Abstract: Traditional regression models need enormous historic data,and it is very hard to build this kind of mo del.With those limitations,a grey combined forecast model,based on grey incidence degree and GM (1,1) mo del,is put forward. This model seeks dependency relationships of sequences based on the grey incidences degree,employs the GM(1,1)model to forecast the trend of development among data,and then a forecast model about dependent variable is set up.The model not only reflects the modeling thought of regression analysis based on causality,but also has the characteristics of small example for building model.The GDP in 2007 and 2008 are forecasted with this model,and the results illustrate the validity and practicability of the novel model.

Key words: forecast technology, combined forecast model, grey incidence degree, regression analysis, GM(1,1) model