Modelling & Analysis
Estimating choice models from your data - MNL, mixed logit, WTP space, latent class, and RP/SP joint estimation in Apollo.
Knowledge Base -> Modelling & Analysis
SurveyEngine, 09.07.2026
General methodology
Mixed logit - accounting for preference heterogeneity - The MNL model assumes everyone values attributes the same way. Mixed logit relaxes this assumption - and typically produces much more realistic and insightful results.
Interpreting MNL model results from a DCE - MNL output tables contain coefficients, t-ratios, and fit statistics - knowing what each means is the difference between a conclusion and a guess.
WTP space vs preference space estimation - Estimating WTP from the ratio of coefficients produces unreliable confidence intervals. WTP space models estimate WTP directly and give better inference.
Health research
Latent class models for health preference heterogeneity - When patient preferences are not just heterogeneous but genuinely segmented - distinct groups with qualitatively different priorities - latent class models reveal the segments that mixed logit averages over.
WTP estimation for health outcomes in patient preference studies - WTP estimates for health outcomes - reduced side effects, improved efficacy, better quality of life - have certain benefits over TTO and QALYS as an output output of patient preference DCE studies.
Transport research
RP/SP joint estimation in Apollo - Joint RP/SP estimation combines the anchoring power of real behaviour with the variation power of stated preference tasks. Apollo handles both data sources in a single model.
Value of travel time estimation from DCE data - Value of travel time is one of the most important outputs of transport SP research - and one of the most misunderstood. This requires careful model specification and honest reporting.
Environmental research
Modelling protest responses in environmental DCE analysis - How you model protest responses matters as much as how you detect them. Simple exclusion biases WTP upward; ignoring them biases it downward. Spike models offer a middle path.
WTP estimation for environmental goods - WTP estimates for environmental improvements are the primary output of environmental valuation DCEs - and they must be estimated and presented with appropriate care to be credible in policy processes.