دانشگاه آزاد اسلامی واحد علوم و تحقیقات

 آمار

تعداد نشریات50
تعداد شماره‌ها2,232
تعداد مقالات20,475
تعداد مشاهده مقاله25,227,120
تعداد دریافت فایل اصل مقاله22,858,726
Dalili Yazdi, Hoda, MOVAHEDI SOBHANI, FARZAD, Kazemipoor, Hamed. (1402). Comparison of the combined methods PCA-DEA (principal component analysis - data envelopment analysis) and FA-DEA (factor analysis - data envelopment analysis) in the presence of negative data. , (), -. doi: 10.30495/jnrm.2023.71552.2377
Hoda Dalili Yazdi; FARZAD MOVAHEDI SOBHANI; Hamed Kazemipoor. "Comparison of the combined methods PCA-DEA (principal component analysis - data envelopment analysis) and FA-DEA (factor analysis - data envelopment analysis) in the presence of negative data". , , , 1402, -. doi: 10.30495/jnrm.2023.71552.2377
Dalili Yazdi, Hoda, MOVAHEDI SOBHANI, FARZAD, Kazemipoor, Hamed. (1402). 'Comparison of the combined methods PCA-DEA (principal component analysis - data envelopment analysis) and FA-DEA (factor analysis - data envelopment analysis) in the presence of negative data', , (), pp. -. doi: 10.30495/jnrm.2023.71552.2377
Dalili Yazdi, Hoda, MOVAHEDI SOBHANI, FARZAD, Kazemipoor, Hamed. Comparison of the combined methods PCA-DEA (principal component analysis - data envelopment analysis) and FA-DEA (factor analysis - data envelopment analysis) in the presence of negative data. , 1402; (): -. doi: 10.30495/jnrm.2023.71552.2377

Comparison of the combined methods PCA-DEA (principal component analysis - data envelopment analysis) and FA-DEA (factor analysis - data envelopment analysis) in the presence of negative data

Journal of New Researches in Mathematics
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 20 شهریور 1402  XML
نوع مقاله: research paper
شناسه دیجیتال (DOI): 10.30495/jnrm.2023.71552.2377
نویسندگان
Hoda Dalili Yazdi1؛ FARZAD MOVAHEDI SOBHANI email 1؛ Hamed Kazemipoororcid 2
1Department of Industrial Engineering, Islamic Azad University, Science and Research Branch, Tehran, Iran.
2Department of Industrial Engineering, Islamic Azad University, Central Tehran Branch, Tehran, Iran.
چکیده
One of the significant issues with DEA occurs when there is the extensive number of inputs and outputs compared to the number of DMUs. This situation leads to attribute one to the efficiency score of a large number of units, as a result, the ranking power of the DEA becomes further moderated. By combining dimension reduction methods such as principal component analysis (PCA) and factor analysis (FA) with data envelopment analysis (DEA), the mentioned problem can be solved. In this paper, the effectiveness of two dimension reduction methods, named PCA and FA, combined with DEA has been compared. The superiority criterion of these two methods is based on the reduction in the number of efficient units. By implementing both integrated methods on the data of companies in the Iranian stock market, the effectiveness of these two methods have been compared. Since the data available in the stock market include both positive and negative values, the integrated methods presented in this research are able to determine efficiency for units with both positive/negative data in their input and output indices. The number of efficient units determined by both methods are not different significantly. Both integrated methods are successful in reducing the efficient units, so another index called (MSE) is used to determine the superiority of the methods. This index shows the difference between efficiency scores calculated by integrated methods and efficiency scores calculated by DEA (SBM). This index for FA-DEA is less than for PCA-DEA, which indicates the superiority of FA-DEA.
کلیدواژه‌ها
Data Envelopment Analysis (DEA)؛ Principle Component Analysis (PCA)؛ Factor Analysis (FA)؛ Efficiency score and Negative Data
آمار
تعداد مشاهده مقاله: 141


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب