3.8.1 Removing experts
Course subject(s)
Module 3. Performance-based weights and the Decision Maker
Recall the previous example about the correlation between intelligence in primary school children and other personality traits and success in several aspects of life. The experts assessments are provided below.
Question | Realization | Expert A
5% 50% 95% |
Expert B
5% 50% 95% |
Expert C
5% 50% 95% |
---|---|---|---|---|
1 | 24 | 2 5 7 | 20 23 34 | 20 25 28 |
2 | 11 | 12 13 15 | 8 10 11 | 10 13 15 |
3 | 68 | 87 89 92 | 60 70 90 | 65 67 70 |
4 | 47 | 2 5 8 | 20 35 45 | 42 44 46 |
5 | 31 | 48 50 52 | 30 35 40 | 32 33 35 |
As mentioned in the hint of the previous question, the intrinsic range of Question 1 is [0,37.2].
Consider now removing Expert 1 from the pool with experts. We are left with Expert 2 and Expert 3 assessments.
We see how the intrinsic range of Question 1 has changed when Expert 1 assessments have been removed!
Consequently, the information score of Expert 2 and Expert 3 for Question 1 will change when Expert 1 is removed!!
This is because the intrinsic range, through it’s values L* and U* is part of the formula that compute the information score.
Decision Making Under Uncertainty: Introduction to Structured Expert Judgment by TU Delft OpenCourseWare is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Based on a work at https://online-learning.tudelft.nl/courses/decision-making-under-uncertainty-introduction-to-structured-expert-judgment//.