## Pages

### Linear Conjoint Analysis - Simplified version

What do you look for, when you go to purchase a new mobile phone ? Price, Brand, its features such as camera quality, RAM, battery life, color etc. ? Your mind compares all the attributes of several mobile phones (you are unaware of the processing part though) , and decides the best one for you.

Think of the manufacturer perspective now, how does he decide that about features to be provided in a mobile within a price range, while his aim definitely is maximizing his sales and market share.

Conjoint Analysis helps answer "What a Consumer Wants ?"

Disclaimer : It definitely won't help answer "What a girl wants?"

What is Conjoint Analysis ?

Conjoint analysis is a statistical technique used in market research to determine how people value different attributes (feature, function, benefits) of a product or service.

How it is useful ?

Quite useful for manufacturing or service providing organizations during product designing as it helps optimizing the features of a product. It also helps them in pricing strategy.

Conjoint analysis is a marketing technique used to determine which product attributes are important to a consumer and how important each attribute is.
All in all, it helps understand the customer preferences and answer most critical question :

What and how a customer thinks, while buying a product ?

How to do it ?

Let's understand the process with a simple example :

Suppose for buying a mobile phone, customers consider only 3 attributes for deciding:

1 . Brand    2. Color    and   3. Price

A manufacturer needs to understand the weightage customers give to each of the above mentioned attributes. He can take help of Conjoint Analysis for the same.

Consider a situation ...

There are 3 Brands, 2 colors and 3 Price variants in the mobiles phone.

There are 18 possible variants that can be designed from these three attributes:

3 brands × 2 colors × 3 prices = 18

We list all the variants and give to a costumer. We ask him to rate each variant on a scale of 1 to 10.

1  stands for least desirable
10 stands for most desirable

Post survey we get the data as shown here >>>

Based on this data, we can conclude the weightage he gives to for various attributes and also preferences for variants in each attribute.

Really ?

Yes ... With the help of Conjoint Analysis !

Now let's explore the process of Linear Conjoint Analysis.