This study estimates cloudiness data using meteorological parameters which include climatic variables and air quality index. Daily average observed values of all meteorological parameters used in this study were transformed to monthly mean data for 1990-2015 period. The monthly mean values of cloudiness were estimated by using the other climatic elements and the value air quality index at urban area in Kayseri. Multiple Linear Regression model was built to determine the mathematical relationships for predicting cloudiness. It has been shown that meteorological parameters affect cloudiness the most in May and October, and the least in September and January. Additionally, according to the estimated models, air quality index value has effect on cloudiness data on January, July, October and November as statistically significant.