Considering the problems that should be solved in the synthetic earthquake prediction at present, a new model is proposed in the paper. It is called joint multivariate statistical model combined by principal component analysis with discriminatory analysis. Principal component analysis and discriminatory analysis are very important theories in multivariate statistical analysis that has developed quickly in the late thirty years. By means of maximization information method, we choose several earthquake prediction factors whose cumulative proportions of total sam-ple variances are beyond 90% from numerous earthquake prediction factors. The paper applies regression analysis and Mahalanobis discrimination to extrapolating synthetic prediction. Furthermore, we use this model to charac-terize and predict earthquakes in North China (30~42N, 108~125E) and better prediction results are obtained. It is called called joint multivariate statistical model combined by principal component analysis with discriminatory analysis. Principal component analysis and discriminatory analysis are very important theories in multivariate statistical analysis that has developed quickly in the late years years. By means of maximization information method, we choose several earthquake prediction factors whose total proport proportions of total sam-ple variances are beyond 90% from numerous earthquake prediction factors. analysis and Mahalanobis discrimination to extrapolating synthetic prediction. Furthermore, we use this model to charac-terize and predict earthquakes in North China (30-42N, 108-125E) and better prediction results were obtained.