Concept Architecture
Concept
Theoretically, Conjoint Analysis is a family of stated preference methods used to estimate how individuals value the attributes of healthcare interventions, products or services by observing their evaluations or choices between hypothetical alternatives. It is based on random utility theory and consumer choice theory, recognising that overall preference is determined by the combined utility of individual attributes. The method exists to quantify preferences and estimate the trade-offs individuals make between competing characteristics.
Mathematically, Conjoint Analysis represents the utility of an alternative as the sum of the utilities associated with its individual attributes. Preference parameters are estimated using regression-based or discrete choice models, depending on the conjoint method employed, allowing the contribution of each attribute level to overall utility to be quantified.
In practice, Conjoint Analysis is implemented by designing hypothetical healthcare scenarios that vary according to selected attributes and levels, collecting respondents' ratings, rankings or choices, and estimating part-worth utilities. It is widely used in health economics to evaluate patient, clinician and public preferences, estimate willingness-to-pay, and inform health technology assessment and service design.
Purpose
Used to quantify preferences for healthcare interventions, estimate the relative importance of treatment attributes, evaluate trade-offs between intervention characteristics, derive willingness-to-pay estimates, and support healthcare decision-making.
Mathematical Formulae
Primary Formula
U? = ?? + ????? ??x?? + �?
Where:
- U? = Utility of alternative i
- ?? = Preference coefficient for attribute k
- x?? = Attribute level
- �? = Random error term
Supporting Formulae
For choice-based conjoint analyses:
P? = exp(V?) / ????? exp(V?)
Related Mathematical Methods
- Random Utility Theory
- Linear Regression
- Conditional Logit Model
- Multinomial Logit Model
- Mixed Logit Model
- Maximum Likelihood Estimation
Example
A conjoint survey evaluates preferences for asthma treatments using the attributes:
- Monthly cost
- Improvement in symptoms
- Dosing frequency
- Risk of adverse effects
Respondents complete a series of hypothetical tasks. Estimated part-worth utilities indicate that symptom improvement has the greatest influence on preference, followed by adverse effects and treatment cost. These utility estimates are then used to predict preferences for alternative treatment profiles.
Excel Implementation
| Function | Example Formula | Health Economics Application |
|---|---|---|
| SUMPRODUCT | =SUMPRODUCT(B2:E2,$B$10:$E$10) | Calculate total utility from estimated part-worth utilities. |
| EXP | =EXP(F2) | Calculate exponential utility for discrete choice models. |
| SUM | =SUM(G2:G5) | Calculate the denominator for predicted choice probabilities. |
| LINEST | =LINEST(Y_range,X_range,TRUE,TRUE) | Perform simplified exploratory estimation before specialised conjoint analysis software. |
VBA (Optional)
Automate the generation of conjoint survey profiles and prepare response datasets for statistical estimation.
Sources
- Green PE, Rao VR. Conjoint Measurement for Quantifying Judgemental Data. Journal of Marketing Research.
- Louviere JJ, Hensher DA, Swait JD. Stated Choice Methods: Analysis and Applications. Cambridge University Press.
- Train KE. Discrete Choice Methods with Simulation. Cambridge University Press.
- Bridges JFP, Hauber AB, Marshall D, et al. Conjoint Analysis Applications in Health: A Checklist. Value in Health.
- ISPOR Conjoint Analysis Good Research Practices Task Force Reports.
Related Concepts (2)
Library
Publications
1
Conjoint Analysis Applications in Health — A Checklist: A Report of the ISPOR Good Research Practices for Conjoint Analysis Task Force — Bridges, Hauber, Marshall, Lloyd, Prosser, Regier, Johnson & Mauskopf, Vol. 14, No. 4 ed., 2011 (Value in Health)
The ISPOR good-practice checklist for conjoint analysis and discrete-choice experiments in health — the stated-preference methods used to elicit patient and public preferences over treatment attributes for value assessment and priority-setting.
Journal ArticleView source →
Frequently Asked Questions (6)
What is conjoint analysis?
A method for measuring how individuals value different attributes of a good or service by analysing their evaluations of combined alternatives.
Source: Luce & Tukey 1964
Where does conjoint analysis come from?
It originates in work on how a judgement about a combined stimulus can be decomposed into contributions from its separate components, which established the conditions under which such a decomposition is possible. That formal result was taken up in marketing research as a practical way of estimating what buyers value in a product, and later in health to value features of services and treatments. The family therefore rests on a measurement theory rather than on a survey technique, which is what distinguishes it from simply asking people what matters.
Source: Luce & Tukey 1964
What forms does conjoint analysis elicitation take?
Respondents may rate each described alternative on a scale, rank a set of alternatives in order of preference, or choose one alternative from a set. Rating collects the most information per question and imposes no requirement to trade off, so respondents can score everything favourably. Ranking forces an ordering but not a magnitude. Choice most closely resembles a real decision and yields data suited to established models of choice behaviour, which is why it has become the dominant form in health.
Source: Green & Srinivasan 1978
How are attributes and levels chosen in conjoint analysis?
Attributes should cover what matters to the decision, be capable of being changed by whoever will act on the results, and be understood consistently by respondents. Levels must span a range that is plausible and wide enough for respondents to notice, since an attribute varied over a narrow range will appear unimportant regardless of how much it matters. The selection is normally developed from qualitative work with the people who will answer, because attributes chosen by analysts routinely omit what respondents actually weigh.
Source: Ryan, Gerard & Amaya-Amaya 2008
What does conjoint analysis produce?
It produces a weight for each level of each attribute, showing how much that level contributes to the overall attractiveness of an option, from which the relative importance of attributes can be compared. Where one attribute is expressed in money, the weights on the others can be converted into monetary terms. Where one is expressed in health, they can be converted into health terms. The outputs also support prediction of how uptake would change if a service were configured differently.
Source: Lancsar & Louviere 2008
How does conjoint analysis compare with other valuation methods?
It differs from asking directly what something is worth, since respondents reveal values through choices rather than stating them, which avoids some of the difficulty people have in naming a figure. It differs from methods that value whole health states by valuing the separate features of a service or treatment, which suits questions about how care should be organised. Its results depend on the attributes presented, so it can only value what the analyst thought to include, and this is the constraint that most limits it.
Source: Bridges et al. 2011
Trust Record
Verified by Dr Darrin Baines
British health economist
Professional identity: darrinbaines.org
Verification date: 31 Jul 2025
Content version: 1.0.0
Canonical Identity
- Persistent URI
- https://healtheconomics.wiki/concept/conjoint-analysis
- Term code
- HE-EE-CBA-010
Stable URI · Machine-readable · Resolvable · CC BY 4.0