Browsing by Author "Johnson, Andrew L."

Now showing 1 - 3 of 3

A unified model for detecting efficient and inefficient outliers in data envelopment analysis
(2010-02-01)
Chen, Wen-Chih
;
Johnson, Andrew L.
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Data envelopment analysis(DEA) uses extreme observations to identify superior performance, making it vulnerable to outliers. This paper develops a unified model to identify both efficient and inefficient outliers in DEA. Finding both types is important since many post analyses, after measuring efficiency, depend on the entire distribution of efficiency estimates. Thus, outliers that are distinguished by poor performance can significantly alter the results. Besides allowing the identification of outliers, the method described is consistent with a relaxed set of DEA axioms. Several examples demonstrate the need for identifying both efficient and inefficient outliers and the effectiveness of the proposed method. Applications of the model reveal that observations with low efficiency estimates are not necessarily outliers. In addition, a strategy to accelerate the computation is proposed that can apply to influential observation detection. (C) 2009 Elsevier Ltd. All rights reserved.
The dynamics of performance space of Major League Baseball pitchers 1871-2006
(2010-12-01)
Chen, Wen-Chih
;
Johnson, Andrew L.
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
A central decision-maker, the principal, employs performance evaluation criteria consistent with an organization's overall goal(s) to measure the effectiveness of the agents who execute decisions and implement strategies within a specified period. The dataset of performance criteria spanning the performance space will change over time to reflect the principal's strategic modifications. This paper applies a Data Envelopment Analysis (DEA) based approach to reveals the dynamics of the performance space of Major League Baseball (MLB) pitchers with minimum subjective judgment imposed on the data. The proposed approach is applied to data on MLB pitchers from 1871 to 2006. We conclude that many of the findings are consistent with the observations of baseball's experts. The approach also suggests new directions for investigating a large dataset to identify revealed preferences or strategies by using historical and modern observations.
The dynamics of performance space of Major League Baseball pitchers 1871-2006
(2010-12-01)
Chen, Wen-Chih
;
Johnson, Andrew L.
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
A central decision-maker, the principal, employs performance evaluation criteria consistent with an organization's overall goal(s) to measure the effectiveness of the agents who execute decisions and implement strategies within a specified period. The dataset of performance criteria spanning the performance space will change over time to reflect the principal's strategic modifications. This paper applies a Data Envelopment Analysis (DEA) based approach to reveals the dynamics of the performance space of Major League Baseball (MLB) pitchers with minimum subjective judgment imposed on the data. The proposed approach is applied to data on MLB pitchers from 1871 to 2006. We conclude that many of the findings are consistent with the observations of baseball's experts. The approach also suggests new directions for investigating a large dataset to identify revealed preferences or strategies by using historical and modern observations.