One promising way to address turbine durability issues is early detection of mass and aerodynamic imbalances. More probabilistic methods are necessary to improve the accuracy of rotor imbalance diagnostics. The research question that this work addresses is: can current imbalance detection for an offshore wind turbine be improved through uncertainty quantification of its operating conditions? An uncertainty quantification strategy was proposed to model uncertainties in wind speed, pitch angle, and blade mass density using assumed probability density functions based on available data/information. These input parameters served as random variables that were fed into an aeroelastic software to model dynamic and power output variables for multiple imbalance scenarios. 4% variation in wind speed exhibited power differences as much as 500-kW for given imbalance cases. Additionally, the results indicated that a 10% variation in pitch angle, and blade mass density demonstrated power differences of 20-kW and 10-kW respectively due to imbalance in one blade. In addition, probability distributions for power output and dynamic loading indicated that turbine underperformance and excessive blade loading occurred approximately 40–52% and 45–77% of the time respectively depending on the imbalance scenario. This imbalance detection strategy could serve as a useful tool to help minimize turbine operation uncertainties.