Introduction: To assess efficiency as a relative concept, the difference between real and expected values must be determined by comparing the productivity of economic units of industry and the efficiency in potential production conditions. As economic units, hospitals need to utilize efficiency analysis in order to make optimal use of their available resources. Therefore, the present study compared the efficiency of different hospitals of Shahid Beheshti University of Medical Sciences.Methods: Since this applied analytical research referred to the documents and performance statistics of hospitals and therfore used real data, evaluating the validity and reliability had no relevance. In order to measure the relative efficiency of health care in 16 hospitals associated with Shahid Beheshti University of Medical Sciences and also to determine efficient and inefficient hospitals during 2005-2007, CCR (Charnes-Cooper-Rhodes) input oriented multiplier model of data envelopment analysis (DEA) was used for data analysis. In addition, AP (Anderson-Peterson) model was used to rank efficient hospitals. LINDO software was utilized to solve the model.Results: Based on our results, 43.75%, 31.25% and 37.5% of hospitals were efficient respectively in 2005, 2006 and 2007.Conclusion: The results suggested that the efficiency of inefficient hospitals could be improved through the potential savings in resources (62.44% in infrastructure, 43.88% in the number of active beds, 37.15% in the number of physicians and 38.58% in the number of paramedics).

Missing data is a chronic disease in applications of data envelopment analysis. Very often, important input or output variables are not completely specified and/or the decision-making units do not report all the required statistics. Therefore, the missing values in the inputs and outputs cannot be studied using the original data envelopment analysis models. This paper introduces methods for finding missing data when the existing data is certain. In this article, after explaining the essential concepts of missing values, we describe some methods of missing value imputation that reduce the complexity of data analysis. There are several methods for imputing missing data, including various methods of simple imputation and multiple imputation. This paper is the first systematic attempt to utilize data containing missing values using statistical approaches in the DEA. In particular, we examine what happens if we keep empty entries in the data set and assign a certain numeric value to them. To show how the proposed methods work, they will be used to evaluate a set of secondary public schools in Greece in some of which there are missing input or output values.

In this article, we try to use statistical experiment in data envelopment analysis to obtain more accurate analytical DEA models, and use cluster sampling in this operation. Also we have examined the models for 35 branchs of commerical banks in different monthes and the results show that the models work well.

data envelopment analysis (DEA) is a nonparametric approach for measuring the relative efficiency of a decision making units consists of multiple inputs and outputs. In all standard DEA models semi positive real valued measures are assumed, while in some real cases inputs and outputs may take complex valued. The question is related to measuring efficiency in such cases. As far as we are aware, there is not any special formulation replying the complex-valued questions. The formulation developed in this paper enables one to estimate efficiency when the data are complex valued.

In this research, a new fuzzy streaming data classification method is presented. Fuzzy data classification is one of the most challenging areas in data analysis due to high-volume and sophisticated computation engaged in data analysis techniques. However, in some other areas such as mathematical programming, great achievements are obtained in modeling of systems measured by fuzzy data. So, in this research classification based on data envelopment analysis (DEA) is selected to handle fuzzy data classification. On the other hand, the proposed method can be applied for dealing with streaming data by using an updating schema. This feature makes the proposed method suitable for non-stationary environment in which data pattern varies over the time. Experiments using simulated data demonstrate the capability of the proposed method in dealing with uncertain and non-stationary environment.

The classification of fuzzy uncertain data is considered one of the most challenging issues in data analysis. In spite of the significance of fuzzy data in mathematical programming, the development of the analytical methods of fuzzy data is slow. Therefore, the current study proposes a new fuzzy data classification method based on fuzzy data envelopment analysis (DEA) which can handle streaming data. The new method is tested by simulated data and the results indicate its effectiveness in facing uncertain data and variable conditions.

In the process of production, some of the inputs are fixed and cannot easily be changed, such as work hours of workers and hours of administrative or work, these types of inputs are fixed and others are variables. In this paper, by considering some inputs or outputs which are limited, their amounts must be integrated; this concept for integer data is extended. We show the importance of subject by bringing a real example of 25 branches of a bank.