Nonlinear Regression, Forecasting, and Optimization

Abstract

對於非線型聯立方程式，本文提供新的估計、預測與非線型最適控制方法。本文考慮餘差項所引起的估計誤差，並使用高斯西德反覆法與預測與糾正方法，所以可以預測總體經濟的最適政策指標。This study provides a new algorithm for estimation, forecasting, and nonlinear optimal control with nonlinear simultaneous equations. This algorithm can be used to forecast the optimal macroeconomic policies by considering the unprecise estimates due to noises and by combining the Gauss-Seidel algorithm and the predictor-corrector method for both short-term and long-term forecasting.