CMStatistics 2022: Start Registration
View Submission - CFE
Title: Adjusted-range-based Kolmogorov-Smirnov type statistics for structural breaks and parameter constancy Authors:  Yongmiao Hong - Cornell University (United States)
Brendan McCabe - The University of Liverpool (United Kingdom)
Jiajing Sun - University of Chinese Academy of Sciences (China) [presenting]
Shouyang Wang - Academy of Mathematics and System Science, Chinese Academy of Sciences, (China)
Abstract: A self-normalization approach is proposed based on the adjusted range of a partial sum, which is robust to those irregularities and helps to rectify the better size but less power phenomenon for existing self-normalized statistics. We also introduce adjusted-range-based Kolmogorov-Smirnov (KS) type statistics to test for structural breaks in the mean, approximately linear statistics in general, and correlation coefficients/matrix. Furthermore, our proposed test statistics are portmanteau and can cater for general alternatives. Under suitable conditions, it can also be applied to detect the constancy of parameters. Monte Carlo simulations and empirical studies demonstrate the adequacy of our proposed method.