Day 5 PERMAP: Team B

PERMAP is a multidimensional scaling (MDS) computer program, used to find out hidden attributes that might otherwise not appear in the data set being analysed. Perceptual Maps are sometimes called product maps, sociograms, sociometric maps, psychometric maps, stimulus-response diagrams, relationship maps, concept maps, etc.

In PERMAP technique, we measure the Overall Similarity levels between Objects or Rank the Objects based on common Attributes they share.

What is an object?

Objects can be anything. They can be stimuli, constructs, artifacts, characteristics, traits, people, companies, bones, arrowheads, and so forth. For instance, Coke and Sprite are two objects. Both these beverages can be related to each other based on the fact that they come from the Coca Cola stable.

What is an attribute?

An attribute is some aspect of an object. It may be called a factor, characteristic, trait, property, component, quantity, variable, dimension, parameter, and so forth. E.g. taste, fizz are attributes associated with soft drinks.

What is Overall Similarity?

It is a measurement of how similar/dissimilar is a pair of objects. This similarity can be gauged based on any attribute. For instance, Coke and Sprite are similar because they are both products of Coca Cola. However, measuring the overall similarity is a difficult process, as the attributes are not explicitly defined and are difficult to identify and map.

While using Overall Similarity criteria, one needs to be aware of all possible attributes for the given pair of objects and should have thorough knowledge of the same.

The advantage of this method is that PERMAP brings out some hidden attributes, which otherwise are not directly visible. More similarity between the objects, closer they are in the PERMAP output. In other words, proximity is higher.

What is Attribute Based?

Here objects are ranked on the basis of attributes. Scale variables are used as this is a rating/ ranking scale.  Here, we need t o list down all possible attributes on which the objects are being compared. It is easy and simple method; however there is a chance of error if any attribute is missed out.

Using PERMAP

1.       To use PERMAP, first we need to identify the objects that need to be compared. Then based on the number of objects, say ‘N’, we form pairs between the objects.

No. of pairs of ‘N’ objects = N(N-1)/2

2.       Once pairs are formed, we need to assign ratings to the pairs based on our judgement.

3.       After ratings are done, we take the average of ratings and divide the same by 10. (10 is taken in case the scale is 0-9. Higher number for higher rating ). This average rating acts as the distance.

4.       After taking out the average, we create a distance map on excel sheet.

Distance Map for the same:

As the diagonal shows 1 for similar objects, this is a similarity matrix. If the diagonal were to have 0, then it
would have been a dissimilarity matrix.

5.       Then this distance map is pasted on Notepad. The title of the file is given. Then we denote number of objects: nobjects=6 (as the case above). Finally, we write whether the matrix is similaritylist or dissimilaritylist. In both these cases no space is to be given.

6.       This completes the notepad and we need to then open this file in PERMAP. Following is the output.

7.       Finally, click start tab and clusters would be formed based on the similarity (as defined by the ratings) Following is the output:

8.       In this case, Coke & Pepsi form one cluster. Sprite & Mountain Dew form another cluster and Slice & Maaza form third cluster.

9.       In this figure, the objective function value is the sum of squares of error. Lower the value, lesser is the error.

10.   Another function is the PERMAP if Parked Objects. This is used to identify the changes in cluster if one of the objects is removed from the output. This function comes in handy to identify the impact of one object on the other objects in the cluster.  For instance, in an election scenario, one candidate opting out of the polls at the last moment will change the entire equation and politicians will form new alliances, i.e. new clusters.

PERMAP: Benefits for Businesses

Perceptual mapping is a two-dimensional tool, highly beneficial for any company to understand what consumers think about the brand, the product and how is the company positioned relative to its competitors. It is a very effective tool to understand the brand positioning strategy of a company relative to its competitors.

In addition, it also helps the company to launch new products. Since, the clusters are identified, the company can, based on the results of the perceptual map identify areas, gaps where it can launch and position its product.

--Neeraj Gandhi (TEAM B)
Reference: http://belkcollegeofbusiness.uncc.edu/jaredhansen/Teaching/MBA%20Marketing%20Research/PermapManual.pdf