Conjoint model design Conjoint study programming (you can do this yourself through SurveyWriter or request our assistance) Results analysis Report development

Typically, Conjoint Analysis refers to several different modeling/analysis techniques that serve to understand the relative impact or importance that different product or service features have on individual’s choices. Conjoint analysis is sometimes referred to as “trade-off” analysis because individuals are forced to make trade-offs among different product features when they complete conjoint questions.  Through these trade-offs, researchers are able to infer how important or valuable different features are and how they influence individuals’ decision-making processes.

SurveyWriter can be used to conduct all forms of conjoint analysis (click links for explanation of specific modeling techniques):

	Traditional conjoint analysis
	Discrete choice analysis
	Best/worst conjoint

Traditional Conjoint Analysis  

Respondents are shown different product/service scenarios whose features, or attributes, vary according to an experimental design -- actually the specific levels of the attributes vary.  Respondents are typically asked to rate or rank the product scenarios. A rating task is easier to complete, particularly with web-based surveys.  Once data is collected, analysis reveals the relative importance, called utility, of each of the different levels of each attribute.  These utilities can then be used to understand the importance of the attributes, can be used as the basis for segmentation analysis (e.g., to understand whether different segments vary in terms of the attributes that are most important to them), and can also be used to develop a market simulator that allows “what-if” scenarios to be conducted. For example, what if we modified our current computer design by increasing the hard drive capacity. What impact would this have on potential sales? 

Discrete Choice Conjoint

Respondents are again shown different products or services. In this case, rather than rating or ranking them, they are asked to select the one they would be most likely to purchase.  For example, respondents might be shown three different computer models and asked to indicate the one they would purchase.  Discrete choice holds a number of advantages over traditional conjoint including:

	It is a more realistic exercise for individuals to indicate which product they would purchase rather than rating/ranking since this is what they actually do in the marketplace.
	In discrete choice, individuals can be given the option to select “none” of the products, thus indicating that they do not find any of the products appealing.
	Discrete choice allows for much more complex statistical modeling to be performed, which often yields better data (e.g., interactions, alternative–specific effects, cross-effects, etc., can be accommodated).  As with traditional conjoint analysis, the utilities that come from discrete choice can be used to develop market simulators and can also be used to examine whether different segments exist using either latent class analysis or Hierarchical Bayes.

Best/Worst (BW) conjoint (also known as maximum difference scaling)

With BW conjoint, respondents are shown the levels associated with attributes and are asked to select the one that they like best (or that’s most appealing, etc.) and the one they like least.  They repeat this process several times, each time being shown a different set of levels.  Like the other two types of conjoint, utilities are calculated that indicate the relative value of the attributes and their levels.  BW conjoint works best with “soft” or abstract attributes that are not easily quantified. For example with pizza, “soft” attributes might be excellent taste, fresh ingredients, fast delivery, courteous order-taker, etc. One particular area that BW conjoint excels in is message optimization – determining which points are most important in marketing communications.