Handbook on Data Envelopment Analysis, COOPER

This handbook covers DEA topics that are extensively used and solidly based. The purpose of the handbook is to (1) describe and elucidate the state of the field and (2), where appropriate, extend the frontier of DEA research. It defines the state-of-the-art of DEA methodology and its uses. This handbook is intended to represent a milestone in the progression of DEA. 

Written by experts, who are generally major contributors to the topics to be covered, it includes a comprehensive review and discussion of basic DEA models, which, in the present issue extensions to the basic DEA methods, and a collection of DEA applications in the areas of banking, engineering, health care, and services. 

The handbook's chapters are organized into two categories: (i) basic DEA models, concepts, and their extensions, and (ii) DEA applications. First edition contributors have returned to update their work.

The second edition includes updated versions of selected first edition chapters. New chapters have been added on: 

·         Different approaches with no need for a priori choices of weights (called “multipliers) that reflect meaningful trade-offs.

·         Construction of static and dynamic DEA technologies.

·         Slacks-based model and its extensions

·         DEA models for DMUs that have internal structures network DEA

·         Selection of DEA applications in the service sector with a focus on building a conceptual framework, research design and interpreting results.

 

William W. Cooper, Pakar Metode DEA

Professor Emeritus William W. Cooper, an academic giant widely considered to be a father of management science, died Wednesday, June 20, at the age of 97. A high school dropout and former boxing champ, he went on to revolutionize business education and research.

In a career that spanned nearly seven decades and included stints at the University of Chicago, Carnegie Mellon, and Harvard Business School, Cooper was a prolific researcher who was at the forefront of a new way of studying business, emphasizing scientific rigor and integrating disciplines. In the words of one of his star doctoral students, Andrew Whinston, professor at McCombs: “The models Bill pioneered fostered a huge transformation of worldwide company operations. He has, as they say in today’s jargon, a big footprint.”

He was also a fixture on campus, coming to work nearly every day until just a few weeks before his death.

BUKU DEA RAMANATHAN: AN INTRODUCTION TO DEA

'This book is an excellent tool for practitioners who are interested in the merits and pitfalls of the technique.... (The author's) research is an example of inventiveness, diligence and accuracy' - Freerk A. Lootsma, Delft Institute of Technology

Data envelopment Analysis is a Mathematical Programme for measuring performance efficiency of organizational units. The organizational units, termed as decision-making units (DMU) can be of any kind: manufacturing units, a set of schools, banks, hospitals, power plants, police stations, prisons, a set of firms etc.

DEA has been unsuccessfully applied to measure the performance efficiency of these different kinds of DMUs which share a common characteristic - that they are non-profit organization where measurement of performance efficiency is difficult.

DEA has been employed for assessing the relative performance of a set of firms that use a variety of identical inputs-say in the case of a school: quality of students, teachers, grants etc.,-to produce a variety of identical outputs-number of students who pass the final year, average grades obtained by the students in the final year etc.

DEA assumes the performance of the DMUs by using the concepts of efficiency or productivity which is measured as the ratio of total outputs to total inputs. Also, the efficiencies estimated are relative to the best performing DMU or DMUs. The best performing DMU is given a score of 100% and the performance of other DMUs vary between 0 -100%.

BUKU TENTANG DEA: METODOLOGI PENELITIAN EKONOMI ISLAM

Buku ini mengkaji lebih dalam metodologi-metodologi aplikatif dan powerful yang dapat diaplikasikan bagi penelitian di bidang ekonomi Islam seperti zakat, lembaga keuangan syariah, manajemen dan bisnis syariah, ekonomi makro dan mikro. beberapa yang dikupas tuntas adalah metode Analytical Network Process (ANP), Data Envelopment Analysis (DEA), dan Vector Autoregression (VAR) model.

Dapatkan dan pesan bukunya sekarang juga.

BUKU: New Efficiency Theory: With Applications of Data Envelopment Analysis

New efficiency theory refers to the various parametric and semi-parametric methods of estimating production and cost frontiers, which include data envelopment analysis (DEA) with its diverse applications in management science and operations research. 

This monograph develops and generalizes the new efficiency theory by highlighting the interface between economic theory and operations research. Some of the outstanding features of this monograph are: (1) integrating the theory of firm efficiency and industry equilibrium, (2) emphasizing growth efficiency in a dynamic setting, (3) incorporating uncertainty of market demand and prices, and (4) the implications of group efficiency by sharing investments. 

Applications discuss in some detail the growth and decline of the US computer industry, and the relative performance of mutual fund portfolios.

Fuzzy DEA

Data envelopment analysis (DEA) is a methodology for measuring the relative efficiencies of a set of decision making units (DMUs) that use multiple inputs to produce multiple outputs. Crisp input and output data are fundamentally indispensable in conventional DEA. 

 

However, the observed values of the input and output data in real-world problems are sometimes imprecise or vague. Many researchers have proposed various fuzzy methods for dealing with the imprecise and ambiguous data in DEA. 

 

 In this study, we provide a taxonomy and review of the fuzzy DEA methods. We present a classification scheme with four primary categories, namely, the tolerance approach, the a-level based approach, the fuzzy ranking approach and the possibility approach. We discuss each classification scheme and group the fuzzy DEA papers published in the literature over the past 20 years.

Two Stages DEA (DEA Dua Tahap)

Selain metode yang lazim digunakan dalam pengukuran tingkat efisiensi dengan DEA, dikenal pula dengan Two Stages DEA atau DEA dua tahap. First Stage: Metode Data Envelopment Analysis (DEA). Metode DEA adalah sebuah metode frontier non parametric yang menggunakan model program linier untuk menghitung perbandingan rasio output dan input untuk semua unit yang dibandingkan dalam sebuah populasi. Tujuan dari metode DEA adalah untuk mengukur tingkat efisiensi dari decision-making unit (DMU ie.bank) relatif terhadap bank yang sejenis ketika semua unit-unit ini berada pada atau dibawah “kurva” efisien frontier-nya. Jadi metode ini digunakan untuk mengevaluasi efisiensi relatif dari beberapa objek (benchmarking kinerja).

Metode DEA menghitung efisiensi teknis untuk seluruh unit. Skor efisiensi untuk setiap unit adalah relatif, tergantung pada tingkat efisiensi dari unit-unit lainnya di dalam sampel. Setiap unit dalam sampel dianggap memiliki tingkat efisiensi yang tidak negatif, dan nilainya antara 0 dan 1 dengan ketentuan satu menunjukkan efisiensi yang sempurna. Selanjutnya, unit-unit yang memiliki nilai satu ini digunakan dalam membuat envelope untuk frontier efisiensi, sedangkan unit lainnya yang ada di dalam envelope menunjukkan tingkat inefisiensi.

Skor Efisiensi DEA = Output / Input

       Second Stage: Model Regresi Tobit. Metode Tobit mengasumsikan bahwa variabel-variabel bebas tidak terbatas nilainya (non-censured); hanya variabel tidak bebas yang censured; semua variabel (baik bebas maupun tidak bebas) diukur dengan benar; tidak ada autocorrelation; tidak ada heteroscedascity; tidak ada multikolinearitas yang sempurna; dan model matematis yang digunakan menjadi tepat. Dalam penggunaan metode analisis regresi untuk penelitian bidang sosial dan ekonomi, banyak ditemui struktur data dimana variabel responnya mempunyai nilai nol untuk sebagian observasi, sedangkan untuk sebagian observasi lainnya mempunyai nilai tertentu yang bervariasi. Struktur data seperti ini dinamakan data tersensor (censored data).