Descriptions of Retrun Period and those Degrees of Experience for a Trend Model of Sea Extremes
暂无分享,去创建一个
It is important to detect the incremental tendency of extremal sea phenomena (sea level, wave height and so on) in recent short record and to predict the future's return level by extrapolating the trend line. It is noted that the extrapolation is adopted here in double senses: one is the extension of regression relation in time domain, another is that of rare occurence in probability domain. For the statistical uncertainty accompanied with those extrapolations, the degree of experience is introduced and executed for two types of return periods based on the instantaneous and mean occurence rates.
[1] David A. Belsley,et al. Regression Analysis and its Application: A Data-Oriented Approach.@@@Applied Linear Regression.@@@Regression Diagnostics: Identifying Influential Data and Sources of Collinearity , 1981 .
[2] Richard L. Smith. Extreme value theory based on the r largest annual events , 1986 .