顾及偏态的IQR法则在GPS时间序列异常值探测中的应用

Consider the IQR Law in the Detection of Outlier in Time Series Considering Skewness

引入非正态数据分布偏态因子MC值对GPS时间序列的偏态性进行度量,并构造相应的函数,改进标准IQR法则中异常值的探测区间。利用Sopac提供的CHAN站时间序列进行实验,剔除异常值后进行插补,人工添加不同量级、不同密度的异常值。分别对比两种方案的探测结果,证实顾及偏态的IQR法则较标准IQR法则算法更严谨、探测效果更好。

In order to analyze the skewness of GPS time series data,a skewness factor MC is introduced for measurement as well as construction of the corresponding function in order to improve the detection range of the IQR law.We interpolate after rejecting the outliers,using the time series of the CHAN IGS station provided by Sopac experimental sequence,artificially adding different orders of magnitude and different densities of outlier.We confirmed that the IQR law considering skewness is more rigorous in algorithm and more effective in outlier detection than IQR law alone.