分位数回归在时间序列中的应用-概率论与数理统计专业论文.docx

ABSTRACT l咱 、 (，.. Time series analysis is one of the modern statistical methods in the prφ cessing of data. Its theory and method have been widely applied to engineering technology，meteorology，hydrology，earthquake，biomedicine ，economic man agement ，military science and so on. Time series analysis model the timeordered data，analyze its dynamic structure and law of development ，then predict the future. Time series data involves so many areas，and its structure is also com- plicated and diversified. Random error distribution in model will appears different featur创 for different data types，such asωymmetric or thick tail. There is not any requirement to the distribution of random errors，when we estimate the parameters in model with quantile regression. Quantile regre分 sion could also estimate the quantile function of conditional distribution ，and describe the features in different locations by 创timating function in different quantiles. In this paper ，we model the time series data by quantile regression. Its on the basis of studying quantile regression and time series thωry，we collect monthly sales data about Australian wine and analyze this time 肥ries data with quantile regression. Then，we estimate and test the model parameters in different quantiles，further forecast the sales of wine. Therefore ，quantile regression can get more complete information compared to the usual time series models. 飞 KEY WORDS: Quantile Rβgression ，Time Series，AR，MA，ARMA 第…章绪论 第…章绪论 目录 第一章绪论 1 1.1 分位数回归的研究现状 1 1.2 论文的主要内容与创新点 2 第二章分位数回归的基本理论 4 2.1 基本定义 4 2.2 分位数回归的性质... 5 飞 2.2.1 同变性 6 问 2.2.2 稳健性 6 2.3 分位数回归的渐近理论... 9 2.3.1…致性.. 11 …. 9 2.3.2 渐近性 11 第三章时间序列模型 13 3.1 时间序列的基本概念 13 3.1.1 时间序列的定义 13 3.1.2 自回归模型 14 3.1.3 移动平均模型 15 3.1.4 自凹归移动平均模型 15 3.1.5 自相关函数 16 3.1.6 偏自相关函数 18 3.2 时间序列的建模 ，.，... ... ，?.?? 11. 四 3.2.1 时间序列数据的预处理和模型的识别 19 3.2.2 模型的参数估计 21 (. 3.2.3 模型的检验和优化 ... 24 第四章澳大利亚月度红酒销最实证分析 26 唱 第五章结束语 31 参考文献 32 附录A R 程序 36 致谢 39 III