I conducted AHP using 3 pairwise comparisons. Unfortunately the CR comes out as 0.302. A balanced scale using principal eigen vectors also results in a CR of 0.22. Is there any way to be able to move forward with these results?
Saaty has stated that just because the ratio is greater than 0.1 does not mean that there is certain inconsistency. It means that human decision makers and respondents are human.
In my opinion that level of inconsistency is not acceptable, especially in a 3x3 matrix. Fortunately, since this is a small matrix it is also easy to check where the possible error is. Maybe the error is not in the matrix itself, but in the way that the criteria are being compared, I mean that maybe the model is incomplete (breaking Axiom4) or some criterion does not belong to that comparison matrix (breaking Axiom2). You have to check these options before making peace with that results.
How many alternatives and attributes do you have?
Maybe you can hypothesize cr=0.15. As you know CR=0.1 is Prof.saaty's suggestion.
I don't suggest you to use cr=0.15 if you have small matrix.
I think, that level of inconsistency is not acceptable
- Badges
- Science topic
- Similar topics
- Statistics
- Survey