Robust Modeling for Factors Affecting in Relative Humidity in Basra Governorate

Abstract

Basra Governorate is considered among the Iraqi governorates, with high levels of relative humidity sometimes, which makes the weather uncomfortable during the year. It was necessary to building in this research a robust regression model to study the effect of some factors such as the maximum and minimum temperatures, the amount of rainfall, atmospheric pressure, and the average amount of dust falling. When building linear regression models, many problems occur in which failure some of the hypotheses model. In this research, least squares estimates were compared with robust and found the preference for the method of S.