Understanding and minimizing the uncertainties in the wind energy field is of high importance to reduce the reliability risks and financial risks of wind farm projects. The present work aims to observe the levels of uncertainty in modeling the wake effect by attempting to perform statistical inference of a wake parameter, the wind speed deficit. For this purpose, an uncertainty propagation framework is presented. The framework starts by randomly sampling mean wind speed data from its probability density function (PDF), that is fed an inflow model (TurbSim), resulting in random full-flow fields that are integrated into an aeroelastic model (FAST), which results in the variability of the power and thrust coefficients of a wind turbine. Such coefficients and wind data, finally, fed the wake engineering model (FLORIS). The framework ends with the determination of the 95% coefficient intervals of the time-averaged wind speed deficit. The results obtained for the near and far wake regions introduce fundamentals in estimate the uncertainty in wind speed deficit of a single wind turbine wake and concludes that a systematic uncertainty quantification (UQ) framework for wind turbine wakes may be a useful tool to wind energy projects.