Discrete choice analysis is a quantitative framework used to understand and predict how individuals make decisions between two or more alternatives.
It examines how people trade off attributes, evaluate options, and choose the one that maximizes their utility.
Discrete choice analysis has strong theoretical foundations in utility maximization and random utility theory.
It also has practical applications across transportation, marketing, health, environmental economics, and any field where human decision-making needs to be modelled.
Discrete choice analysis is formulated through probabilistic models—such as Logit, Nested Logit, Mixed Logit, and Latent Class Models—that represent the likelihood of choosing each alternative.
These models incorporate attributes of the alternatives, characteristics of individuals, and random utility components.
Discrete choice analysis is used to evaluate preferences, forecast demand, understand behavioural responses, and support policy design.
It helps researchers and practitioners estimate how changes in price, travel time, service quality, or other attributes affect people’s choices.
Tools for discrete choice analysis include statistical software and specialized packages such as:
- R (apollo, mlogit, gmnl)
- Python (biogeme, pylogit, choice-models)
- BIOGEME (Python/Swiss Army knife for discrete choice models)
- Stata (cmset, cmclogit, mixlogit)
- MATLAB (econ & choice modelling toolboxes)
- Sawtooth Software (widely used in marketing choice modelling)
- NLOGIT (advanced econometric modelling for choice data)
Traffic Studies and Mobility 
Deja un comentario