I reckon you misunderstand the function arima. If you're interested in the significance of any regressor, you should use the proper fitting tools. Check all the code examples from the book I recommended before on :
http://www.stat.pitt.edu/stoffer/tsa2/index.html There's a nice tutorial that explains quite well how to proceed. In the code for chapter 1-5 they give you examples for the functions you need to do formal testing of your regressors. Cheers Joris On Wed, May 26, 2010 at 1:28 AM, Jianyun Wu <jianyun.fred...@gmail.com>wrote: > Thanks for ur reply. But wot i want is to see the significancy of > intervention regressors,rather than see the goodness of fit of time > series itself. > > Thanks > > On 5/26/10, Joris Meys <jorism...@gmail.com> wrote: > > Check http://cran.r-project.org/doc/contrib/Ricci-refcard-ts.pdf for > some > > ideas on testing time series in R. I'd go with the acf() and pacf() on > the > > residuals of the arima model. If arima works, both plots will indicate > > absence of autocorrelation. > > > > also check ?tsdiag > > > > And if you're really going to use those more often, I really can > recommend > > this book : > > > http://www.amazon.com/Time-Analysis-Its-Applications-Statistics/dp/0387293175 > > > > Cheers > > Joris > > On Tue, May 25, 2010 at 9:34 AM, Fred <jianyun.fred...@gmail.com> wrote: > > > >> Hi, > >> > >> I want to give a summary or anova for "arima" model in R, as > >> "summary", and "anova" for "lm". > >> > >> As including various intervention factors in arima(xreg = ) part, I > >> want to assess the significancy of thse factors. > >> > >> I can do it using interrupted analysis of time series by linear > >> regression, but want to see whether arima model works for the data > >> first. > >> > >> "summary", "anova" do not work for "arima", any alternatives ??? > >> > >> Thank you very much. > >> > >> Fred > >> > >> ______________________________________________ > >> R-help@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. > >> > > > > > > > > -- > > Joris Meys > > Statistical Consultant > > > > Ghent University > > Faculty of Bioscience Engineering > > Department of Applied mathematics, biometrics and process control > > > > Coupure Links 653 > > B-9000 Gent > > > > tel : +32 9 264 59 87 > > joris.m...@ugent.be > > ------------------------------- > > Disclaimer : http://helpdesk.ugent.be/e-maildisclaimer.php > > > > -- > Sent from my mobile device > -- Joris Meys Statistical Consultant Ghent University Faculty of Bioscience Engineering Department of Applied mathematics, biometrics and process control Coupure Links 653 B-9000 Gent tel : +32 9 264 59 87 joris.m...@ugent.be ------------------------------- Disclaimer : http://helpdesk.ugent.be/e-maildisclaimer.php [[alternative HTML version deleted]] ______________________________________________ R-help@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.
