摘要：Based on the research technology of scholars’ prediction of farmers’ income and the data of per capita annual net income in rural households in Henan Statistical Yearbook from 1979 to 2009, it is found that time series of farmers’ income is in accordance with I(2) non-stationary process. The order-determination and identification of the model are achieved by adopting the correlogram-based analytical method of Box-Jenkins. On the basis of comparing a group of model properties with different parameters, model ARIMA (4, 2, 2) is built up. The testing result shows that the residual error of the selected model is white noise and accords with the normal distribution, which can be used to predict farmers’ income. The model prediction indicates that income in rural households will continue to increase from 2009 to 2012 and will reach the value of 2 282.4, 2 502.9, 2 686.9 and 2 884.5 respectively. The growth speed will go down from fast to slow with weak sustainability.
