Dear Researchers,
There are a lot of techniques like AHP, ANP, DANP etc wherein a group of experts are requested to give their opinions. My specific questions are:
1. How is the sample size determined?
2. What should be the sufficient sample size?
3. How sampling is carried out?
4. Any specific rule to determine the composition of the sample?
It would be of great help if any researcher answer my questions and share supportive literature.
With best regards,
Norah
Hi Norah,
Most of the techniques you have mentioned above, are consensus based MCDM methods. We prefer to call it "Experts Panel" in MCDM methods, "Sample size" is usually used in case of empirical (survey) based research.
These are my answers to your questions.
1. There is no hard and fast rule to determine, the number of experts, from which you collect the response or opinion. Generally, it should be between 5 and 10.
2. The upper limit of number of experts should not exceed 10. Since responses from more than 10 number of experts lead to high degree of inconsistency, and hence make your results unreliable.
3. Generally the experts are chosen in the following ways.
i. Based on their subject knowledge and industry experience, pertaining to your case problem.
AND
ii. Based on authors professional and personal contacts (like convenience sampling)
4. In most of the MCDM papers I have seen, they consider 80 % industry practitioners and 20 % academicians as experts. Further, the industry practitioners may be from different area like, sales, operations, finance, maintenance with an ample years of experience.
The individual responses from each experts are collected separately and they are further aggregated (averaged), in order to be used as an input to any MCDM tool.
I have used DANP (DEMATEL + ANP) for my research work. You can refer and cite me, if you find it's helpful.
Article A hybrid approach for quantifying supply chain risk and prio...
I hope, this help you!
Best Regards.
Pradeep
Refer the article
https://www.emerald.com/insight/content/doi/10.1108/BIJ-10-2017-0281/full/html
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Sampling Design
- Sample Size