|
|
Publication
|
| Research Title |
Variable Selection in Data Envelopment Analysis Using Stepwise Modeling Approach: A Case Study of Tourism Sector in Indonesia |
| Date of Distribution |
9 August 2018 |
| Conference |
| Title of the Conference |
2018 International Conference on “Physics and Mechanics of New Materials and their Applications” (PHENMA 2018) |
| Organiser |
Korea Maritime and Ocean University, Busan, Republic of Korea; Southern Federal University, Russia; and National Kaohsiung Marine University, Taiwan, ROC. |
| Conference Place |
Korea Maritime and Ocean University |
| Province/State |
Busan, Republic of Korea |
| Conference Date |
9 August 2018 |
| To |
11 August 2018 |
| Proceeding Paper |
| Volume |
PHENMA 2018 |
| Issue |
August 2018 |
| Page |
120 |
| Editors/edition/publisher |
Korea Maritime and Ocean University, Busan, Republic of Korea |
| Abstract |
Data Envelopment Analysis (DEA) is a non-parametric technique for measuring the relative efficiency of a set of similar units, usually referred to as Decision Making Units (DMUs), which convert multiple inputs to multiple outputs. One of the interesting research subjects in DEA is to choose appropriate input and output indicators. Besides the choice of DEA technology (model), selecting inputs and outputs is the other crucial consideration, which the analyst must keep in mind. Unfortunately, there has been inadequate attention to this issue, while most attention has been given to building models. Several researchers have just chosen variables subjectively or calculated efficiency based directly on others’ selection results. In this paper will apply the stepwise modelling approach to conduct the variable selection in DEA. This method is intended to produce DEA models that include only variables with the largest impact on the DEA results. The backwards approach of stepwise modeling starts by considering all possible input and output variables in the DEA model. At each step, one variable is dropped from the model by analyzing the efficiency scores of the DMUs. Theoretically, the method can continue until only one input and one output variable remain in the model. From a practical viewpoint, stopping rules can be incorporated using the decision criterion to create a parsimonious DEA model. In this study, we illustrate these methods using datasets of a case study of tourism sector in Indonesia. |
| Author |
|
| Peer Review Status |
มีผู้ประเมินอิสระ |
| Level of Conference |
นานาชาติ |
| Type of Proceeding |
Abstract |
| Type of Presentation |
Oral |
| Part of thesis |
true |
| Presentation awarding |
false |
| Attach file |
|
| Citation |
0
|
|
|
|
|
|
|
|
|
Journal Publication
ไทย