A study was conducted to determine whether air traffic control (ATC) communication events would predict subjective estimates of controller workload as well as measures of controller taskload. We compared different regression models� predictions of subjective workload estimates made by 16 subject matter experts on 5 occasions during 8 samples of air traffic activity. The predictors were different combinations of four taskload principal components computed from routinely recorded ATC data, two principal components representing the number and duration of voice communication events, and two principal components representing the content of voice communications.