We compare and analyze the spatial distribution,seasonal and decadal variations,and the coefficient distribution of climate trend in haze days under three identification methods using 34 year (19812014) surface observation data from 156 stations in Sichuan. The periodic variation characteristics are analyzed by using the Morlet wavelet transformation. The results show that the original observation of haze days was concentrated in northern Sichuan Basin. Haze days were however concentrated in the south and east of the basin by using method I. Haze days were concentrated in the basin area without representative high value area by using method II. The distribution characteristics from method III are similar to them from method I. Different identification methods show similar seasonal variation of haze days higher in fall and winter than spring and summer. Haze days in Sichuan show obvious decadal variation. The original observation of haze days suddenly increased in 2013. Haze days have significant increase from the beginning of 2001. Inter-decadal variations from method I are similar to them from method III. The climate trend of original observation is not obvious. The coefficients obtained from method I show a reverse change from north to south. The distribution from method II is similar to that from method I. The positive and negative zones are more concentrated using method III. The wavelet transform results indicate insignificant periodic change in the original observation of haze days. Discrimination method I,II and III have their own periodic variations characteristics.