Stated Preference

Why this matters for your decision

Stated preference methods have major advantages: they work before an offer exists, they can cover many combinations of attributes and prices, and they provide explanations. Choice-based methods such as conjoint analysis reflect trade-offs more realistically than simple scales.

The limit lies in the situation. Whoever answers makes no choice with consequences. In a meta-analysis of 77 studies, Schmidt and Bijmolt (2020) show that hypothetically stated willingness to pay is on average 21 % above real willingness to pay, and no less so for indirect methods than for direct questions. Morwitz, Steckel and Gupta (2007) find that surveyed purchase intent is more weakly linked to later sales for new products than for existing ones.

For a decision, this means: stated preference data is a good basis for understanding and narrowing down options. As the sole assumption for demand and price in new or costly decisions, it carries a risk of unknown size.

Methods at a glance

Stated preference methods include scale questions on willingness to buy, concept tests, conjoint analyses and discrete choice experiments, MaxDiff, and pricing surveys such as Van Westendorp and Gabor-Granger. They differ in how realistically the choice is designed; what they have in common is that the answer remains hypothetical.

Example

A telecommunications provider is planning a mobile tariff with three data allowances. A conjoint analysis shows that data allowance and price are the most important attributes and simulates market shares for several combinations. For the two combinations that are ultimately in contention, a behavioural test measures sign-up intent. The conjoint analysis supported the selection of the variants, the behavioural test the decision between them.

How it differs

Revealed preference is the counterpart: the preference inferred from observed behaviour. The Say-Do Gap describes the distance between the two, hypothetical bias the price component of that distance.

Purchase intent is stated preference when it is asked on a scale, and revealed preference when it is measured in behaviour. Horizon measures the second form and works as a complement to surveys: the final variants go into a behavioural test, and the survey provides the why.

Limitations

Criticism of stated preference is not criticism of surveys in general. For perception, understanding, satisfaction and motives, they are often the better tool, and they reach target groups that are hard to address online.

Conversely, the behavioural test has limits too: it tests a few variants, not dozens of combinations, it measures purchase or sign-up intent at the moment of the offer, and on its own it does not explain why one variant is ahead. That is why the two methods complement each other.