[R] Contradicting results on stationary test!!!

Jeff Newmiller jdnewmil at dcn.davis.CA.us
Sat Mar 29 15:38:21 CET 2014


This is a question about statistics theory, not about R, so it is off topic here... you might try discussing this at the CrossValidated forum. In general, the amount of lag that is relevant depends on how you intend to use the data. This is not unlike the application of linear models to nonlinear processes when only a very limited domain is of interest.
---------------------------------------------------------------------------
Jeff Newmiller                        The     .....       .....  Go Live...
DCN:<jdnewmil at dcn.davis.ca.us>        Basics: ##.#.       ##.#.  Live Go...
                                      Live:   OO#.. Dead: OO#..  Playing
Research Engineer (Solar/Batteries            O.O#.       #.O#.  with
/Software/Embedded Controllers)               .OO#.       .OO#.  rocks...1k
--------------------------------------------------------------------------- 
Sent from my phone. Please excuse my brevity.

On March 28, 2014 6:31:23 PM PDT, ritesh_061176 <ritesh.kumar at mail.mcgill.ca> wrote:
>I have a time series with 1100 rows of data and am getting
>contradicting
>results from these tests:1) My ACF and PACF plots have lot of lags and
>upon
>looking visually, it looks as if the series in not-stationary.2) But
>when I
>do the ADF test with with lag=30, I reject the null and conclude that
>series
>is stationary.3) When I do the ADF with 100 lags, I end up accepting
>the
>null and have to interpret that series is non stationary.Which one
>shall I
>choose here ?  What is the correct way to go about in these situations.
>    
>
>
>
>--
>View this message in context:
>http://r.789695.n4.nabble.com/Contradicting-results-on-stationary-test-tp4687790.html
>Sent from the R help mailing list archive at Nabble.com.
>	[[alternative HTML version deleted]]
>
>______________________________________________
>R-help at r-project.org mailing list
>https://stat.ethz.ch/mailman/listinfo/r-help
>PLEASE do read the posting guide
>http://www.R-project.org/posting-guide.html
>and provide commented, minimal, self-contained, reproducible code.




More information about the R-help mailing list