Data envelopment analysis of integer-valued inputs and outputs

Lozano, Sebastián; Villa, Gabriel

doi:10.1016/j.cor.2005.02.031

Cited by 103 publications

(75 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As pointed out by Kuosmanen and Kazemi Matin (2009), simply rounding the optimal solution to the nearest whole numbers can result in misleading efficiency assessment and reference targets. Researchers including Lozano and Villa (2006) and Kuosmanen and Kazemi Matin (2009) …”

Section: Integer Super-efficiencymentioning

confidence: 99%

Super-Efficiency in Data Envelopment Analysis

Chen

2015

International Series in Operations Research &Amp; Management Science

View full text Add to dashboard Cite

In an effort to discriminate the performance of efficient decision making units (DMUs), the concept of super-efficiency is proposed, whose basic idea is to eliminate the DMU under evaluation from the reference set. When applied to the variable returns to scale (VRS) situation, the resulting super-efficiency model may become infeasible for certain DMUs due to the convexity constraint. Infeasibility restricts a wider use of super-efficiency DEA. Therefore, taking different viewpoints, a significant amount of studies tackle this problem by developing various new VRS super-efficiency models.

show abstract

Section: Integer Super-efficiencymentioning

confidence: 99%

Super-Efficiency in Data Envelopment Analysis

Chen

2015

International Series in Operations Research &Amp; Management Science

View full text Add to dashboard Cite

show abstract

“…Initially, Banker and Morey (1986) incorporated the categorical variable into DEA formulation, to which Kamakura (1988) contributed a variation to its mixed integer linear programming formulation (MILP), and subsequently, Rousseau and Semple (1993) improved over the shortcomings in the Kamakura's method. More recently, Lozano and Villa (2006) pioneered work on integer inputs and outputs in DEA by incorporating integrality constraints to the DEA framework and developing the MILP procedure for solving DEA in integer values. However, their model violated the DEA properties of convexity, free disposability, and returns to scale.…”

Section: Introductionmentioning

confidence: 99%

Aggregate directional distance formulation of DEA with integer variables

et al. 2015

View full text Add to dashboard Cite

Conventional data envelopment analysis (DEA) models make the assumption of non-negativity and real values in the input and output of the systems that are under study. This paper combines these two interrelated ideas. One is the non-radial measurement of efficiency by establishing an aggregate directional distance formulation of the DEA model (ADDM). Another is the introduction of an integer directional distance function. Usually, directional distance formulations of DEA and ADDM projections of efficient targets for inefficient decision making units (DMUs) have non-integer values. In this paper directional distance function is modified and a mixed integer directional distance formulation of DEA is proposed. This model guarantees integer targets for inefficient DMUs and is applicable to measure efficiency even when input and output variables are negative integer values.

show abstract

“…ð1Þ the original LVM model proposed by Lozano and Villa (2006) is (hereafter referred to as, LVM-R):…”

Section: Introductionmentioning

confidence: 99%