论文部分内容阅读
为了研究时间序列理论中自回归AR(p)模型,采用最小二乘方法求解模型参数时未考虑数据相关性的问题,引进总体最小二乘这种能够处理系数矩阵和观测矩阵同时存在偶然误差的平差方法,将总体最小二乘平差准则用于自回归AR(p)模型的参数解算,讨论了AR(p)模型的阶数p的确定方法。结合建筑物沉降数据的分析与预测结果,表明基于总体最小二乘准则的时间序列分析方法得出的模型更加准确,短期预测效果更好。
In order to study autoregressive AR (p) model in time series theory, the least squares method is used to solve the model parameters without considering the data correlation problem. The introduction of total least squares (LSLS), which can cope with the coincidence error of the coefficient matrix and the observation matrix Adjustment method, the global least squares adjustment criterion is used to solve the parameter of autoregressive AR (p) model, and the method of determining order p of AR (p) model is discussed. Combined with the analysis and prediction results of building settlement data, it shows that the model based on the least-squares criterion of time series analysis is more accurate and the short-term forecasting effect is better.