论文部分内容阅读
一、背景时间序列分析是概率统计学中的一个重要分支。它用概率统计方法预测随时间变化的随机数据序列,包括建立模型,参数估计以及确定最佳预测等内容。近几年来,在工业、农业、国防、科技等多个领域中都得到了广泛的应用。过去,上海市政府有关部门每月在下旬初要对下一个月的市工业总产值作出预估。据反映,由于主要靠经验、资料和推断,预测精度受到一定影响。为此,我们以市经委提供的上海市近年来的工业(月)总产值历史数据(1980年1～9月)为基础,选用了关系式数据分析软件包RDAS中TIME SERIES分析等过程,对上述原始数据进行了分析、处理,建立了
First, the background Time series analysis is an important branch of probability statistics. It uses probabilistic statistics to predict random data sequences that change over time, including building models, estimating parameters, and identifying best predictions. In recent years, it has been widely used in many fields such as industry, agriculture, national defense and science and technology. In the past, the relevant departments of the Shanghai municipal government estimated the gross industrial output value of the city in the next month at the beginning of each month. It is reported that, due mainly to experience, data and inference, prediction accuracy is affected to a certain extent. Therefore, on the basis of historical data of industrial output in Shanghai in recent years (from January to September, 1980) provided by Shanghai Municipal Commission of Economic Research, we selected TIME SERIES analysis of RDAS in relational data analysis software package, The original data was analyzed, processed and established