How can I test temporal autocorrelation of binary data?
Since the data is dichotomous already, the nonparametric 'runs test' might be appropriate, though I am ignorant as to its properties (power in particular). help(runs.test,package=tseries) Regards, Andreas ----- Original Message ----- From: "Patrick Burns" <pburns at pburns.seanet.com> To: <dschad at umich.edu> Cc: <r-help at stat.math.ethz.ch> Sent: Monday, October 31, 2005 6:49 PM Subject: Re: [R] How can I test temporal autocorrelation of binary data?
If you mean you want to test that there is no autocorrelation, then there is some information on using the Ljung-Box test on such data in the working paper 'Robustness of the Ljung-Box test and its rank equivalent' on the Burns Statistics website. The executive summary is that the test seems to do okay as long as one of the values is not too dominant. What 'dominant' means depends on the length of the series. If some one has a better answer, I'm keen to hear it. Patrick Burns patrick at burns-stat.com +44 (0)20 8525 0696 http://www.burns-stat.com (home of S Poetry and "A Guide for the Unwilling S User") dschad at umich.edu wrote:
Hi, I have a binary (o/1 - coded) data set and want to test it's autocorrelation structure. Is that function implemented in R? Can I use the ACF - funtion with binary data? Thanks for your help, Daniel
______________________________________________ R-help at stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
______________________________________________ R-help at stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html