A new method: multi-factor trend regression and its application to economy forecast in Jiangxi

The principle of a new method called Trend Regression is introduced and applied to the economy forecast of Jiangxi Province. The method improved previous time series forecasting method in which only self-extension is done and multiple factors (variables) are not taken into consideration. Also, it got over the weakness of forecasting by general regression analysis that relies on simultaneous independent variables. A time series is the function of multiple factors. The values (independent variables) in a period may affect the value (dependent variable) to be predicated in the next period. The nearer the sample time to the predicted time, the more important the sample to the predict value. By shifting the dependent variable to establish models, sequential regression and prediction can be realized. In this way the trend of information can be mined.