Objective:To forecast the monthly incidence of hepatitis A,B and C in China by state space model. To analyze the relationship between the accuracy of prediction and the cycle regularity of the incidence,and to provide a new approach to forecast the incidence of hepatitis. Methods:State space model was fitted with data of monthly reported cases of hepatitis A,B and C in China from 2005 to 2013. The SSM toolbox of MATLAB software was performed to construct the state space model,and the constructed model was applied to predict the monthly incidence of 2014. The evaluation index of the cycle regularity of the incidence was established by standardizing data. Results:The average relative error of prediction of hepatitis A,B and C was 17.03%,6.30% and 2.03%,respectively,and the mean periodic standard deviation of the standard data was 0.2143,0.1952 and 0.1724,respectively. Conclusion:The state space model can be fitted and performed to make a short-term prediction of the incidence of hepatitis. When the periodic standard deviation of the standardized data is smaller,the predicted result is more accurate.