The successful design and effective utilization of solar energy systems and devices for application in various facets of human needs, such as power and water supply for industrial, agricultural and domestic uses, largely depend on the availability of information on solar radiation characteristic of the location in which the system and devices are to be situated. The diffuse solar radiation for eight stations in Nigeria is estimated using Klein (1977) model. A statistical analysis of monthly mean correlation is examined, using a 16 years achieve (1995- 2010) of monthly mean of global and diffuse solar radiation obtained at eight selected meteorological stations over Nigeria area. The accuracy of the candidate correlations are performed in terms of the two widely used statistical indicators, mean bias (MBE) and root mean square errors (RMSE). The results indicate that the correlations relating the diffuse fraction (Kd) with clearness index (KT), the relative sunshine duration (S/Smax), relative humidity and ratio of maximum to minimum daily temperature are more reliable for diffuse radiation predictions in the Nigerian environment than using each variable separately. The study found that the present correlation produced the best estimates of diffuse solar radiation.