This article presents an efficient method for power transformer tap position estimation based on the Hypothesis Testing for a Population Mean. To have a good performance, energy management system requires a precise model of the modern power networks. This makes the parameter estimation to be a vital part, and the transformer tap position is a crucial parameter in the networks. Therefore, this article focuses on the transformer tap position estimation. To this aim, the power system states are estimated for all tap positions using the measurements and the weighted least-squares (WLS) method. Then, the estimated measurements are calculated by the estimated states. Finally, the mean of every measurement is compared with its estimated value by employing the Hypothesis Testing for a Population Mean, and the tap ratio with the largest correct responses is identified as the correct one. Simulations are done on both the IEEE 14-bus system and a power network of Iran, showing the reliability and efficiency of the proposed method over the most recent ones.