Sensitivity Analysis in AHP

Sensitivity analysis is a fundamental concept in the effective use and implementation of quantitative decision models, whose purpose is to assess the stability of an optimal solution under changes in the parameters. (Dantzig)

Weighted sum model (Alternative Evaluation)

In AHP the preference Pi of alternative Ai is calculated using the following formula (weighted sum model):
(1)with  Wj the weight of criterion Cj, and aij the performance measure of alternative Ai with respect to criterion Cj. Performance values  are normalized.
(2)

Example


Table 1

Sensitivity analysis will answer two questions:

  • Which is the most critical criterion, and
  • Which is the most critical performance measure,

changing the ranking between two alternatives?

Continue reading Sensitivity Analysis in AHP

Weight Uncertainties in AHP-OS

It is now possible, to analyse the weight uncertainties in your AHP-OS projects. When you view the results (View Result from the Project Administration Menu), you see the drop-down list for different AHP scales and a tick box var is shown.

Tick var and click on Refresh. All priority vectors of your project will display the weight uncertainties with (+) and (-).

Continue reading Weight Uncertainties in AHP-OS

Why the AHP Balanced Scale is not balanced

As part of my current work about AHP scales, here an important finding for the balanced scale:

Salo and Hamalainen [1] pointed out that the integers from 1 to 9 yield local weights, which are not equally dispersed. Based on this observation, they proposed a balanced scale, where local weights are evenly dispersed over the weight range [0.1, 0.9]. They state that for a given set of priority vectors the corresponding ratios can be computed from the inverse relationship

r = w / (1 – w)      (1a)

The priorities 0.1, 0.15, 0.2, … 0.8, 0.9 lead, for example, to the scale 1, 1.22, 1.5, 1.86, 2.33, 3.00, 4.00, 5.67 and 9.00. This scale can be computed by

wbal = 0.45 + 0.05 x     (1b)

with x = 1 … 9 and

 (1c)

c ( resp. 1/c) are the entry values in the decision matrix, and x the pairwise comparison judgment on the scale 1 to 9.

In fact, eq. 1a or its inverse are the special case for one selected pairwise comparison of two criteria. If we take into account the complete n x n decision matrix for n criteria, the resulting weights for one criterion, judged as x-times more important than all others, can be calculated as:

(2)

Eq. 2 simplifies to eq. 1a for n=2.

With eq. 2 we can formulate the general case for the balanced scale, resulting in evenly dispersed weights for n criteria and a judgment x with x from 1 to M:

(3)

with

(3a)

(3b)

(3c)

We get the general balanced scale (balanced-n) as

(4)

Continue reading Why the AHP Balanced Scale is not balanced

Incoming search terms:

  • AHP scales 0 to 9

AHP Judgment Scales

The original AHP uses ratio scales. To derive priorities, verbal statements (comparisons) are converted into integers from 1 to 9. This “fundamental AHP scale” has been discussed, as there is no thoretical reason to be restricted to these numbers and verbal gradations. In the past several other numerical scales have been proposed [1],[3]. AHP-OS now supports ten different scales:

  1. Standard AHP linear scale
  2. Logarithmic scale
  3. Root square scale
  4. Inverse linear scale
  5. Balanced scale
  6. Balanced-n scale
  7. Adaptive-bal scale
  8. Adaptive scale
  9. Power scale
  10. Geometric scale


Fig. 1 Mapping of the 1 to 9 input values to the elements of the decision matrix.

Continue reading AHP Judgment Scales

AHP-OS Data Download and Import in Excel

Most data generated with AHP-OS can be downloaded as csv files for import into a spreadsheet program and further analysis:

  • From the Hierarchy Input Menu – decision hierarchy and local & global priorities
  • From the Group Result Menu – Priorities by node and consolidated decision matrix
  • From the Project Data Menu – Decision matrices from each participant

For each download you can select “.” or “,” as decimal separator. The downloaded csv (text) file is coded in UTF-8 and supports multi-language characters like Chinese, Korean, Japanese and of course a variety of Western languages.

How to import into excel?

Open Excel, click on “File” -> “New” to have a blank worksheet. Click on “Data“. On the left top you will find the “Get External Data” box.

Continue reading AHP-OS Data Download and Import in Excel

AHP-OS – Editing saved projects

In the project menu of the latest AHP-OS version (2017-05-25), I added a button to edit saved projects. As long as there are no participants’ inputs (completed pairwise comparisons), any saved project’s hierarchy, alternatives or description can be modified.

Open a project from your project list, and click on Edit Project. The project hierarchy page will open with a message on top , indicating that you are modifying an existong project. You can now change the hierarchy, for example add criteria or alternatives. A click on Save/Update in the Hierarchy Input Menu

will overwrite the data of the original project under the same session code. You will see it in a message . Before you click on Go to save,  you  can also update the project short description:

Continue reading AHP-OS – Editing saved projects

AHP-OS New Release with simplified project administration

Based on feedback from users, I just released a major update of BPMSG’s AHP online software AHP-OS with simplified menu structure and additional functionality.  Starting the program as registered and logged-in user, the project session  table is displayed, showing your projects.

You can open one of your projects, either using a click on the session code in the project table, or selecting the session code from the session administration menu:

This will bring you to the project summary page, showing

Continue reading AHP-OS New Release with simplified project administration

AHP Group Consensus Indicator – how to understand and interpret?

BPMSG’s AHP excel template and AHP online software AHP-OS can be used for group decision making by asking several participants to give their inputs to a project in form of pairwise comparisons. Aggregation of individual judgments (AIJ) is done by calculating the geometric mean of the elements of all decision matrices using this consolidated decision matrix to derive the group priorities.

AHP consensus indicator

In [1] I proposed an AHP group consensus indicator to quantify the consensus of the group, i.e. to have an estimate of the agreement on the outcoming priorities between participants. This indicator ranges from 0% to 100%. Zero percent corresponds to no consensus at all, 100% to full consensus. This indicator is derived from the concept of diversity based on Shannon alpha and beta entropy, as described in [2].  It is a measure of homogeneity of priorities between the participants and can also be interpreted as a measure of overlap between priorities of the group members.

Continue reading AHP Group Consensus Indicator – how to understand and interpret?

Incoming search terms:

  • diversity shannon entropy

The Analytical Hierarchy Process (AHP) – Is it old and outdated?

This was a question in researchgate.net, and the answer of Prof. Saaty – the creator of the method – is of course: “The AHP is the only accurate and rigorous mathematical way known for the measurement on intangibles. It is not going to get old for a long time., with a lot of answers from others following.

When it comes to AHP, it seems the scientific world is still divided in opponents and advocates of the method.

I answered with the statistic of my website: BPMSG has more than 4000 users of the online software AHP-OS, 600 of them active users with 1000 projects and more than 3500 decision makers. My AHP excel template reached nearly 21 thousand downloads.  It clearly shows that the method is not outdated.

As a reply Nolberto wrote:

No, I don´t think that AHP is outdated, but the fact that over than 1000 projects have been developed using AHP does not mean that their results are correct (which is impossible to check), or that the method is sound (which is easily challenged)… 

Here my answer:

yes, I agree, the numbers only show that AHP is not outdated (which was the original question). They don’t show, whether the results are correct or incorrect, but they also do not show whether the users did or did not realise the method’s drawbacks and limitations.

For me, as a practitioner, AHP is one of the supporting tools in decision making. The intention of a tool is what it does. A hammer intends to strike, a lever intends to lift. It is what they are made for.

From my users feedback I sometimes get the impression that some of them expect a decision making support tool to make the decision for them, and this is not what it is made for.

In my practical applications AHP helped me and the teams a lot to gain a better insight into a decision problem, to separate important from less important criteria and to achieve a group consensus and agreement how to tackle a problem or proceed with a project. Probably, this could be achieved with other tools too, but as you say, AHP is simple, understandable and easy.

For sure, real world problems are complex. Therefore they have to be broken down and simplified, to be handled with the method, and I agree, over-simplification can be dangerous. On the other hand, what other approach than the break down of complex problems into digestable pieces is possible?

Finally, it’s not the tool producing the decision, but the humans behind it. They will be accountable for the decision, and it’s their responsibility to find the appropriate model of a decision problem and the right balance between  rational and non-rational arguments and potential consequences of their decision.

Let me know your opinion!

 

AHP-OS News March 2017

I received some feedback about session timeout and expired session errors. I have now extended the session timeout to 45 min. After 45 minutes of inactivity (no refresh of html pages, click on menu botton, etc.) the session expires and session data are lost. Kindly feedback, if you still face a problem.

AHP-OS can handle multibyte characters (Chinese, Korean, Japanese etc.) Unfortunately, the bar chart of priorities on the group result page cannot handle these characters; the annotation of the axis will not be readable. I am working on a solution.

When doing a pairwise comparison – leaving all comparisons at the default value of 1 (equal importance) – criteria will get equal priorities. I implemented a confirmation message box: Are you sure to leave all comparisons at equal importance?  This was done in order to avoid unintential submission of the default values.