I am trying to test for seasonality of the time series using Kruskal-Wallis test. My data is in the form of months and spans over 3 years. i want to do a quarterly analysis specifically oct-dec of every year.
This is the code i used:
p<-ts(data=data$rupee, frequency = 12)
q<-aggregate(p, nfrequency=4)
I got a p-value>0.05. However, my plot seems to indicate indicate seasonality:
Decomposed ts
Please let me know what I’m doing wrong.
New contributor
Sruthi is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.