This paper analyzes the observed decision-making behavior of a sample of individuals impacted by Hurricane Irma in 2017 (n = 645) by applying advanced methods based in discrete choice theory. Our first contribution is identifying population segments with distinct behavior by constructing a latent class choice model for the choice whether to evacuate or not. We find two latent segments distinguished by demographics and risk perception that tend to be either evacuation-keen or evacuation-reluctant and respond differently to mandatory evacuation orders. Evacuees subsequently face a multi-dimensional choice composed of concurrent decisions of their departure day, departure time of day, destination, shelter type, transportation mode, and route. While these concurrent decisions are often analyzed in isolation, our second contribution is the development of a portfolio choice model (PCM), which captures decision-dimensional dependency (if present) without requiring choices to be correlated or sequential. A PCM reframes the choice set as a bundle of concurrent decision dimensions, allowing for flexible and simple parameter estimation. Estimated models reveal subtle yet intuitive relations, creating new policy implications based on dimensional variables, secondary interactions, demographics, and risk-perception variables. For example, we find joint preferences for early-nighttime evacuations (i.e., evacuations more than three days before landfall and between 6:00 pm to 5:59 am) and early-highway evacuations (i.e., evacuations more than three days before landfall and on a route composed of at least 50% highways). These results indicate that transportation agencies should have the capabilities and resources to manage significant nighttime traffic along highways well before hurricane landfall.

Regret is often experienced for difficult, important, and accountable choices. Consequently, we hypothesize that random regret minimization (RRM) may better describe evacuation behavior than traditional random utility maximization (RUM). However, in many travel related contexts, such as evacuation departure timing, specifying choice sets can be challenging due to unknown attribute levels and near-endless alternatives, for example. This has implications especially for estimating RRM models, which calculates attribute-level regret via pairwise comparison of attributes across all alternatives in the set. While stated preference (SP) surveys solve such choice set problems, revealed preference (RP) surveys collect actual behavior and incorporate situational and personal constraints, which impact rare choice contexts (e.g., evacuations). Consequently, we designed an RP survey for RRM (and RUM) in an evacuation context, which we distributed from March to July 2018 to individuals impacted by the 2017 December Southern California Wildfires (n = 226). While we hypothesized that RRM would outperform RUM for evacuation choices, this hypothesis was not supported by our data. We explain how this is partly the result of insufficient attribute-level variation across alternatives, which leads to difficulties in distinguishing non-linear regret from linear utility. We found weak regret aversion for some attributes, and we identified weak class-specific regret for route and mode choice through a mixed-decision rule latent class choice model, suggesting that RRM for evacuations may yet prove fruitful. We derive methodological implications beyond the present context toward other RP studies involving challenging choice sets and/or limited attribute variability.