Science topic

Data Envelopment Analysis - Science topic

Data Envelopment Analysis
Questions related to Data Envelopment Analysis
  • asked a question related to Data Envelopment Analysis
Question
2 answers
Dear colleagues,
I am currently exploring the Benefit of the Doubt (BoD) approach within Data Envelopment Analysis (DEA) for composite indicators. I would appreciate your insights on the following:
  1. What are the recommended software options for implementing DEA BoD?
  2. Has anyone successfully run this approach using Stata? If so, could you share relevant commands, packages, or references?
Relevant answer
Answer
Hi Ermita,
you can use Compind package on R https://cran.r-project.org/web/packages/Compind/index.html developed with Elisa Fusco that implements BoD, the robust, conditional, spatial, multidirectional, etc ... versions and other methods derived from DEA-type techniques.
Regards,
  • asked a question related to Data Envelopment Analysis
Question
3 answers
Hello everyone,
I’m currently working on a Data Envelopment Analysis (DEA) project and I’m unsure whether to use original values or natural logarithms value for my input and output variables. I would greatly appreciate any insights on this topic.
Specifically, what are the advantages and disadvantages of each approach? Additionally, if anyone could recommend relevant studies or literature that discuss this issue, I would be very grateful.
Thank you in advance for your help!
Relevant answer
Answer
Thank you for your insight! I would appreciate it if you could provide some references or research studies that support this viewpoint. It would be helpful to see how others have addressed the limitations of applying monotonic transformations, like logarithms, in nonparametric and non-linear methods (DEA). Looking forward to learning more about this.
  • asked a question related to Data Envelopment Analysis
Question
4 answers
I would appreciate it if you could share your suggestions and experience with me.
Relevant answer
Answer
Jorge Ventura thanks for your help.
  • asked a question related to Data Envelopment Analysis
Question
2 answers
Data Envelopment Analysis (DEA) is a mathematical modeling technique that has been primarily used and implemented in the field of Operations Research and Management Science. DEA has since found applications in various disciplines, including Economics, Finance, Healthcare, Education, Environmental Studies, Transportation, and Logistics. These are just a few examples of the disciplines where DEA has been implemented as a tool. The versatility and broad applicability of DEA make it a valuable analytical technique for evaluating efficiency and guiding decision-making in various domains.
Recently, MATLAB's implementation of data envelopment analysis (DEA) aims to provide a powerful tool for scientists and engineers to analyze and optimize the efficiency and productivity of various processes. DEA is a technique used to evaluate the relative efficiency of a set of entities, by comparing their input-output relationships. The primary goals of implementing the DEA tool in MATLAB are as follows:
Efficiency Evaluation, Benchmarking and Best Practices, Input-Output Optimization, Sensitivity Analysis and Decision Support, Integration with Other MATLAB Features.
In summary, MATLAB's implementation of the DEA tool aims to empower scientists and engineers with a comprehensive and versatile framework for evaluating, benchmarking, and optimizing the efficiency and productivity of various processes. By providing robust analysis capabilities and integration with other MATLAB features, the tool facilitates informed decision-making and supports continuous improvement efforts.
You are free to discuss this further as your contributions are welcomed. At the moment, please contact the email provided if you are willing to publish a chapter in a multidisciplinary book for possible indexation in Scopus: abel.ajibesin@aun.edu.ng or follow the links below for more information about the book and submission. https://www.igi-global.com/publish/call-for-papers/call-details/6516, https://www.igi-global.com/book/data-envelopment-analysis-dea-methods/321646#description.
Also, if you are using MATLAB's implementation of data envelopment analysis (DEA) and planning to be part of the incoming book that is focusing on Science, IT, and Engineering using DEA, kindly send an email to abel.ajibesin@aun.edu.ng or ajibesin@ieee.org
Relevant answer
Answer
This is a discussion (not a question), about the application of data envelopment analysis (DEA)/MATLAB in science, technology, and engineering.
  • asked a question related to Data Envelopment Analysis
Question
3 answers
I'm comparing some financial companies using data envelopment analysis(DEA) on their financial statements. One of the outputs is income or profit. In some companies, we have negative income or negative profit. The incomes are between -69 000€ and 270 000€. We added the constant 70 000. Is there any maximum value of a constant (the data are negative) in data envelopment analysis (DEA) in a financial case? Can the high value of constant influence the data?
Relevant answer
Answer
Adding constants to make the data all positive is not a good method. This is because DEA measurements have relative characteristics. You can try to normalize the data and convert it to a positive number. In fact, some DEA models can absorb negative values. MSBM (Modified Slack Based Measure) is an SBM (ERM) proposed by Sharp, Meng, &Liu (2007).
  • asked a question related to Data Envelopment Analysis
Question
2 answers
I am using Data Envelopment Analysis for my research. Most of the inputs and outputs are derived from the past literature. However I want to test some additional factors which may be considered as Input or Output factor. I read about the 3-level fractional factorial design as suggested by Hiroshi Morita and Necmi K Avkiran in their 2008 paper "Selecting Inputs and Outputs in Data Envelopment Analysis by designing statistical experiments".
1. Can somebody provide clarifications on how to use this approach?
2. Is there any other approach to choose inputs and outputs?
Relevant answer
Answer
1. The 3-level fractional factorial design is a statistical method used in data envelopment analysis (DEA) to select inputs and outputs. It involves selecting a set of inputs and outputs that are believed to be relevant to the problem. These factors are then varied at three levels (low, medium, high) to create a set of experimental conditions. DEA models are then run on each experimental condition to obtain efficiency scores. The results are analysed using statistical methods to identify the factors that have the greatest impact on the efficiency scores. This approach allows for the identification of important inputs and outputs, as well as their optimal levels, in a relatively efficient and effective manner.
2. There are other approaches to selecting inputs and outputs in DEA. These are expert judgment, conducting a literature review, analysing correlation and regression analysis, and using principal component analysis (PCA) and factor analysis. It is generally sound to use a combination of methods to ensure a comprehensive selection process.
  • asked a question related to Data Envelopment Analysis
Question
2 answers
I am trying to measure the efficiency of tax collection using stochastic frontier analysis and data envelopment analysis. Is there any literature about this.
Relevant answer
Answer
Ahmad Alwaked you can try this paper of James Alm, Denvil Duncan (2014)
Thanks
  • asked a question related to Data Envelopment Analysis
Question
2 answers
In my data envelopment analysis (DEA) model, I have 3 outputs, namely (i) No. of Sponsored Projects, (ii) No. of Consultancies and (iii) Total Revenue generated from Sponsored Projects and Consultancies. My DMUs are different universities. It is clear that the third output is the overlapping factor as the revenue is generated due to the sponsored projects and consultancies. If I choose only the third output, the problem is that I cannot take into account the social benefits from a university because it is possible that a university undertakes many projects and consultancies (i.e. indicators of social benefits) while generating less revenue. Again, if I take the first two outputs, then I miss the part of revenue generation because all the projects and consultancies may not generate same revenue. Should I consider the first two outputs or the third output or all the three outputs in my model?
Relevant answer
Answer
It is generally recommended to include all three outputs in your DEA model, as each of them represents a distinct aspect of the performance of the DMUs (universities).
What I understand is that the first output, No. of Sponsored Projects, reflects the ability of the university to attract funding for research and development. The second output, No. of Consultancies, reflects the university's ability to provide services to external organizations. The third output, Total Revenue generated from Sponsored Projects and Consultancies, reflects the university's overall financial performance.
If you include all three outputs in your model, you can capture a university's social benefits and financial performance. However, you should be aware that the third output may be correlated with the first two outputs, as revenue is generated from sponsored projects and consultancies. This could potentially affect the results of your DEA model.
One way to account for this is to use a model that allows for overlapping outputs, such as the common weights model or the free disposal hull model. These models allow for the possibility that some inputs and outputs may be used in the production of multiple outputs, and can provide a more accurate assessment of the efficiency of the DMUs.
Ultimately, the decision of which outputs to include in your DEA model will depend on the specific research question you are trying to answer and the data that is available to you. It may be helpful to consider the strengths and limitations of each model and the implications of including or excluding certain outputs in your analysis.
Good luck.
  • asked a question related to Data Envelopment Analysis
Question
1 answer
Dr. Kamran Rashidi sir wrote that paper.
On that paper, i tried alot over a year but couldn't figure out the code.
I need the MATLAB Code.
I have found the CCR,BCC models, but there is no additive model. Please someone help me.
Relevant answer
Answer
Here you are.
  • asked a question related to Data Envelopment Analysis
Question
2 answers
Are there anyone envelopment data analysis in the Frontier Analysis program by weighting up inputs and outputs with multiple criteria decision-making techniques? In the Frontier Analysis program, the weight restrictions in the section of weight are required to be entered in the minimum and maximum. How can I solve this problem?
Relevant answer
Answer
Data envelopment analysis (DEA) is a nonparametric method measuring relative carbon emissions reduction efficiency within a group of homogeneous decision-making units (DMUs) with multiple inputs and multiple outputs. Here the DMUs may be companies, schools, hospitals, shops, bank branches, and others.
  • asked a question related to Data Envelopment Analysis
Question
20 answers
I am planning to use DEA analysis for my on going research. I have SPSS with me. therefore, I would like to figure out how it can be done with SPSS.
Your suggestions would be highly appreciated. 
Relevant answer
Answer
No You can't
  • asked a question related to Data Envelopment Analysis
Question
3 answers
How to perform CCR (Charnes–Cooper–Rhodes) model for Data Envelopment Analysis for the estimation of three measures of efficiency (TE, PTE and SE).
How to arrange the raw data to perform the model or analysis?
Relevant answer
Answer
Thank you sir @ Ramrattan and Kyrgiakos.
  • asked a question related to Data Envelopment Analysis
Question
6 answers
I have to evaluate sequential MI with bootstrapping. If Is any one of you is using MaxDEA 7 Ultra please help me in this regard. I will be very thankful.
Relevant answer
Answer
YES. I am using this software
  • asked a question related to Data Envelopment Analysis
Question
1 answer
Hello to everyone!
I am doing a research on bank branches efficiency, and I want firstly to count Malmquist efficiency index (I have data for 3-year period), and then run a double bootstrapped truncated regression, with Malmquist Index as dependent variables and one exogenous variable.na
Maybe someone can advice me, how can I run such a regression on Malmquist index in R?
Thank you very much in advance!
Best regards,
An
Relevant answer
Answer
Take a look at this search for some useful information. Best wishes David Booth
  • asked a question related to Data Envelopment Analysis
Question
3 answers
I read interestingly one article titled “Analysis of the Global Burden of Disease study highlights the global, regional, and national trends of chronic kidney disease epidemiology from 1990 to 2016”. In the article, authors performed Frontier analysis. I tried it in R software (Benchmarking, rDEA package) but could not perfectly did well. I only got the efficiency for every country at each year but failed to get the frontier pinpoint. I have examined many books and papers but could not find the answer.
Could anybody know how to perform frontier analysis using data envelopment analysis?
Relevant answer
Answer
OSDEA is easy and also free.
  • asked a question related to Data Envelopment Analysis
Question
4 answers
Do we need to run the panel regression diagnostic tests for panel stochastic frontier analysis (xtfrontier or sfpanel)?
Could someone suggest the best read for this analysis, especially for the time-varying decay model and sfpanel with inefficiency functions explicitly mentioned?
Relevant answer
Answer
Regarding your problem, I can recommend the following article:
Battese, G.E., Coelli, T.J. Frontier production functions, technical efficiency and panel data: With application to paddy farmers in India. J Prod Anal 3, 153–169 (1992). https://doi.org/10.1007/BF00158774.
  • asked a question related to Data Envelopment Analysis
Question
2 answers
Hi I am new to the DEA model. And it may be a plain question. But I hope someone can help me to clarify it.
So in a DEA model, I get the efficiency score for each of the units in a chain group. Can I simply compare the score and say which hospital is more efficient or less efficient?
Since the composite unit is created based on different weights from each unit, then the composite unit is different for each target unit compared. So I don't know if those scores are comparable.
Can anyone explain if those are comparable and why?
Many thanks!
Relevant answer
Answer
You could, first of all, create some clusters (by utilising methods included in the main statistical packages) in wich each composite unit is weighted with the number (or other important characteristics) of base units, to understand if there some tendency of units to group closer in terms of efficiency . You could, after, to describe each cluster by means of the additional variables cluster's average you have.
  • asked a question related to Data Envelopment Analysis
Question
3 answers
So what if the slacks are zero but the TE is still not equal to one?
When the slacks are zero PTE will be equal to one.
We get PTE equal to 1 because the firm is benchmarked with it’s fellow IRS or DRS.
Let’s remember the main difference between CCR and BCC is the constraint on λ, where by in the CCR model it is just non zero value and that expands the Efficiency Reference Set (ERS). However with BCC the constrain is summation of λ is equal to 1, which limits the ERS to only those firms in the same scale. Therefore if it is benchmarked with firms at same productive scale they are efficient but they are still not performing similar to those at CRS. This is equivalent to say that there is no excessive usage of inputs but the output to input ratio is still not the same as the most efficient firm, the firm is still using more inputs to produce one output.
Where did the concept of scale come from in BCC?
Lets consider this example, if we have Car A and car B. Car A is designed to travel 20miles per Gallon of gas and car B is designed to travel 30 miles per Gallon of gas. It will be unfair to say that car A is inefficient because it only travels 20 miles per gallon ( it will only be 66.7% efficient) if it is benchmarked with the car B. But this information does not consider the weight capacity of the car and other qualitative information. So with BCC, car A will be benchmarked with its peers in similar scale by assigning different weights on the inputs and outputs. Therefore BCC will find that if the car is actually traveling at 20 miles per gallon, then it is efficient interms of utilizing the inputs to produce outputs. However it will still declare that the car A is not scale efficient, and will compute the distance that car A needs to move to achieve an efficient scale (1-SE).
Before going further into theoretical analysis, I would suggest that the DMU that has PTE =1 but scale inefficient can enhance its output interms of quality or accompanied service. And if we are input oriented, outsourcing can also be a good idea, like opening a new department with in and then outsource service or some inputs from there.
What determines if DRS or IRS?
It is the summation of λ. λ is the weight of inputs assigned by the DEA, and the results of this summation can be computed by the Joe Zhu software.
Under CCR model an efficient firm will have λ =1, and in BCC Summation of λ will be equal to one. If less than one than the firm is operating at IRS and if greater than one than it is operating at DRS.
If we remember the Cob-Douglas production function the implications of return to scale are the same.
q=Akalb (a and b are exponents to k and l respectively)
Where q represents the firm’s services during a period, k represents the capital usage during the period, l represents hours of labor input and A is the technology used in the production of service.
when summation of input elasticity (a+b) equal to one then the firm is operating at CRS, less than one is IRS and more than one is DRS.
Joe Zhu suggest that in certain situations the λ can be used/ translated as Marginal Rate of Technical Subsititution (MRTS), how much of input X1 can be substituted with input X2 to maintain the same level of outputs. As we know that MRTS is actually related to the Marginal productivity of both inputs at that particular combination.
MRTS x1 for x2 = MPx1/MPx2
Normally we need to understand the cost of inputs, and the best combination is found at the point of tangent between Iso-cost and Isoquant. So how do we know the best combination before including the cost? And what is the relationship between MRTS and RTS?
So how do we know the best combination before including the cost?
When the summation of λ equals to 1 then that means MRTS is equal to one which implies that we can substitute one unit of input X1 with one unit of input X2 and still maintain the same level of inputs.
Relationship between RTS (Returns To Scale) and MRTS.
They are both related to Marginal productivity. With CRS the MRTS is equal to one which will mean that the marginal productivities of both inputs are similar. The Cob-Douglas production function is homothetic that at any isoquant (any increase in inputs by scalar t) should yield another isoquant with the same RTS, same slope. When the next slope is is greater than 1 (DRS) Marginal productivity of input 1(MPx1) will be greater than MPx2 and vice versa for IRS.
And yes, it is wise to use more of the input that still has high Marginal productivity than the one that has less. I think this is how a firm can move towards CRS. But how you determine the decomposition in a situation with more than 2 inputs? (Beyond the time that I have for now).
I hope this information is somehow useful for the interpretation of BCC DEA results. And ofcourse further analysis and discussion is needed.
References:
1. Nicholson, W., & Snyder, C. (2008). Microeconomic theory: basic principles and extensions. Cengage Learning
2. Sherman, H. D., & Zhu, J. (2006). Data Envelopment Analysis Explained. Service Productivity Management: Improving Service Performance using Data Envelopment Analysis (DEA), 49-89.
Relevant answer
Answer
In case of CCR if summation of shadow prices of binding constrain equals to 1, then you can continue with the model. If not, you will have to switch to the VRS model. In the VRS model the sum of shadow prices or lambda will be equal to 1.
  • asked a question related to Data Envelopment Analysis
Question
3 answers
I know that using non-discretionary input could be an issue in the original, input-oriented DEA models where input can be expanded and/or contracted. The concern, I think, was that we don't want to produce efficiency scores suggesting efficiency could be improved by reducing uncontrollable (non-discretionary) inputs. However, I wonder if the inclusion of non-discretionary input is as consequential for output-oriented VRS DEA models? Most of the literature is based on input-oriented DEAs. Any comments will be appreciated, Thanks.
Relevant answer
Answer
good question
  • asked a question related to Data Envelopment Analysis
Question
14 answers
Do you have some ideas on how to apply DEA or general efficiency measures to help fight COVID? Thanks!
  • asked a question related to Data Envelopment Analysis
Question
5 answers
Dear Colleague,
Part of my Ph.D. thesis needs to be completed questionnaire, which, unfortunately, due to Covid 19, we cannot attend the company under review. For this reason, I request supply chain experts who wish to complete the questionnaire to notify me, that I will email the questionnaire to them. It would be your generosity to respond to the questionnaires and also distribute them among your colleagues, students, and networks.
Thank you in advance for your help and cooperation.
Relevant answer
Answer
thank you so much, I sent it to your email
  • asked a question related to Data Envelopment Analysis
Question
6 answers
Could someone recommend me a software for conducting windows analysis in DEA? Any procedural articles on the concept are also requested.
Thanks
  • asked a question related to Data Envelopment Analysis
Question
8 answers
Dear all.
I would like to ask you some sort of guideline, developed from your own experience or from references, about condition where it is better to use the "traditional" DEA and when is more appropriate to consider for the Slack Based alternative, (Tone, 2001 and Tone, 2002). I mentioned conditions having in mind for istance sample sizes, area of investigation (healthcare, transportation ecc.) or other instrument combined with the DEA analysis (regressions, bootstrap, bayesian methods...).
I thank you in advance.
Stefano
Relevant answer
Answer
Stefano Martinazzi when we use radial measure, the DMU reach the efficient frontier but if it has any slack left, it will be weakly efficient (there may be more chances to reduce the inputs or outputs). However, when we use slack based measure, the inefficient firm become the strongly efficient firm once it reaches the efficient frontier
  • asked a question related to Data Envelopment Analysis
Question
4 answers
Can we use DEA (Data Envelopment Analysis) with 4 inputs and more than 15 outputs? This is technically possible? Can you recommend an application?
Relevant answer
It depends on the number of DMU's that you are considering in your study, and maintain the relationship that mentioned Leonidas Sotirios Kyrgiakos .
I recommend you see the possibility of making a correlation analysis to identify which variables can represent others' performance, and reduce the number of these. You can check Dyson et al. (2001) for the thumb rule about the number of variables.
  • asked a question related to Data Envelopment Analysis
Question
18 answers
For Example, I am performing the analysis by considering 5 and 10 parameters with the help of one the MCDM technique. Which case (5 or 10) gives a more realistic output?
Any suggestions for this situation?
Relevant answer
Answer
Good Q
  • asked a question related to Data Envelopment Analysis
Question
2 answers
I am planning to conduct a meta-analysis on the efficiency of MFIs from existing literature, restricted to DEA/ SFA based studies. However, most DEA/ SFA based meta-analyses (Thiam and Bravo-Ureta (2005); Odeck and Bråthen (2012); Kiadaliri et. al (2013) Fall et. al (2018)) use the mean technical efficiency (MTE) as a measure of effect size usually without compensating for sampling bias (they included sample size as a moderating variable instead). Is there any other way to compute a different measure of effect size for DEA/ SFA based studies that compensates for bias like the Hedge's g or Fisher's z?
Relevant answer
Answer
Anirban,
You are into something interesting yet, intricate. I agree with Ahmed that we need to know what your goal is with the analysis/ research. The intricacy of your problem since you are dealing with Meta-analysis of technical efficiency (TE) studies, is that you need to know how representative those individual studies were in terms of representing all the DMU’s in the sectors they addressed. Good scientific papers will always address the representativity of their data sets and, they are normally representative such that Mean TE’s (MTE) can be considered as representative. This is the reason that Thiam and Bravo-Ureta (2005); Odeck and Bråthen (2012); Kiadaliri et. al (2013) Fall et. al (2018)) use the mean technical efficiency (MTE) as a measure of effect size without further consideration of sampling bias. Therefore, and in the first instance, you could proceed by using the reported MTE’s as well.
Next and given that you want to consider sampling bias as something new which has not been considered in the literature of meta-analyses of MTE’s, the only option left for you is to go through the abundant literature and ask the individual authors how representative their data were with regards to the total population of their DMUs. If their studies were not all that representative, you may use the information they provide to correct for sampling bias and then produce a paper that goes further to pinpoint the sampling issue. This may be a cumbersome process that may take time to accomplish since a meta-analysis normally includes many studies.
Finally, if you feel that the TE data should be normally distributed and you have good arguments for it, you could apply e.g., the Fisher transformation; but please explain why. Note now that SFA-based-TE’s for instance, apply non-normal distributions built on real observations!
I hope this helped.
  • asked a question related to Data Envelopment Analysis
Question
5 answers
I have got the time series data (results) of mi, tc, pech and sech. How to elucidate these? How to correlate these with real world meanings?
Relevant answer
Answer
@Ahmed Mohamed Habib Sir, thank you.
  • asked a question related to Data Envelopment Analysis
Question
3 answers
Hello,
I am trying to do some analysis on a large dataset with DEA.
Is there any free software out there that has a slack based Network DEA model (Tone, Tsutsui, 2009)?
It can be Python, Matlab, R or any other kind of software.
Thanks in advance :)
Relevant answer
Answer
Thank you Ashiq Mohd Ilyas I will try them out!
  • asked a question related to Data Envelopment Analysis
Question
5 answers
I am using Simar and Wilson 2007 model with exogenous variables. I have 2 doubts:
(i) 5 out of my 7 exogenous variables are dummy and beforehand I have declared them as factor variables. However the concerned command is not allowing non numeric variables in exogenous category. Please guide.
score<- dea.env.robust (X, Y, W=NULL, Z, model, RTS="variable", L1=100, L2=2000, alpha=0.05)
Here X- dataframe of input variables
Y- dataframe of output variables ( I have only 1 output)
Z- dataframe of environmental/exogenous variables.
(Z<- dataframe_name[c('variable 1', 'variable2', 'variable3', etc)]
Some of these variables are binary and I have already declared them as factor using as.factor(dataframe$variable1) command. However overall Z is a mix of numeric and factor variables.
I am getting this error :
Error in dea.env.robust(X, Y, W = NULL, Z, model = "input", RTS = "variable", : Z has to be numeric matrix or data.frame.
(ii) How to interpret results of this model?
I run the command ,
score$beta_hat_hat , but I am not able to comprehend. Moreover I am not able to get any online resources which explain the results.
Relevant answer
Answer
Dear all,
In chapter 10.3.3 they write that "Most studies using SW2007 approach based their inference mainly on checking whether or not the bootstrap-estimated confidence interval (CI) for a coefficient of interest covers zero (or another hypothesized value)."
  • asked a question related to Data Envelopment Analysis
Question
62 answers
I need a good software that could help to conduct an empirical investigation with efficiency approach: I want to apply the DEA analysis; PIM-DEA for example.
Relevant answer
Answer
Try free version of PIM-DEA at http://deasoftware.co.uk/bookoffer/MSP/
  • asked a question related to Data Envelopment Analysis
Question
9 answers
I am doing frontier analysis of banks and I calculated the robust efficiency scores for each of the bank. Now I want to run a bootstrap truncated regression with efficiency scores as dependent variable to examine their relationship with characteristics of banks. How can I run the method proposed by simar and wilson (20007) in R. Please help in this regards.
Relevant answer
Answer
A Latif Patwary You can use the "lt" function from this package https://cran.r-project.org/web/packages/truncSP/truncSP.pdf if you want to only use truncated bootstrapped regression.
However, if you want to execute simar and Wilson(2007,2011) two step bootstrapping algorithm with environment variables then use "dea.env.robust" from from https://cran.r-project.org/web/packages/rDEA/rDEA.pdf.
if you want to run a simple truncated regression then use "truncreg" function from https://cran.r-project.org/web/packages/truncreg/truncreg.pdf
Hope this will help you. All the best.
  • asked a question related to Data Envelopment Analysis
Question
17 answers
for output oriented one output multiple inputs case
Relevant answer
Answer
Dear Mario
I did estimate the data again by DEA and the correlation between the SFA & DEA is significant with some discrepancies in the ranking.
The data used in the paper include small and large hospitals and urban and remote areas hospitals. this may justify using SFA; the noise in data is a determining factor.
  • asked a question related to Data Envelopment Analysis
Question
4 answers
Can Anyone introduce sample GAMS code for solving Robust DEA Model (preferably based on "Bertsimas and Sim" Robust Model)?
  • asked a question related to Data Envelopment Analysis
Question
13 answers
I'm doing research on the performance efficiency of different oil companies in the world. It has come to my attention that many scholars use DEA Analysis to measure it. However, it is not clear which variable should be treated as an output or input, for instance, should revenue be considered an output? How about oil reserves? Choosing the wrong variable alters the results.
Relevant answer
Answer
DEA is taken as Drug Enforcement Agency, USA . The following inputs and outputs variables should be considered.
• Input would be circulating capital, Investment, labor, selling cost, expense, and energy consumption.
• Output would be revenue, monetary income, profit and net value of output value
  • asked a question related to Data Envelopment Analysis
Question
3 answers
Where I can find a global database free for Arab Maghreb Union (AMU) (classic and Islamic banks) with information about profitability, liquidity, capital adequacy, asset quality ... of Islamic banks worldwide?
Relevant answer
Answer
bloomberg , fitchconnect , orbis ,datastream
  • asked a question related to Data Envelopment Analysis
Question
4 answers
I have a doubt in understanding the concept of input and output models in DEA.
I want to assess the efficiency of the states with respect to number of accidents and Strict rules (e.g., heavy fine).
What would be the input and out put variables in this context?
Could anyone suggest me which DEA approach would be best fit to assess state wise efficiency.
The implications may suggest to minimize the death rate by maximizing the impositions of rules (may be followed by the frontiers).
Relevant answer
Answer
You should determine first the input and output variables for your study based on literature.
Next, the CRS and VRS frontier of DEA analysis generally defined by assumption you make for DMUs (States), eg. If you assume states are homogeneous then choose CRS (CCR) model. I recommend you to go for both scales and see the difference in efficiency scores then decide which scale can be more specific.
Next, the orientation you can choose considering which variable (input or output) can be more control by DMUs.
  • asked a question related to Data Envelopment Analysis
Question
9 answers
Dear All,
Is it possible for a variable to be both input and output in Data Envelopment Analysis?
Relevant answer
Answer
It is not logic at all that the same variable used to be both input and output in the same time, means author don't know the object of the model /study.
In the production system inputs are different to outputs in all sector, i think. If the case that you study the inputs are same outputs, this is other thing you need to explain.
In addition, in the production function there is transformation of input to output, if used the same means there is no production, which is not the case in reality. Also, in the case of cost function is not logic.
  • asked a question related to Data Envelopment Analysis
Question
12 answers
I am currently working on the Container terminals productivity. I will probably use Data Envelopment Analysis or another nonparametric model to determine the efficiency of different ports. However, I am struggling to collect data. Some terminals do not have websites others do not provide enough information about their infrastructure and equipment.
In my model I will use as an output:
- Total container throughput and/or number of ship calls
and as input, I would like to include some of the following indicators:
- Total Terminal area in square meters
- Maximum draft in the terminal
- Total quay length in meters
- STS crane index
- Yard equipment stacking index
- Gantry crane/quay cranes/shore cranes (Number)
- Top loader/side loaders (Number)
- RMG cranes/ RTG cranes (Number)
- Empty handlers (Number)
- Reach Stackers (number)
- Prime movers (number)
- Translifters (Number)
- Cassettes (Number)
- Chassis (Number)
- Number of trucks
- Number of people working at the port
- Number of gates lanes, and railway tracks at the gate
- the number of containers moved per working hour per ship
I am particularly interested in the container terminals in ASEAN.
Relevant answer
Answer
Hello Nikola Kutin ,
Before 2012 a part of statistical data was published in the 'Containerization International Yearbook' , after 2012 You need to search in websites port authorities or government port authority. for some port you can collect data according to many sources , it is dependent from the authorities and the company that study the port statistical, in some case you need to contact the port authorities but it spend more time to receive answer.... etc.
world port source http://www.worldportsource.com/ports/JPN.php can help you to know the website adresse of port.
it is very hard work to collect data for ports .... good luck.
  • asked a question related to Data Envelopment Analysis
Question
3 answers
.If Input values are in figures(Employee cost, Selling Cost, Raw material Cost) and output value in ratios (inventory turnover ratio, Working capital ratio,return on investment ). which model is effective CCR-o or BCC-o or both?
Relevant answer
Answer
Hello Gurmail,
to decide whether to use CCR/BCC model, I recommend using the Banker test. H0 is the assumption of CRS against the alternative of H1 with VRS (Banker and Slaughter 1997; Banker 1996).
DOI: 10.1007/BF00157038
DOI: 10.1287/mnsc.43.12.1709
Furthermore, when I look at your input/output variables, you combine volume measures and ratios. In this case, I recommend reading Dyson et al. (2001).
All the best, Dominic
  • asked a question related to Data Envelopment Analysis
Question
5 answers
The question is in the title. Could you give me resons for using one of them in my second stage DEA analysis?
Relevant answer
A good strategy would be to implement both alternatives and choose based on the results obtained
  • asked a question related to Data Envelopment Analysis
Question
5 answers
Firm operation performance analysis using data envelopment analysis and balanced scorecard: A case study of a credit cooperative bank
Relevant answer
Answer
I would recommend reading the following article:
- James M. Kohlmeyer III and Janet A. Samuels. (2017) Rebecca's Coffee and Tea House: A Strategic Mapping and Balanced Scorecard Case Study. Issues in Accounting Education Teaching Notes 32:2, 13-25.
  • asked a question related to Data Envelopment Analysis
Question
28 answers
I have data (Annual generation, availability, O&M expenses) of three hydropower plants for a period of ten years. I want to apply data envelopment analysis to determine relative efficiency of these power plants. I am considering every power plant as a separate DMU (Decision making unit) for every year. This makes my total DMUs as 3 x 10 = 30. I want to know that for using O&M (Operation & maintenance expenses) in the DEA model, do I need to consider time value of money or write the ten year O&M values as they are obtained from the plants? If yes, how do I incorporate time value of money?
Relevant answer
Answer
Tme value of money is taken into account by discounting the value for O&M (Operation & maintenance expenses) by a discount rate. Discount rate is the company's average cost of borrowing money from equity or from banks.
  • asked a question related to Data Envelopment Analysis
Question
3 answers
I am doing research related to efficient fund utilization of Swachh Bharat Mission by different states of India. I have collected data related to institution, demography, ease of doing business, etc. I have calculated relative efficiencies of Indian states towards utilizing the funds for Swach Bharat Mission and delivering tangible outcomes. I have used the technique of Deta Envelopment Analysis for the same. Kindly help me with the issue. I have tried bootstrapping, but it did not work well.
Relevant answer
Answer
The short answer is you don't. You don't sat anything about the DV so I'll assume we're talking OLS regression. other choices a re some what different. I'll tell you a rule of thumb for OLS: A min of 5 obs/IV. You are nowhere near that so standard OLS is out. I am going to assume that you want to do prediction-you don't say but you have to get rid of some IVs. I will suggest adaptive one problem down.
lasso variable selection.. See the stuff at this link including the papers esp concerning the oracle property:
. Here are the reasons:.
1 lasso runs even if p>n
2. The oracle property says that the variables selected are the optimal predictor set of you candidate IVs..- solves this problem
  • asked a question related to Data Envelopment Analysis
Question
3 answers
A number of research papers (Bravo-Ureta et al. 2011; Rodriguex et al. 2007; Greene 2010, etc.) investigating the effect of a treatment on the some kind of technical efficiency (TE) consider stochastic production frontier (SPF) for technical efficiency estimation, employing Stochastic Frontier Analysis (SFA) instead of Data Envelopment Analysis (DEA), which is followed by matching approach like Propensity Score Matching to eliminate bias in impact evaluation. Is there any assumption/ limitation within DEA that restricts its use with matching algorithms or is there any added benefit of using matching together with SFA or is it just a research gap that can be explored?
Relevant answer
Answer
Thank you
Ahmed Mohamed Habib
for your reply. I agree with your point that the application of either DEA or SFA for efficiency estimation is fairly common and each method has its own set of benefits and drawbacks. However, what I am looking to understand is why research comparing technical efficiency (TE) across treatment and control groups prefer to use SFA instead of DEA as in and other similar studies.
  • asked a question related to Data Envelopment Analysis
Question
8 answers
Has anyone used Data envelopment analysis (DEA) software EMS: Efficiency Measurement System available at http://www.wiso.uni-dortmund.de/lsfg/or/scheel/ems to calculate Malmquist index? I really need some advice.
Relevant answer
Answer
Using the DEAP Version 2.0 Data envelopment analysis (computer) program by Coelli T.J.
TFP indices in Malmquist DEA can be extracted easily via DEAP.
  • asked a question related to Data Envelopment Analysis
Question
4 answers
i need help on the contemporary model of Data Envelopment Analysis applicable in Micro finance and banking institutions.
Relevant answer
Answer
Dear Christian,
There are no new MODELs of DEA, just variations of Inputs and Outputs. To get inspiration, look at old articles (1990s) of Alexander Vaninsky -- he is the only real matematician working on DEA in a very original way.
  • asked a question related to Data Envelopment Analysis
Question
9 answers
I am using Data Envelopment Analysis (DEA) and Stochastic Frontier Analysis (SFA) to measure the eco-efficiency of dairy farms. I would like to use the "percentage of grasslands in the agricultural area" as an input variable. This variable is expressed in % (from 0 to 100%). Can I include variables expressed as percentage in DEA and SFA models? If not, how to deal with such variables?
Relevant answer
Answer
agreed with the above answers and Magnus Richter but the most simple is to convert it into log. the coefficient will be automatically in percent.
  • asked a question related to Data Envelopment Analysis
Question
33 answers
Dear All;
I have a confused due to determining input and output in DEA. Could you help me, please? Suppose that, There are some inputs (i1, i2, i3) but I want to combine these under a group name and then I want these (i1, i2, i3) to be a singular input. Is this possible? Can I combine my multi inputs to a single input like Exploratory Factor Analysis?
All the best.
Relevant answer
Answer
I will try to do PCA-DEA as soon as possible. And I will share the results of PCA-DEA on this topic.
  • asked a question related to Data Envelopment Analysis
Question
4 answers
I mean for the product ouctome or value.
If so, how can DEA consider effective use, iddle time of the product, time while damaged, time while misused, while stored, while not reentering to a new consumption or reprocessing cycle?
Relevant answer
Very interesting issue.I think that considering the widespread use that DEA has had in the last decade, it could be possible to adapt it for efficiency analysis of reverse logistic products. In my opinion the indicators mentioned could be used, with emphasis on time while damaged, time while misused, while not reentering a consumption or reprocessing cycle and other metrics related to the strategies adopted in the reverse logistic. It is also to be consider new circular approaches to manage end of life cycles and products. Regards
  • asked a question related to Data Envelopment Analysis
Question
6 answers
I am using Data Envelopment Analysis (DEA) and Stochastic Frontier Analysis (SFA) to measure the eco-efficiency of dairy farms. I would like to use the quantity of chemical fertilizers as an input. Some farms, e.g. organic farms, do not apply any chemical fertilizers and have a 0 value for this variable. How can I deal with 0 values in DEA and SFA inputs and outputs? Is it correct if I replace the 0 with a 1 (knowing that 1 is a very small value for total fertilizer application on a farm and so it is very similar to having no fertilizer application at all)?
Relevant answer
  • asked a question related to Data Envelopment Analysis
Question
4 answers
I want to deine targets for DMUs with a DEA model with one or two inputs and two outputs. What R package would you recommend, and how are the targets extracted? Thanks for any help.
Relevant answer
Answer
Yes sir the Slack DEA model produce targets in Benchmarking package,
Despite these packages in R, an Excel program DEAsolver also produce targets.
  • asked a question related to Data Envelopment Analysis
Question
2 answers
When conducting a two-stage Data Envelopment Analysis, I have to perform the first stage on DEAP 2.1 to obtain the technical efficiency estimates, then perform the second stage (regression between technical inefficiency and the operational environment & enterprise-level variables) using other programs such as STATA. It is time consuming procedures! So, is there a possibility to perform the two stage using DEAP 2.1, and if so, how?
Relevant answer
Answer
Win4deap software has facility to compute the 2 stage DEA analysis, it is an integrated software of deap.
  • asked a question related to Data Envelopment Analysis
Question
45 answers
Dear collegues, researchers and practicioners on DEA.
In the 16th International Conference on Data Envelopment Analysis we presented deaR, a new R package for DEA. Now, it is a pleasure for me to announce that deaR is available to be installed and used.
deaR has been designed and built so that non-R users can easily use it. This package allows to run a wide variety of models based on DEA:
  • Conventional DEA models: CCR, BCC, directional distance function multiplier, additive, non radial, sbm, radial super efficiency, additive super efficiency, sbm super efficiency, cross efficiency, bootstrapping, etc.
  • Malmquist index
  • Fuzzy DEA models: Kao and Liu´s model, some possibilistic DEA models, fuzzy cross efficiency.
You can get a brief introduction tutorial to install and use deaR (in English, Spanish, and Chinese) by clicking on the following link:
deaR is not only oriented to research but also teaching. For that reason, deaR provides some datasets that come from articles already published. These datasets are used in the deaR function examples to replicate the results of the articles.
We would really appreciate if you could spread the information about deaR among your colleagues and students.
We will release a deaR shiny version (an interactive web app) son. We will inform you when it is available.
Any comments and suggestions to improve deaR will be really appreciated. We also accept suggestions of DEA models to be considered for being programmed in new versions of deaR.
Best regards.
Relevant answer
Answer
deaR has been updated. The new version (1.1.0) includes:
- several decompositions of the malquist index (sequential, global, generalized, etc.)
- cost, revenue and profit models
- undesirable (and separable) inputs/outputs (according to Tone 2003) in sbmeff model
- fixed some bugs
  • asked a question related to Data Envelopment Analysis
Question
12 answers
If you are interested in learning about our (Co-authored with Mosayeb Dashtpeyma & Professor Reza Ghodsi) new article, entitled "Developing the resilient solar energy management system: a hybrid qualitative-quantitative approach", which published in International Journal of Ambient Energy, please click or use the following link:
Relevant answer
Answer
Ohhh.... thank you... yes of course¡....
  • asked a question related to Data Envelopment Analysis
Question
8 answers
I am a beginner of studying DEA model to analysis water use efficiency, and I choose modified dea model, which could consider undesirable output and input. When I read the related published journals, I found that is hard to understand. Thank you all.
Relevant answer
  • asked a question related to Data Envelopment Analysis
Question
5 answers
Does modelling corporate governance variables in bank intermediation function in a data envelope analysis (DEA) framework resolve the endogeneity to some extent?
Relevant answer
Answer
Hello dear I am very happy to read the questions and find the answers
  • asked a question related to Data Envelopment Analysis
Question
4 answers
If you are using MaxDEA Software then please help me to measure sequential and global malmquist indices of 15 DMU's for 11 years. I promise will add the person as a co-author . Thank you very much.
Relevant answer
Answer
Akber Aman Shah Thank you very much for the suggestion. Yes DEAP can be used to measure Malmquist Indices however, I have to assume VRS, no-technical regress and have to decompose it into finer measures not only TC and EC. Moreover,have to bootstrap the indices.
  • asked a question related to Data Envelopment Analysis
Question
7 answers
I am looking for free software that perform Data Envelopment Analysis. I have downloaded one software but it can analyze less than 20 DMUs but I need to analyze more than 30 DMUs. I would welcome suggestions. Thank you!
Relevant answer
Consult Tim Coellis book.
  • asked a question related to Data Envelopment Analysis
Question
25 answers
I am performing SFA based on distance functions with STATA. After more than several outputs, I realised that the sign or significance of the parameters may change depending on the order that inputs and outputs are introduced. This also applies for environmental variables in the inefficiency term, the mu may disappear, but if changing the order it comes back again. Is this a known problem, but not acknowledged? Also, how could I increase the number of iterations (likelihood) in STATA from the usual one (100) to maybe 300?I am currently using sfpanel package within STATA. Thank you in advance for your time
Relevant answer
Answer
HI ANE can I have distance function command in stata,how can I have environmental variables? what about metafrontier? any one can help me plz?my data are cross-section
  • asked a question related to Data Envelopment Analysis
Question
11 answers
I am a nurse scientist and a novice researcher in the area of optimization. Might I ask a favor of your easy and comprehensive explanations on the difference between optimization and data envelopment analysis? Thank you so much for your help in advance.
Relevant answer
Answer
Saeed Assani How different is the following article from your article (2018)?
Eslami, R., Khodabakhshi, M., Jahanshahloo, G.R., Lotfi, F.H., & Khoveyni, M. (2012). Estimating most productive scale size with imprecise-chance constrained input–output orientation model in data envelopment analysis. Computers & Industrial Engineering, 63(1), 254-261. doi:10.1016/j.cie.2012.02.009 (http://www.sciencedirect.com/science/article/pii/S0360835212000617)
  • asked a question related to Data Envelopment Analysis
Question
5 answers
Can we do that? And if yes, assuming that we have negative and positive output features, how to deal with them? By negative and positive features I do not mean value, but a feature like happy and sad and happy 5 is good sad 5 is bad. One thing that tried is to use the negative features as inputs and positive features as output, results did not make much sense!
Thanks
Relevant answer
Answer
Thanks Saeed, Sobhan, and Samah,
I am not a DEA expert but trying to help a colleague in ranking DMUs. Now, from Sohban answer, I am having 10 DMUs and 10 output variables, it seems that I need to remove some of the features to maintain robustness. Also from Samah and Sobhan, I have two suggestions to go forward: trying output-oriented weighted additive model or BCC-O!
  • asked a question related to Data Envelopment Analysis
Question
2 answers
The main premise of the SFA approach is a recognition that whether allDMUs are efficient or not is an empirical question that can and should be statistically tested against the data, while allowing for a statistical error. To enable such testing, the SFA approach provides a framework where production relationship is estimated also as aconditional average (of outputs given inputs and other factors, in the case of productionfunction) but the total deviation from the regression curve is decomposed into two terms
- statistical noise and inefficiency. Both of these terms are unobserved by a researcher butwith relatively mild assumptions the different approaches within SFA allow the analyst to stimate them for the sample as a whole (e.g., representing an industry) or for each individual
DMU.
Relevant answer
Answer
Thanks
  • asked a question related to Data Envelopment Analysis
Question
8 answers
I need to calculate technical efficiency using the DEA. The data I have is quarterly. Can you advise?
Relevant answer
Answer
Thank you dear Saeed
  • asked a question related to Data Envelopment Analysis
Question
14 answers
Can some please suggest an easy-to-read/understand book on data envelopment analysis (DEA) for the beginners that explains the usages/interpretation of various DEA models without providing the mathematical details. Any help would be highly appreciated. Thanks,
Relevant answer
Answer
I'm sending a 60 books about DEA for free.
Visit:
If you liked my statement of DEA books, make a recommendation.
  • asked a question related to Data Envelopment Analysis
Question
23 answers
Please i will use Network DEA to Education sector, do you know the software that i can use for NeworK DEA model.
Thank you so much
Relevant answer
Answer
I saw that this web site dont have the full text. What your email that i can send to you?
  • asked a question related to Data Envelopment Analysis
Question
3 answers
I am trying to identify important variables for my study of Technical efficiency & scale efficiency of Indian Insurance Companies in India, suggest me input and output variables which should be considered for Data Envelopment Analysis (DEA).
Thanks in advance!
Relevant answer
Answer
Check this article:
The inputs were claims incurred and operating expenses. The outputs were earned premiums and investment income.
--> dynamic DEA model
  • asked a question related to Data Envelopment Analysis
Question
7 answers
In CRS model, the input and output oriended objective function values are reciprocal to each others. But why not in VRS?
Relevant answer
Answer
It is not sufficient to attribute it just to the difference in the orientation between the CCR and the BCC models since "maximizing the outputs subject to the given inputs" and "minimizing the inputs subject to the given outputs" under CRS assumtpion provide reciprocal efficiency scores. Thus, we firstly have to consider the additional free in sign variable in the multiplier BCC model and the additional constraint about the lambdas (Σλ=1) in its envelopment counterpart. This changes the shape of the frontier (BCC efficient frontier) and allows, besides CRS, for increasing and decreasing returns to scale. The above, in conjuction with the orientation that guides the projections, provides non-reciprocal efficiency scores between input and output orientation under VRS assumption.
For a schematic represenation of the above check the attached image.
  • asked a question related to Data Envelopment Analysis
Question
1 answer
I want to be helped from a professor in data envelopment analysis special in cost efficiency from Denver Colorado?
Relevant answer
Answer
Cost efficiency scores can easily computed from WinDeap Software package which is freely available on web,
for theoretical study about DEA you can prefer various books which are available online.
You can also visit YouTube Channel "Club of Research Scholars" for Data Envelopment Videos.
  • asked a question related to Data Envelopment Analysis
Question
9 answers
Thinking about a classroom, its teaching, its students and its evaluation, I have problems to characterize the possible inputs, to generate the products or outputs that the method raises. Although I am aware that it depends on the research problem, I do not quite understand how to consider it, without falling into reductions in the model to be used.
Relevant answer
Answer
Appreciated Maria M
My interest coincides with yours, but I'm glad you address your questions to Magnus Richter, since his answer will surely help me understand the use of the DEA method
Grateful for your interest
Regards
Chema
  • asked a question related to Data Envelopment Analysis
Question
4 answers
I want to asses the efficiency of the supply chain using DEA. However, DEA's approach is based on relative efficiency; meaning it seeks the best practice among same organisations . ​Therefore, Can we benchmark the firm to its optimal performance or do we have to benchmark it against other branches ?
Relevant answer
Answer
Implementing the data envelopment analysis (DEA) approach requires decision-making units (DMUs), inputs and outputs (as the criteria for evaluating these units). If the nature of each supply chain member dose not important, you can simply use this method. But in reality, and due to the difference in the nature of each member, it maybe possible that you can use the multi-group DEA method.
  • asked a question related to Data Envelopment Analysis
Question
8 answers
I am having problem with the Frontier v4.1 software, 
By using the frontier v4.1 software I estimated the cost efficiency scores. The problem is for all firms i get efficiency scores greater than 1 the eff. mean as in the output file of the Frontier software = 0.14561349E+01 or like it appears in the excel sheet = 1.46E+00 Given that i have tried all kinds of models; cross-sectional and panel, i have made the necessary transformations on the inputs, and i also applied DEA by the Deap software on the same data and i get eff. mean = 83% So what could have gone wrong ??
Relevant answer
Answer
Yes, it will be greater than one due to algorithem behind it. You need to convert it into comparable mode by taking 1/your score.
  • asked a question related to Data Envelopment Analysis
Question
3 answers
Hello everybody.DEA is a non parametric analysis.Can it be used as a quality indicator tool or for supporting the quality indicator in finding the efficient use of a particular unit,especially in hospitals? Is it possible it can be used for research purposes?
Relevant answer
Answer
Ms.Alma Braimllairi Spaho thankyou for the answer.I just want to clarify when applying weight restrictions to the inputs/outputs can into be done according to policy makers decision.Also DEA is helps for technical efficiency and how we can justify it for measuring the quality? Thankyou
  • asked a question related to Data Envelopment Analysis
Question
4 answers
Could anyone help to find free software's to perform data envelopment analysis, besides classical methods of DEA, I have special interest in software that directly consider undesirable outputs.
Relevant answer
Answer
DEAP V 2.1
  • asked a question related to Data Envelopment Analysis
Question
13 answers
In primal form of DEA CRS model, we are going to maximize the efficiency of the reference firm. But how is it possible that in the dual form also, we are minimizing the efficiency of the reference firm? What is the physical interpretation of the dual version? Please see the attached file.
Relevant answer
Answer
There are two things to keep in mind when dealing with DEA models. Input oriented and output oriented objective function. In the input oriented you minimize the ratio of inputs to outputs. In otherwords, you are seeking here the minimum input combination that produce specific level of output, Where as in the output oriented objective function you maximie the ratio of outputs combination at specific level of inputs. Your case of theta minimiation refers to the first case mentioned above.
  • asked a question related to Data Envelopment Analysis
Question
9 answers
I am looking for the answers of the following questions. Any kind of help is highly appreciated.
1. In the primal form of DEA, we want to maximize the efficiency (θ) of any Decision Making Unit (DMU). But in case of dual form, what (i.e. which parameter) we want to minimize?
2. What is the physical significance/interpretation of the decision variable(s) (λ1, λ2, λ3...) used in the constraints of dual form? In other words, what actually λ1 or λ2 these parameters represent and what do their values represent for a particular decision making unit (say DMU2), when they are addressed in the efficiency reference set or benchmarks?
3. What are the physical interpretations of the constraints used in the dual form?
Thanks in advance...
Relevant answer
Answer
I upload DEAwithCrossEfficient.pdf that is one of first chapter of DEA with CCR and Inverted DEA models and crossEficient published from Amazon.
I explain how to build LINGO SEts model and DEA.
  • asked a question related to Data Envelopment Analysis
Question
4 answers
I have built a full Data Envelopment Analysis model but do not understand what I am meant to be looking at to answer the above question?
Some hints, pointers and tips would be greatly appreciated!
Relevant answer
Answer
Yes Ehsan is right. Compute super efficiencies and you will get a ranking of efficient units as well. You can also compute cross efficiencies to compare them. Returns to scale will also give some insight into their performance. Also compare for how many inefficient units are these units the peers. This also gives a ranking structure to the efficient units.
  • asked a question related to Data Envelopment Analysis
Question
5 answers
Data Envelopment Analysis (DEA) is usefull to assess an efficiency of HEIs but as far as I know there are not to many papers on the implementation of DEA to assess and compare national system of HE. Do you know any papers on that subject?
Relevant answer
Answer
I evaluated several Japanese industries, not education.
But, it is the same problems for DEA.
I published DEA from Amazon kindle version.
See my anouncement of DEA on RG.
I open my DEA code in the book.
Unlimited users are free.
The Price is $9.99.
  • asked a question related to Data Envelopment Analysis
Question
5 answers
DEA software for bootstrapping
Relevant answer
Answer
Dear sir,
You can use Stata, Eviews and Shazam to run Bootstrap.
But there's the point that with this software you can not get the corrected bias estimators for each DMUs.
So, I suggest using the Excel software. In this software, you must use the correct command to get the corrected bias estimators and then try to estimate the distances.
  In the this regard, I sent you an attachment file that can help you with this.
I hope it could help...
Alireza
  • asked a question related to Data Envelopment Analysis
Question
7 answers
I have beening trying to work out a slack-based model which several undesirable outputs is taken into consideration.And I've finished the MATLAB code.But the problem is that the dataset contains more than 190,000 DMUs,so the program runs quite slowly. Can anybody help me with this?
Relevant answer
Answer
I just checked, MaxDea Ultra can solve your problem because it consider the case of undesirable outputs. 
Good luck!