I have a time series data where Mann-Kendall test shows no monotonic trend and KPSS test shows no stationary trend. What should I comment about the trend then? Monotonic or stationary? Or something else? And, if I should do further analysis for comprehending the nature of such trends, what test/analysis should I apply?
Thank you in advance!
Dear Mohammad Mohaiminul Islam,
maybe you should try with other unit root tests to make your results more robust: non-parametric PP test or Ng-Perron test? Also, it is possible that there is a structural break in time series, in which case it is good to apply Zivot-Andrews or Lee-Strazicich test. Then the results might indicate the stationarity of the time series which is in line with the findings of the Mann-Kendall test.
Hope it will help.
Regards,
Vladimir
- Badges
- Science topic
- Similar topics
- Statistics
- Time Series