• Fitness & Health
• Sport & Exercise Science
• Physical Education
• Strength & Conditioning
• Sports Medicine
• Sport Management
• Dance

Conjoint analysis: Determining why consumers choose one product over another

This is an excerpt from Research Methods and Design in Sport Management-3rd Edition by Damon P.S. Andrew,Paul M. Pedersen.

By Gonzalo A. Bravo, PhD, Doyeon Won, PhD, Weisheng Chiu, PhD

INTRODUCTION TO CONJOINT ANALYSIS

Conjoint analysis originated from the pioneering work of Luce and Tukey (1964) on simultaneous conjoint measurement in mathematical psychology (Rao, 2014). Their key idea was that when two or more attributes of a product or service jointly influence consumer preference or judgment, their combined effect can be represented on a numerical scale. This foundational work laid the groundwork for significant advancements in psychometrics, econometrics, and decision theory. Moreover, it established the foundation for conjoint analysis methodology, a technique that has been widely used in marketing and social science research for over three decades. Rao (2014) defines conjoint analysis as “any decompositional method that estimates the structure of a consumer’s preferences in terms of levels of attributes of the alternatives” (p. 4). In a conjoint analysis researchers are interested in evaluating specific product characteristics and product attributes. Rao (2014) pointed out that while a product characteristic can be measured objectively (e.g., weight), evaluating a product attribute involves a subjective judgment (e.g., determining whether it is expensive or inexpensive). Despite this distinction, much of the conjoint analysis literature uses these terms interchangeably, with “attribute” being the more commonly accepted term.

Green et al. (2001) noted that conjoint analysis addresses the central question of why consumers choose one product or service over another, particularly when the selection process involves products with distinct features. For example, when deciding on the best running shoes to buy, an experienced runner might prioritize weight and comfort, whereas a casual runner may focus on price and durability. In both cases, consumers face a value trade-off between different product attributes. Similarly, when purchasing a five-game ticket package for their favorite basketball team, fans encounter trade-offs. One package may offer greater value, such as reserved lower-level seats, parking, and the flexibility to trade unused tickets, but at a higher price. Conversely, a more affordable package might come with randomly assigned upper-level seats, no ticket exchanges, and no parking benefits. In such scenarios, consumers must evaluate competing alternatives, each presenting a degree of conflict, and engage in a cognitive process aimed at minimizing this conflict (Hansen, 1976). Ultimately, consumers strive to maximize decision outcomes while minimizing effort and ensuring accuracy (Bettman et al., 1998). Conjoint analysis, as an experimental design approach, allows researchers to create scenarios for a product or service that include attributes (e.g., ticket price) and corresponding levels (e.g., $100, $200, $300). Participants are then asked to express their preferences among different options. A crucial aspect of conjoint analysis involves breaking down consumer preferences into part-worths, which represent the estimated value assigned to a specific level of an attribute (Hair et al., 1998). A higher part-worth indicates that a consumer is more willing to trade off other features in favor of the attribute that shows a higher value.

Hair et al. (2009) highlighted the flexibility of conjoint analysis as a marketing technique. It can incorporate both metric (e.g., dollar value) and nonmetric (e.g., seating level) dependent variables, as well as categorical predictor variables (e.g., season ticket holder vs. non-season ticket holder). Moreover, it enables researchers to make assumptions about relationships between independent and dependent variables. From a practical point of view, conjoint analysis “concerns the day-to-day decisions of consumers” (Green et al, 2001, p. s57).

Rao (2014, p. 19, 22) identified five key features of conjoint analysis: (1) a measurement technique to quantify consumer trade-offs and values; (2) an analytical tool for predicting consumer reactions to new products or services, (3) a segmentation method for identifying consumer groups with similar trade-off characteristics; (4) a simulation technique to assess new product and service offerings; and (5) an optimization tool for identifying product profiles that maximize market share and return.

Given that conjoint analysis provides insights that closely reflect real-life consumer decision making, this research method has gained significant attention from marketing practitioners (see the sidebar “Preference vs. Choice: Do They Mean the Same Thing” for insights regarding the difference between a consumer preference and a choice, which refers to the evaluative process a consumer undergoes when deciding whether to adopt a product or service). The methodology has been applied across various market contexts, not only to understand how consumers choose products and services, but also to test product design (Green and Srinivasan, 1990), evaluate pricing strategies (Orme, 2020), identify market segmentation (Rao, 2014), and more recently, to evaluate different features of sport-related products and services (Feilhauer et al., 2023; Newland et al., 2013; Popp et al., 2020; Won et al., 2008).

More Excerpts From Research Methods and Design in Sport Management-3rd Edition

---