Time series analysis and modelling

时间序列分析和建模

• 批准号: 4145-2008
• 负责人: Roy, Roch
• 金额: $ 1.31万
• 依托单位: Université de Montréal
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2010
• 资助国家: 加拿大
• 起止时间: 2010-01-01 至 2011-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=449624
• 关键词: Time; series; analysis; modelling

Data collection over time on a particular phenomenon gives rise to a time series. Such data are collected on a regular basis for physical phenomena, for phenomena related to human activities and in many areas of science and engineering. An important role of a statistician is to help the decision maker to draw the right decisions from the available data with the most efficient modeling. In contrast with classical statistics that rely heavily on the assumption that the observations are independent, time-series data are generally correlated and it is essential to take that characteristics into account in the modeling process.

随着时间的推移，对某一特定现象的数据收集产生了一个时间序列。定期收集有关物理现象、与人类活动有关的现象以及许多科学和工程领域的此类数据。统计学家的一个重要作用是帮助决策者从可用数据中得出正确的决策，并进行最有效的建模。与严重依赖于观测独立假设的经典统计学相反，时间序列数据通常是相关的，在建模过程中必须考虑到这些特征。