[R] Trend significant at p=0.05?

Chattopadhyay, Somsubhra sch298 at g.uky.edu
Mon Mar 14 16:49:04 CET 2016


I am trying to calculate trends in my climatic time series, using the "Zyp"
package. Initially, I tried with my daily data (I have daily rainfall data
of 30 years) but then both the Zhang method and Yue-Pilon method yielded
unrealistic results. The trend estimates were zero and so were the
confidence limit bounds. But I guess, that is because the noise in the
daily data. So, I converted my time series to annual data and now I see the
attached output. I see that there is a positive trend, but my question is
is this trend significant at 95% confidence interval? I suspect no because
the confidence interval contains zero? Can anyone please confirm?

I also attached the autocorrelation plot of the original time series.


*Somsubhra Chattopadhyay*
Graduate Research Assistant
Biosystems and Agricultural Engineering Department
University of Kentucky, Lexington, KY 40546
Email: schattop14 at uky.edu
Cell: 9198026951
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ACF.png
Type: image/png
Size: 3898 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20160314/33e7a780/attachment.png>

More information about the R-help mailing list