Discovering conjoint analysis

Conjoint analysis is an advanced market research technique that gets under the skin of how people make decisions and what they really value in products and services. Also known as Discrete Choice Estimation, or stated preference research, it involves presenting people with choices and then analysing the drivers for those choices. For an example, check out our interactive conjoint analysis demonstration or our simple conjoint in Excel to see how conjoint analysis works.

Outputs from conjoint analysis are measurements of customer value called utility or part-worths. Utility scores can be combined to build build market models and forecasts to answer questions such as "Which should we do, build in more features, or bring our prices down?" or "Which of these changes will hurt our competitors most?" to allow the business to better optimise product and service design to customer needs.

The aim of conjoint analysis and choice research is to predict how purchase decisions will be made by working out what customers value, based on the choices they make. If a business knows what customers really value, they can use this focus their strategic effort on the areas that matter most to customers (see the market modelling example).

The demonstration below is a simplified example of a conjoint exercise that uses a QuickLearn algorithm and works best if you are consistent in your choices. See the technical notes for more information and a comparison with full/commercial conjoint analysis. Alternatively look at a worked up conjoint analysis example using Excel to understand how calculations can be made.

Conjoint analysis and trade-off studies are amongst the most sophisticated forms of market research. The aim is to quantify the underlying values (utilities or part-worths) that drive customers' decisions, and then to build models  of demand and market forecasts, in order to optimise product or service features. Like any form of research, the quality of the output depends heavily on the quality of the design.

For conjoint analysis, in particular this means choosing the right flavour or type of conjoint to use and ensuring that the design of the attributes and levels, the way the profiles are shown and the number of choice tasks meets the research, analysis and business requirements.

For those new to the subject of conjoint analysis, it is easy to believe that there is only one type or version of conjoint analysis (the one type your agency knows). Or the reverse, and become bewildered by the number of abbreviations and names - eg ACA, CBC, MPC, ACBC, full profile, stated preference, DCE/discrete choice estimation among others.

Most conjoint analysis studies carried out professionally use Choice-based Conjoint (CBC) for pricing and brand value studies. Newer adaptive types of conjoint such as Adaptive Choice-Based Conjoint (ACBC) or menu-based conjoint are used for more complex studies. MaxDiff is a commonly used adjunct or substitute for conjoint analysis with large numbers of items. However, different types or "flavours" can be used, depending on the task at hand, and might incorporate Buy-your-own tasks, configurators or take the basic principles and extend them to create tailored designs for specific markets.

 This is a demonstration of the type of modelling you might get as a result of conducting a conjoint analysis market research study. The aim is to predict market share (strictly share of preference as the model doesn't take into account distribution or promotional effects) and possibly revenue or profit potential by changing product features.

There are other types of market models for other types of trade-off research such as Pricing research or Brand-Price Trade Off research. Models are a major benefit of trade-off studies over other forms of quantitative market research.

Conjoint analysis is used in a wide range of different market research and insight applications from copy testing, to pricing research to product and service design, to defining membership schemes. The list of applications is relatively long as conjoint gets adapted to different purposes. For instance it's possible to use some of the design principles to develop and test areas like website or promotional message design using live in-market testing. Below is a list of common uses.

As an advanced market research technique, conjoint analysis is most commonly used by larger businesses and for multinationals operating across several countries where it is important that product design and business strategies reflect both global and local needs. In contrast to traditional scale-based rating approaches, conjoint analysis and techniques like MaxDiff are less affected cultural differences in the way people give ratings in different countries. Consequently international conjoint projects can be an effective method of understanding common needs and desires across global markets. We have expertise in running international conjoint across Europe, the US and into Asia.

Conjoint analysis is a widely established market research technique for understanding how people value the component elements that make up a product or service - the attributes and levels. However, in certain circumstances, for instance where there are lots of attributes to consider, or where bundles are being built, it may be better to consider alternatives such as MaxDiff, Configurators, Simalto or a range of other more bespoke designs and choice tasks.

Note that we would consider options such as Discrete Choice Modelling (DCM), stated preference research and elements like shop-display tests for pricing as 'flavours' of conjoint analysis rather than purely distinct.

The earliest forms of conjoint analysis can be traced back to the 1970s having developed from the psychology of decision making and econometric choice theory.

Key developers have been Paul Green (Marketing use of decompositional models), Jordan Louviere (Choice-based conjoint) and Rich Johnson (Sawtooth Software and Adaptive conjoint methods) and more recently Sawtooth has pioneered a number of new approaches.

MaxDiff and Hierarchy of Needs studies are used In new product development, concept testing and building marketing messages to identify what customer priorities are for development or marketing communications. Often businesses have a long list of potential product benefits and the key is in identifying which to prioritise and which work best with which audience.

Our specialist MaxDiff or hierarchy of needs studies allow you to test up 40 or 50 benefits in one go, both singularly and in packages so you know where customer priorities lie. These are designed to be very quick and simple to carry out, but to produce market models that allow you to see how combinations of options compare against each other.

Many people ask how the elements of conjoint analysis relate to each other - how do you assign attributes and levels, build profiles and get to a calculation of part-worths or utility scores. In can be easy to talk about conjoint analysis in abstract without quite getting the practical 'this is how it works' element.

One of the original flavours or types of conjoint analysis is Full Profile and this is relatively simple to demonstrate. The attached Excel spreadsheet 📎 shows how a simple small full-profile conjoint analysis design can be built and analysed using Excel.

Our conjoint demonstration is a simplified example of a conjoint exercise to illustrate how choices can be turned into estimates of value. The calculations it uses to estimate the "utility" values, or part-worths associated with the choices being made (as shown on the bars) are simplified.

This article outlines some of the technical notes and issues around the demonstration. There are actually several "flavours" of conjoint analysis depending on the task at hand and we have a simple Excel-based spreadsheet to show the general principles of calculating utilities.