Rapidly increased the environmental pollution, global population and exhausted reserves of consuetudinary resources have become matters of social and economic concern to individuals and scientists since the ’70s. With the rising costs of traditional energy resources, alternative renewable sources of energy are playing more important role. Actually, there is the many types of renewable energy resources such as hydro, solar, wind, biomass, geothermal, wave and tide energy. Among of them, the wind energy is maybe the cleanest, inexhaustible and popular source of energy. But wind energy has several disadvantages and one of them is that winds are inherently random. Wind power prediction processes give the information of how much wind power can be expected at which point of time in the determined time interval. However, these processes required the short and long-term wind characteristics and other measurements at given location. In this respect, obtained wind speed, direction, humidity, pressure values and surface roughness information can provide fundamental and valuable information for the assessment of wind power energy availability and give knowledge/or economic viability of wind energy conversion system and also wind farm design. Turkey has important wind energy potential in the Akdeniz region, especially coasts ofsouthern Anatolia. In this study, wind energy potential was statistically analyzed based on the data that are measured wind speed on daily basis. Wind data obtained from the Directorate of Hatay Meteorological Station located Antioch which is central town of Hatay in southern Turkey, near the border with Syria in years between 2002 and 2009. precise determination of probability distribution for wind speed data is the most important issue in statistically evaluating wind speed energy potential o/‘a region. In generally, wind speed distribution have generally modeled by the 3-parameter Generalized Gamma 2-parameter Gamma inverse Gaussian, 2-parameter Lognormal 3-parameter Beta, singly truncated from below Normal, distributions derived from the Maximum Entropy Principle, and conventional or bimodal (two component mixture) Weibull distribution functions etc.. But the wind energy potential of Antioch was investigated by Weibull Distribution that is popular on the modeling of wind speed and Log-normal distribution function which is previously untested in Antioch. In the estimation o/‘parameters of Weibull and log-normal distribution, the Maximum Likelihood Estimation (ML) and the Least Square Method (LSM) were used as the parameter estimation technique. The value ofthe Weibull shape parameter is between 2. 7l and 3.07 m/s, while the scale parameter varies between 1.96 and 2.09 for ML method. When the LSM method is used, is calculated between 2.61 and 2.96 mnc, while the scale parameter varies between 2.34 and 2.53. If ML method use, the yearly values of'Log-normal scale parameter, range between 0.53 and 0.59. When LSM method preferred, 0' varies between 0.52 and 0.57. The lowest value of the Log-normal location parameter ıu are 0.72 (ML-LSIW) andq/ound in the year 2009, while the highest values were 0.84 (ML) and 0.86 (LSM), which occurred in the year 2004. There are various tests used/or evaluating the accuracy of the forecasted wind distributions obtained from various statistical functions. Both methods were evaluated by using error analysis that are coeflicient of Determination (R?) and the Average Square Root Sum of the Squares Error (RMSE). The highest root mean square error (RMSE) value was found as 0.020014 for the Lognormal distribution function by the ML method. The lowest RMSE value was calculated as 0.016242 by LSM method. Additionally these values were calculated 0.01208I(ML) and 0.014582(LSM) for the Weibull distribution. Other hand, the R2 values obtained using Log-normal distribution function are %98 in both methods, while the value is %99 for the Weibull distribution. The Weibull and Lognormal approximations of the actual probability distributions o/‘wind speed for the whole year have close results. However, the best performance has been demonstrated by Weibull distribution with the ML method. The analysis results also showed that the maximum monthly wind speed occurs in the summer months while the months of winter have the lowest mean wind speed. The Weibull distribution provided better power density estimations in all months than the Log-normal distribution. As result of this research when the wind turbines have low cut-in speed, were preferred, wind energy potential ofAntakya was statistically/ound to be encouraging for production of electrical energy.