Wind turbine selection is a critical engineering problem in the overall cost-effectiveness of a wind project. With the wide spreading and democratization of wind energy technologies, non-expert stakeholders are being faced with the challenge of selecting among very different wind turbines. As a comprehensive indicator, the cost of energy can serve as a guide, but reportedly misleading publicity and commonly unavailable information render its calculation more inaccessible and less reliable. Accordingly, this work proposes a method to compare wind turbines, on the basis of the cost of energy, from only nominal specifications and a standard characterization of the local wind conditions. For this endeavor, it was identified that two key variables are not usually available at a preliminary stage: the total efficiency and a feasible hub height. Through a systematic statistical analysis of the trends in a constructed dataset of 176 turbines, it was possible to establish regression models for the estimation of both variables. These models were tested in a validation set and their estimations were found to correctly characterize the central trend of the data without significant deviations. The uncertainty related to the use of both models was addressed by analyzing the 95% Prediction Intervals and the stochastic rank dominance. The established statistical models were then used as the core of the proposed selection method. When the available information is limited or not trustworthy, the steps of the method can be followed as an approach to estimate the cost of energy of a given horizontal axis wind turbine in a given location.