The use of uncertainty forecasts in complex decision tasks and various weather conditions.

Abstract

Recent research on weather-related decision-making suggests that the inclusion of numeric uncertainty estimates in weather forecasts improves decision quality over single value forecasts or specific advice. However, it is unclear if the benefit of uncertainty estimates extends to more complex decision tasks, presumably requiring greater cognitive effort, or to tasks in which the decision is clear-cut, perhaps making the additional uncertainty information unnecessary. In the present research, participants completed a task in which they used single value weather forecasts, either alone, with freeze probabilities, advice, or both, to decide whether to apply salt to roads in winter to prevent icing or to withhold salt and risk a penalty. Participants completed either a simple binary choice version of the task or a complex version with 3 response options and accompanying rules for application. Some participants were shown forecasts near the freezing point, such that the need for salt was ambiguous, whereas other participants were shown forecasts well below the freezing point. Results suggest that participants with uncertainty estimates did better overall, and neither the task complexity nor the coldness of the forecasts reduced that advantage. However, unexpectedly colder forecasts lead to poorer decisions and an advantage for specific advice.