I do not understand what you mean by 'Regular questionary'

Do you mean comparing 40 alternatives an evaluating them based on criteria?

Could you pls clarify?

Dear Chinonso Udokporo

No you can not use direct questionnaire. There is direct comparisons using saaty scale. But you can use transitive property to shorten the size of questionnaire. If you need further assistance then acknowledge me.

Abid

You can separate the evaluation of priorities and evaluation of alternatives using different methods. 40 alternatives - resulting in 780 (!) pairwise comparisons - cannot be handled by any decision maker. The recommended maximum number is the magic number 7 plus or minus 2. This applies to both, criteria and alternatives.

One way would be, to structure your alternatives hierarchically, i.e. group them in categories, if possible.

The other way would be to use AHP for the prioritization of  criteria only, and any other method for the evaluation of alternatives with respect to those prioritized criteria. It could be a simple table with a yes/no or applicable/not applicable scale, or any other scale, e.g. Likert scale, how good the individual alternative matches the specific criterion.

I did this in some of my projects, using AHP software for criteria prioritization (see e.g. http://bpmsg.com/academic/ahp.php), and an excel sheet for alternative evaluation. 

It is not quite clear to me what you mean with "regular scale". I assume that you have 40 alternatives and few criteria. In this case, you may use AHP to evaluate the criteria as Klaus Goebel proposed in the previous response. The you can interpret these criteria values as weights for alternative, but you have to know what the weigh!  Sometimes people have the maximum values in their mind, when they weigh the criteria, Sometimes the sums. 

Of course, there are also other methods to find the weights. You may e.g. ask people to make pairwise comparisons with some alternative and use this information to estimate the weights,

Anyway, it is not quite clear to me what you mean.

I fully agree with Dr. Korhonen, and certainly it will be nice if you can clarify a little more your question

In addition, you can use ACTUAL weights for criteria using Shannon's entropy formula,  instead of SUBJECTIVE weights, and then use them in any heuristic model. Dr. Zavadskas has experience on this method. Good Luck!!!!

Hello all! Thank you for all your answers. What I mean by regular scale is the likert scale-say a 5 or six point likert scale.

My solution is same as what is suggested by Klaus Goepel.

I think that I have understood your question as I am having same problem. I am preparing a vendor rating system for a small manufacturer. Now, while I have used AHP for prioritizing the criterion(and the sub criterion) I cannot do pair wise comparisons for vendors as there are 44 of them.

The solution I have come up with is to rate the vendors based on their performance with respect to the criterion on a scale of 1-9 (based on their performance) and then multiply it with the respective criteria weight to get the score.

Afterwards I can add up all the scores that a vendor gets in order to get his individual rating. This method will be fool proof as addition of any new vendor will not affect the rating of the others.

I hope this answer helps you. 

I realized the same, that is why I mentioned giving scores to vendors on 1-9 based on their performance. 9 being ideal and 1 being the worst they could perform.

I am also thinking of using TOPSIS instead as it will be better in data normalization, actually I am still working on the case and will update once I get a working solution.

Thank you Mr. Mukherjee for your inputs.

Maybe you can use a method, I used in a different context: setting up a combined performance index as key performance indicator (KPI) in a company dashboard. Each individual performance indicator (= criterion) is mapped to an index range (0 to 100 or -20 to 100 in my case). The scales were developed using a base and target value for each criterion, but you can also use any other scale, like Likert scale. Then I combined the individual indexes (dimensionless) to a summary KPI, weighted by the weights of each criterion.

I made a short video in 2010 explaining the method with an example excel spreadsheet for download: http://bpmsg.com/combined-performance-index/