Non gaussian time series modeling, dealing with outliers, censoring and long memory and process improvement

拟议的研究是商业、金融和工业时间序列建模和统计领域正在进行的研究方案的一部分。评估和预测金融市场的波动性需要对金融数据进行适当的建模和分析。这个项目的目标之一是开发新的随机波动率模型，设计有效的方法来估计它们，并检查它们的充分性。许多环境政策决策和各种环境法规的实施需要从适当收集和适当分析的数据中获得准确的信息。该提案的第二个目标是制定新的方法并加强现有方法，以收集和分析水质时间序列数据，以评估水质趋势和其他方面。商业和制造组织竞争地位的提高显然与质量改进活动有关。使用适当的统计方法是质量改进的重要组成部分。拟议研究的目标之一是开发新的统计方法，并改进可应用于加拿大工商业质量改进工作的现有方法。

The proposed research is part of an ongoing research programme in the areas of time series modeling and statistics in business, finance and industry. Assessing and predicting volatility in financial markets require the appropriate modeling and analysis of financial data. One of the objectives in this project is to develop new stochastic volatility models, devising efficient methods for estimating them, and checking for their adequacy. Many environmental policy decisions and the implementation of various environmental regulations require accurate information obtained from properly collected and appropriately analyzed data. A second objective of the proposal is to develop new methods and enhance existing ones for the collection and analysis of water quality time series data to assess trends and other aspects of water quality. Improved competitive position of business and manufacturing organizations is clearly linked to Quality Improvement activities. The use of appropriate statistical methods is an important part of Quality Improvement. One of the objectives of the proposed research is to develop new statistical methodology and to enhance existing methods that can be applied to Quality Improvement efforts in Canadian business and industry.