US:+1(415)799-9942 UK:+44(0)2032899424 enquiry @
() () () () () () () () () () () ()
() () () () () () () ()

Conjoint Analysis

A proven method which has been used for years for market research is Conjoint Analysis. The portfolio that is offered in Conjoint Analysis at digitGaps is a perfect fit for solving marketing related questions, especially it is the best way to address the ideal target group in service as well as in consumer goods industry.

Conjoint Analysis can be used for when it comes to decision making in order to learn more about purchase decisions and penchants. Conjoint Analysis can be used for a range of applications such as:

  • Designing products and services: In order to optimize existing products and services in competitive set
  • Understanding the pricing policy: To get an answer to the question related to the pricing of the product or services i.e. how much a new product or its features, new service or its features should cost compared to the competitors’ products and services.
  • Segmentation: To understand the product and service features which can get the uppermost benefit in different Market/Customer segments.
  • Understanding sales scenarios: Conjoint Analysis helps in identifying if there are any cannibalization effects. As well as to understand which influence does the introduction of a new product or service have on market share of the competition?

Below are the questions which can be answered by using a suitable Conjoint Analysis:

  • Which factors have the strongest impact on purchase intention?
  • Which product or service has the biggest market potential?

It is very important to choose the right form of analysis for the problem at hand which depends on several factors and should be considered carefully. Generally, the preferred method is the one which stimulates the decision-making process. With Conjoint Analysis, digitGaps offers a comprehensive range of methods for analyzing purchase decisions and underlying consumer preferences. These methods stimulate the purchase decision process in different ways with various points of emphasis.

Conjoint Analysis Methods

For less complex purchase situations, the Choice Based Conjoint Analysis is the perfect form. Situations in which products can be described widely by a small number of relevant features Choice Based Conjoint Analysis is preferred. In Choice Based Conjoint Analysis respondents have to repeatedly choose their preferred product from different sets of the product. Choice Based Conjoint Analysis stimulates purchase decisions realistically and is often used during pricing studies.

Two Attribute Tradeoff Analysis is one early conjoint method of data collection which presented a series of two attributes at a time in which trade-off analysis where respondents rank their preferences of the different combinations of the attribute levels.

To measure attribute utilities Full Profile Conjoint Analysis is a preferred approach. Different product descriptions or different actual products are developed and presented to the respondents for preference evaluation in Full Profile Conjoint Analysis. The researchers can estimate the respondent’s utility at each level by controlling the attribute pairings for each level of each attribute tested.

This form of Conjoint Analysis is useful to handle large problems which require more descriptive attributes and levels. A unique contribution of Adaptive Conjoint Analysis is to adapt each respondent’s interview to the evaluations provided by each respondent. Generally, in Adaptive Conjoint Analysis the respondents are asked to eliminate attributes and levels that would not be considered under any conditions in an acceptable product which is done early in the interview. After this stage, the attributes are presented for evaluation, which is then followed by sets of full profiles, generally two at a time. The choice of these pairs increasingly focuses on determining the utility which is associated with each attribute.

Self-Explicated Conjoint Analysis is the form of conjoint analysis which offers a simple but surprisingly robust approach which can be implemented very easily and also it does not require the development of full profile concepts. Firstly, factors and levels are presented to the respondents for elimination if they are not acceptable under any condition. The approach in Self-Explicated Conjoint Analysis does not need regression analysis or aggregated solution which is required in many other conjoint approaches. Also, Self-Explicated Conjoint approach has provided results equal or superior to full – profile approaches and it also places fewer demands on the respondents.

Hierarchical Bayes Conjoint Analysis is particularly preferred in situations where the data collection task is huge. In such scenario, where the data collection task is so large, the respondents cannot reasonably provide preference evaluations for all attribute levels. This from helps to estimate attributes level utilities from choice data. Hierarchical Bayes Conjoint Analysis approach allows more attributes and levels to be estimated with small amounts of data collected from each respondent individually.