On variable reductions in data envelopment analysis with an illustrative application to a gas company

Toloo, Mehdi; Babaee, Seddigheh

doi:10.1016/j.amc.2015.06.122

Cited by 17 publications

(16 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve this issue, studies were done (Adler and Yazhemsky, 2010;Nataraja and Johnson, 2011;Toloo and Babaee, 2015). One of the models proposed was using PCA with DEA.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Despite of this, DEA is still young for banking and finance studies as can be seen from the citation based literature survey identifying key papers in the area (Liu, Lu, Lu, and Lin, 2013). Factor or variable selection methodology, discriminatory power of DEA, dimension reduction or factor reduction are some of the key concepts when the implementation of DEA is considered (Adler and Yazhemsky, 2010;Nataraja and Johnson, 2011;Toloo and Babaee, 2015). In the banking and finance area, one of the most recent studies of DEA focuses on the factor selection for the retail banking industry from the output side (Eskelinen, 2017).…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

On Dimension Reductions in Data Envelopment Analysis With an Illustrative Application to Turkish Banking Sector Performance

Daver

Küçükkocaoğlu

2019

Uluslararası İktisadi Ve İdari İncelemeler Dergisi

View full text Add to dashboard Cite

A b s t r a c tIn this study we tested the Turkish Banking Sector Performance development and the usage of various methodologies. For this purpose we used several data envelopment analysis(DEA) performance measurement systematics from 2002.12 to 2017.06. Proposed DEA models include dimension reduction techniques. The first one is principal component analysis which is abbreviated as PCA and the second one is correlation based DEA model construction. We investigated performance change over time and found that banks in Turkish Banking Sector should take steps now for maintaining their improved performances. Policies implemented after the 2001 crisis had positive effects during the 2008 crisis period in the Turkish banking sector, but gains should be sustained. We also found that our main model which uses four input and four output factors yields similar results with the investigated dimension reduction technique approaches. AÇIKLAYICI BİR UYGULAMA İLETÜRK BANKACILIK SEKTÖRÜ PERFORMANSINA VERİ ZARFLAMA ANALİZİ BOYUT AZALTIMLARI Ö z Bu çalışmada Türk Bankacılık Sektörü Performansı gelişimi ve çeşitli metodolojilerin kullanımı test edilmiştir. Bu amaçla 2002.12 ile 2017.06 arasında çeşitli veri zarflama analizi (DEA) performans ölçüm sistematiği kullanılmıştır. Önerilen DEA modelleri, boyut azaltma tekniklerini içermektedir. Birincisi, PCA olarak kısaltılmış olan temel bileşen analizi ve ikincisi ise korelasyon bazlı DEA model kurulmasıdır. Zaman içerisinde performans değişimi incelenmiştir ve Türk Bankacılık Sektöründeki bankaların, artan performanslarını sürdürmek için adımlar atmaları gerektiği tespit edilmiştir. 2001 krizinden sonra uygulanan politikalar, 2008 kriz döneminde Türk bankacılık sektöründe olumlu etkiler yaratmıştır, ancak kazanımlar sürdürülebilmelidir. Dört girdi ve dört çıktı faktörü kullanan ana modelinin, araştırılan boyut azaltma tekniği yaklaşımları ile benzer sonuçlar verdiği bulunmuştur.

show abstract

“…To solve this issue, studies were done (Adler and Yazhemsky, 2010;Nataraja and Johnson, 2011;Toloo and Babaee, 2015). One of the models proposed was using PCA with DEA.…”

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

On Dimension Reductions in Data Envelopment Analysis With an Illustrative Application to Turkish Banking Sector Performance

Daver

Küçükkocaoğlu

2019

Uluslararası İktisadi Ve İdari İncelemeler Dergisi

View full text Add to dashboard Cite

show abstract

“…Amirteimoori and Emrouznejad () developed a DEA approach, which integrates some inputs and outputs to reduce the number of performance measures iteratively. However, Toloo and Babaee () developed Amirteimoori and Emrouznejad's approach and suggested a method, which is stable and non‐iterative.…”

Section: Preliminariesmentioning

confidence: 99%

A hybrid data envelopment analysis and multi‐attribute decision making approach to sustainability assessment

Keshavarz

Toloo

2018

Expert Systems

Self Cite

View full text Add to dashboard Cite

The concept of sustainability consists of three main dimensions: environmental, techno‐economic, and social. Measuring the sustainability status of a system or technology is a significant challenge, especially when it needs to consider a large number of attributes in each dimension of sustainability. In this study, we first propose a hybrid approach, involving data envelopment analysis (DEA) and a multi‐attribute decision making (MADM) methodologies, for computing an index for each dimension of sustainability, and then we define the overall sustainability index as the mean of the three measured indexes. Towards this end, we define new concepts of efficiency and cross‐efficiency of order (p, q) where p and q are the number of inputs and outputs, respectively. For a given (p, q), we address the problem of finding efficiency of order (p, q) by developing a novel DEA‐based selecting method. Finally, we define the sustainability index as a weighted sum of all possible cross‐efficiencies of order (p, q). Form a computational viewpoint, the proposed selecting model significantly decreases the computational burden in comparison with the successive solving of traditional DEA models. A case study of the electricity‐generation technologies in the United Kingdom is taken as a real‐world example to illustrate the potential application of our method.

show abstract

“…The normal distribution of the efficiency score feature is particularly attractive because returns-to-scale hypothesis testing may be conducted by using traditional difference-in-means parametric statistical procedures. Both of these features are tested using data and models reported in a published study [16]. The rest of the paper is organized as follows: In Section 2, the basic DEA radial and non-radial models, ensemble DEA model and Entropy criterion for comparing different DEA models are described.…”

Section: Introductionmentioning

confidence: 99%

“…The rest of the paper is organized as follows: In Section 2, the basic DEA radial and non-radial models, ensemble DEA model and Entropy criterion for comparing different DEA models are described. In Section 3, using Iranian gas company data, the results of ensemble DEA models are compared with the results of variable selection models used in Toloo and Babaee's [16] study. Additionally, in Section 3, the properties of the ensemble DEA scores are investigated in terms of the entropy criterion and their statistical distributions.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Ensemble and Dimensionality Reduction DEA Models Based on Entropy Criterion

Pendharkar

2020

Algorithms

View full text Add to dashboard Cite

Dimensionality reduction research in data envelopment analysis (DEA) has focused on subjective approaches to reduce dimensionality. Such approaches are less useful or attractive in practice because a subjective selection of variables introduces bias. A competing unbiased approach would be to use ensemble DEA scores. This paper illustrates that in addition to unbiased evaluations, the ensemble DEA scores result in unique rankings that have high entropy. Under restrictive assumptions, it is also shown that the ensemble DEA scores are normally distributed. Ensemble models do not require any new modifications to existing DEA objective functions or constraints, and when ensemble scores are normally distributed, returns-to-scale hypothesis testing can be carried out using traditional parametric statistical techniques.

show abstract

On variable reductions in data envelopment analysis with an illustrative application to a gas company

Cited by 17 publications

References 15 publications

On Dimension Reductions in Data Envelopment Analysis With an Illustrative Application to Turkish Banking Sector Performance

On Dimension Reductions in Data Envelopment Analysis With an Illustrative Application to Turkish Banking Sector Performance

A hybrid data envelopment analysis and multi‐attribute decision making approach to sustainability assessment

A Comparison of Ensemble and Dimensionality Reduction DEA Models Based on Entropy Criterion

Contact Info

Product

Resources

About