A work-zone introduces unexpected conditions for road users and may cause severe safety issues. This study aims to understand drivers’ pre-crash improper actions, which are the major contributing factor to the crash occurrence and outcomes severity in single-vehicle (SV) work-zone crashes. A mixed logit model with heterogeneity in mean and variance was developed using Florida’s seven-year work-zone crash data. The estimated models investigated five pre-crash improper actions (no contributing action, careless driving, speeding, swerving lanes, and other pre-crash actions) in SV work-zone crashes. Year-paired likelihood ratio tests identified temporal instability existing in the dataset over the study period and suggested yearly model estimation to capture the temporal instability. The model results identified a wide range of variables that impact drivers’ pre-crash improper actions, such as driver and weather conditions, work-zone type, and temporal and lighting characteristics. The findings of this study imply that driving psychology plays a critical role in safety-related driving behaviors in work-zone areas. Engineering or education countermeasures that could increase driver alertness of potential hazards are suggested to reduce improper actions by drivers and improve work-zone safety.