1. Trend Detection in the Presence of Positive and Negative Serial Correlation: A Comparison of Block Maxima and Peaks‐Over‐threshold Data.
- Author
-
O'Brien, N. L., Burn, D. H., Annable, W. K., and Thompson, P. J.
- Subjects
TREND analysis ,AUTOCORRELATION (Statistics) ,ERROR rates ,TIME series analysis - Abstract
Serial correlation in a hydrometeorological time series can have deleterious effects on trend detection tests. To account for significant autocorrelation detected in datasets, various techniques have been developed over time, each having their own assumptions and accuracy. Furthermore, the existence of positive or negative serial correlation has dissimilar effects on these statistical techniques. This research compares the power and Type I error rates of various well‐known and several newer techniques to account for positive and negative serial correlation in combination with the Mann‐Kendall nonparametric trend test. The study additionally explores the application of these techniques in the presence of higher order dependence structures. Through a case study of southern Ontario watersheds, it is determined that the block maxima series (BMS) data are more likely to have significant negative lag‐1 serial correlation. Peaks‐over‐threshold (POT) data are more likely to be serially correlated and this autocorrelation is more likely to be positive. It is determined that in the case of positively serially correlated AR(1) data, block bootstrap (BBS), Hamed and Rao (1998), variance correction (VCCF1), Yue and Wang (2004), variance correction (VCCF2), and sieve bootstrap (SBS) are the most robust. Alternatively, in the case of negative AR(1) autocorrelation, the corrected trend‐free prewhitening approach (CTFPW), modified trend‐free prewhitening (MTFPW), bias corrected prewhitening (BCPW), and VCCF1 are recommended. In the presence of higher order dependence structures, VCCF1 (with all significant lags included) and VCCF2 (with all lags included) should be applied cautiously. Lastly, an assessment of the causality of the serial correlation is provided. Key Points: Numerous techniques to account for serial correlation when applying the nonparametric Mann‐Kendall (MK) Test are compared through various meansBlock maxima data exhibit less evidence of significant serial correlation; more instances of significance found in over threshold dataRecommendations provided based on the memory structure of the data and the causality of significant serial correlation, is also explored [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF