Multiple Discrete-Continuous Choice Modeling in Household Activity Analysis

Multiple discrete-continuous choice modelling unites two decision dimensions that households routinely face: the incidence of choosing among a finite set of activities or goods (discrete choices) and the allocation of limited resources—such as time, money or effort—across those choices (continuous quantities). This family of models has its origins in Karush–Kuhn–Tucker demand system theory and finds application in activity-based travel demand, time-use studies, household task assignment and expenditure analysis. By estimating utility functions that account for complementarity and substitution between alternatives, these models reveal how households decide not only what activities to undertake but also how much time or budget to devote to each. Extensions to the basic framework allow for random preference heterogeneity, explicit budget constraints (or their omission when budgets are negligible), latent class segmentation and the incorporation of unobserved factors. Such developments have enabled rich insights into multimodal transport use, intra-household interactions, weekly activity rhythms and adaptive behaviour under resource scarcity. In practical terms, multiple discrete-continuous models inform urban planners, transport operators and policymakers about likely responses to infrastructure changes, service disruptions or demographic shifts, thereby guiding the design of age-friendly public spaces, shared-mobility hubs and demand-management strategies.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Multiple Discrete-Continuous Choice Modeling in Household Activity Analysis publication trend

The graph below shows the total number of articles in multiple discrete-continuous choice modeling in household activity analysis across all publications each year (not limited to Nature Index journals).

Technical terms

Multiple Discrete-Continuous (MDC) modelling framework: A class of econometric models that jointly estimates which alternatives are chosen (incidence) and the quantity allocated to each (quantities), often subject to resource constraints such as time or budget.

Multiple Discrete-Continuous Extreme Value (MDCEV) model: A popular specification within the MDC framework in which discrete and continuous decisions are derived from an extreme-value utility kernel, enabling closed-form likelihoods and efficient estimation of choice incidence and allocation.

Complementarity and substitution effects: Behavioural phenomena in which the utility of allocating more resources to one alternative either increases (complementarity) or decreases (substitution) the desirability of allocating resources to another.

Latent class MDCEV model: An extension of the MDCEV model that segments the population into distinct classes or groups, each with its own preference structure, to capture unobserved heterogeneity in discrete-continuous choices.

References

1. Modelling the complementarity and flexibility between different shared modes available in smart electric mobility hubs (eHUBS). Transportation Research Part A Policy and Practice (2024).
2. Modeling pedestrians' activity time-use choices in a virtual urban public space: The influences of the environment and affective experience. Cities (2024).
3. Extending the Multiple Discrete Continuous (MDC) modelling framework to consider complementarity, substitution, and an unobserved budget. Transportation Research Part B Methodological (2022).