Conjoint Analysis Surveys and Software

Conjoint Analysis Definition
Conjont Analysis: Self Explicated, Full Profile, Choice Based

Conjoint Analysis is an advanced analytical technique used to determine the joint influence that feature and level combinations of a product or service have on the purchase decisions. A properly designed conjoint analysis study allows any combination of features and levels to be profiled to estimate market or choice share. Competing profiles enable such questions as "What impact will our new product formulation have on our market share?", "What happens if our competitors introduce product formulation X?", or "What feature set would our customers like best?"

Depending on the type of conjoint survey conducted, statistical methods like ordinary least squares regression, weighted least squares regression, and logit analysis are used to translate respondent answers into importance values and utilities. Conjoint analysis methodology has withstood intense scrutiny from both academics and professional researchers over the past 25 years and is widely used in consumer products, durable goods, pharmaceutical, transportation and service industries.

In conjoint analysis, the relationships between each of the features and levels are evaluated. The goal is to reveal the underlying value respondents would consciously or subconsciously place on profiles that represent full product configurations.

Using the Question Wizard, you can build and deploy a conjoint question set in under 20 minutes. If you know the Features/Levels for the product/service that you want to evaluate, the Survey Engine handles all the complex logic of preparing questions for feature and level presentation.

The following section describes the most popular types of conjoint analysis that we offer. More basic types of conjoint analysis can always be done.

Full Profile Conjoint Analysis
Traditional "full profile" conjoint analysis uses ratings or rankings of distinct product profiles as the means to estimate pricing effects. For example, a conjoint analysis product profile might be composed of five attributes. Using express mail services as an example, each service is composed of a set of attributes like company name, delivery options, price and drop-off location options. For each attribute, there are levels that can be identified. For example, the company name might include FedEx, UPS, DHL, USPS, whereas price might include $3.95, $7.95, $11.95 , and delivery options might include next morning, next day, two day or five day.

The conjoint analysis profiles present different combinations representing express mail services. To these profiles respondents state their preference. The design of conjoint analysis combinations is non-trivial and must be done using experimental design methodology. The conjoint analysis process a set of utility functions for each respondent measured, for segments within the sample, and for the total sample. Utility functions show the demand curve or relative importance of each attribute and each level of each attribute.

Conjoint analysis simulations are used to analyze the sensitivity of each of the attributes to changes in the market place. Conjoint simulations of the actual market place can be run to estimate the choice share (market share) that would derived from changing the feature level combinations that make up the product. Conjoint simulations typically assume that consumer utilities are linear and additive and may not represent real world.

Self-Explicated Conjoint Analysis
The self-explicated conjoint model provides a simple alternative producing utility score estimates equal to or superior to that of full-profile and other popular approaches such as Adaptive Conjoint Analysis. The self-explicated model is based theoretically on the multi-attribute attitude models that combine attribute importance with attribute desirability to estimate overall preference.

Initially, all attribute levels are presented to respondents for evaluation to eliminate any levels that would not be acceptable in a product under any conditions. Next, attribute levels are presented and each level is evaluated for desirability. Finally, based on these evaluations, the most desirable levels of all attributes are evaluated relative importance. As with the full-profile model, these scores can be summed and simulations run to obtain a score for any profile of interest. This simple self-reporting approach is easier for the respondent to complete and straightforward in terms of determining the importance or desirability of attributes and attribute levels (See Srinivasan, V. (1997, May). Surprising robustness of the self-explicated approach to customer preference structure measurement. Journal of Marketing Research, 34, 286-291.

Discrete-Choice Conjoint Models
Discrete-choice modeling is used to determine the influence that both price and product features have on brand value. In discrete choice conjoint studies, the respondent chooses from different full profile sets, the one that they most prefer. This choice task is much easier and often more realistic than the rating or ranking tasks used in the other conjoint analysis models.

When customers shop for products such as clothing or even a dishwasher, a brand is often associated with a set of attributes, such as its price, style, color, fit and type of material. Each individual respondent when faced with a choice of two to five product configurations makes his/her choice. These choices reflect the value or utility he/she assigns to each attribute. These choices are later analyzed to produce the utility functions that derive differences in the attribute values from the competing alternatives and/or differences in the characteristics.

Discrete choice conjoint analysis developed using d-optimal designs offers some advantages over a ratings based conjoint analysis. Discrete choice conjoint presents optimal choice sets within a group of products. Discrete choice conjoint analysis provides estimates of the demand curves for all attributes and brands included in the study. Also incorporated is the ability to estimate feature level interactions, including the brand-price interaction. Like all conjoint analysis simulations, discrete choice conjoint analysis simulations can be used to place products choices into a competitive market situation.

Conjoint Analysis Simulation Example

Do you need a conjoint study to help you with Segmentation, Market Share, Product or Service Upgrade options? Give one of our product consultants a call. Our Ph.D.s are experts in advanced analysis and can answer your questions.