Skip to content
Back to formatted view

Raw Message

Message-ID: <9D4B62C4-6A11-49EA-B34C-B764F1922AAE@gmail.com>
Date: 2012-10-25T09:41:57Z
From: R. Michael Weylandt
Subject: correlated events in time series
In-Reply-To: <DDDDFD4A9D76184F8562ACE0629AD4714AA19235@EXCHMBX03.fed.cclrc.ac.uk>

Yes, but you'll need to learn vector (multivariate) time series methods. See, perhaps firstly, B Pfaff's book and corresponding R packages. It's dense, but not too long and will get you going the right way. Terms like VAR and VECM will help guide your googling

Michael 

On Oct 25, 2012, at 8:34 AM, <james.foadi at diamond.ac.uk> wrote:

> Apologies in advance for the basic nature of my question.
> I've never worked with time series, but I am, at present, dealing
> with evolution in time of certain scalar quantities.
> 
> By looking at the plots, scalar quantity vs time, for several of these
> quantities, I am observing a correlation of "events" happening at specific,
> non-regularly spaced instants of time. The fact of observing them in all
> plots, to me means that they are due to some kind of objective physical
> cause.
> 
> My question is: are there well known and effective methods in time series analysis
> to extract such occurrences from multiple series? Is there any package in R that deals
> with this?
> 
> Kind regards,
> 
> J
> 
> -- 
> This e-mail and any attachments may contain confidential...{{dropped:8}}
> 
> ______________________________________________
> 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.