations.

A More Efficient Algorithm for Convex Nonparametric Least Squares

Abstract: Convex Nonparametric Least Squares (CNLS) is a nonparametric regression method that does not require a priori specification of the functional form. The CNLS problem is solved by mathematical programming techniques; however, since the CNLS problem size grows quadratically as a function of the number of observations, standard Quadratic Programming (QP) and Nonlinear Programming (NLP) algorithms are inadequate for handling large samples, and the computational burdens become significant even for relatively small samples. This study proposes a generic algorithm that improves the computational performance in small samples and is able to solve problems that are currently unattainable. A Monte Carlo simulation is performed to evaluate the performance of six variants of the proposed algorithm. These experimental results indicate that a particular variant is most efficient given the sample size and the dimensionality. The computational benefits of the new algorithm are demonstrated by an empirical application that proved insurmountable for the standard QP and NLP algorithms.

Measuring technical efficiency in sports.

Abstract: Standard economic production theory is the basis for measuring technical efficiency in sports. Using programming or regression models, efficiency is defined as the distance of a given team observat...

A decomposition of productivity change in the semiconductor manufacturing industry

Abstract: This study divides a production system into three components: production design, demand support, and operations. Efficiency is then decomposed via network data envelopment analysis and integrated into the Malmquist Productivity Index framework to develop a more detailed decomposition of productivity change. The proposed model can identify the demand effect and the identity of the root cause of technical regress. Specifically, the demand effect allows the source of technical regress to be attributed to both demand deterioration and technical regress in the production technology. An empirical study using data from 1995 to 2000 for the semiconductor manufacturing industry is presented to demonstrate and validate the proposed method. The result shows that the regress of productivity in 1997–1998 and 1999–2000 is mainly caused by demand fluctuations rather than by technical regression in production capabilities.

Aggression in Mixed Martial Arts: An Analysis of the Likelihood of Winning a Decision

Abstract: Within the last decade, mixed martial arts has become one of the most popular sports worldwide. The Ultimate Fighting Championship (UFC) is the largest and most successful organization within the industry. In the USA, however, the sport is not sanctioned in all states because some politicians view the sport as too violent. The sport consists of many fighting forms and, unlike boxing, winning a decision requires judging in multiple facets including wrestling, boxing, kick boxing, and jiu-jitsu. In this study, we estimate the likelihood of winning a decision in the UFC. Using data on individual fights, we estimate the probability of winning based on fighter characteristics. We emphasize power strikes as it relates to aggression to determine the likelihood of winning. Our results indicate that knockdowns and damage inflicted are all statistically significant determinants of winning a fight and have the largest marginal effect of influencing judge’s decisions.

Optimising the location of crossovers in conveyor-based automated material handling systems in semiconductor wafer fabs

Abstract: This research presents several heuristics to optimise the location of crossovers in a conveyor-based automated material handling system (AMHS) for a semiconductor wafer fabrication facility. The objective is to determine the location of crossovers that minimises the total cost of the expected work-in-process on the conveyor and the cost of installing and operating the AMHS with the crossovers. The proposed heuristics are integrated with a queuing-based analytical model incorporating practical hardware considerations of the AMHS, such as turntables and crossovers. To illustrate the proposed heuristics’ practical application they are applied to SEMATECH's virtual wafer fabrication facility. Experimental results demonstrate that under a wide variety of operating conditions and cost scenarios the local improvement heuristic is able to identify the optimal solution and outperform other commonly used heuristics for layout design such as genetic algorithms.

Multilateral Contracting and Prevention

Abstract: A major factor in the cost of the US healthcare system is related to the strategic behavior of system participants based on their incentives Contracts may be used to align incentives in such distributed systems We consider an insurer contracting with two agents, a consumer and a provider We focus on the trade off between ex ante moral hazard and insurance, and consider both consumer and provider incentives to solve the problem of optimal contracting in the presence of unobservable preventive efforts We consider two classes of efforts on behalf of the provider: those which would complement consumer efforts, and those which substitute with consumer efforts Our results show that the provider must be given incentives when the consumer is healthy to induce effort, and that inducing provider effort allows an insurer to save on incentives given to the consumer The insurer can save informational costs by using a multilateral contract compared to the bilateral benchmark We provide an illustrative example showing which model features affect the overall savings that the multilateral contract achieves

Scope Properties: Nonparametric Assessment, Policy Insights and Functional Estimation

Abstract: Knowledge of the production function's scope and scale properties can provide insights for firms choosing their operating strategy, policy makers considering industry structure, and analysts determining which tools are appropriate. Although scale properties and their assessment have been popular topics in the productivity literature, scope properties have received less attention. We introduce a new property, returns to scope, which is disentangled from scale properties and does not rely on price information. We consider existing frontier estimation procedures under various scope and scale properties, and identify methods which impose restrictions on the frontier consistent with these properties. Based on desirable characteristics of an estimator of returns to scope, we propose two methods for its assessment. Finally, we present examples and insights using simulated and real data.