. The outputs of regional climate model simulations need to be corrected because of their systematic spatial and temporal biases. This study simulates bias correction using the statistical methods on rainfall data outputs generated by RegCM4.4 during the period of 1981-2005. We found that linier regression did not improve the spatial distribution and pattern of rainfall data. However, by using polynomial regression better results were performed especially third order polynomial. Moreover, when the third order of polynomial regression was combined with the zero intercept, it gave the best bias correction and therefore, can be further used for drought analysis. Standardized Precipitation Index (SPI) method was used to analyze drought index with different time scale of 1, 3, 6 and 12-months. We found that SPI performed well when implemented for time scale more than 1-month. This was demonstrated by the relationship with the rainfall anomaly and drought history during El-Nino years of 1982/1983, 1986/1987 and 1997/1998.