The purpose of this paper was to analyze the content of impact prediction in EISS, in order to find the degree of the acuracy of impact prediction . 30 EISS were selected as analysis objects through variance miximization strategy. Content analysis of the selected EISS was performed by 5 analysis items, such as quantification of measurement, range of impact area, time frame of impact, likelihood of impact, and explict characterization of impact significance. The results showed that the accuracy investigated by the 5 items was very low. In conclusion, 5 suggestions were proposed in order to improve the credibility of EIS as a scientific report. The 5 suggestions were : 1) impact prediction should be described by quantitative measurement; 2) In establishing the time frame of the impact and the referent populatioin influenced by the impact, the characteristics of the proposed action should be carefully considerd; 3) the significance of the predicted impact should be quantitatively described; 4) specific description should also be used in the likelihood or the probability of the predicted impact in a real world; 5) equal emphasis should be put on the three environment, including natural and social as well as living environment.