false.nearest on tseriesChaos

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

false.nearest on tseriesChaos

norqui
Dear all:

I am new in R and in Analysis of Chaotic Time Series. I have seen that the package tseriesChaos
can estimate the embedding dimension using the FNN. In this program false.nearest does the work,
but to use it, I need the escape factor(rt) and the neighborhood diameter (eps = sd(x)/10).
My problem is that I do not understand the definitions of these parameters.
I have read Kennel, Brown, and Abarbanel�s paper. There the authors suggest two criteria for the embedding dimension looking at the FNN. One is the ratio between the distances in d and d+1 dimensions, respectively. If such ratio is bigger than a threshold R_tol, then one has a false neighbor.
The second criterio is that R_{d+1} > A_{tol} x fractal size then one has a FNN.
 What these thresholds  R_{tol} and A_{tol}  have to do  with the escape factor and the eps?


I hope someone can help me.
Thanks

        [[alternative HTML version deleted]]


______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.
Reply | Threaded
Open this post in threaded view
|

Re: false.nearest on tseriesChaos

Jeff Newmiller
This theory question doesn't seem on-topic here. Read the Posting Guide mentioned below... contact the package maintainer if the package description doesn't inform you where to go for support.

On January 3, 2021 11:07:48 PM PST, "Norma Elizabeth Quiroz Pérez" <[hidden email]> wrote:

>Dear all:
>
>I am new in R and in Analysis of Chaotic Time Series. I have seen that
>the package tseriesChaos
>can estimate the embedding dimension using the FNN. In this program
>false.nearest does the work,
>but to use it, I need the escape factor(rt) and the neighborhood
>diameter (eps = sd(x)/10).
>My problem is that I do not understand the definitions of these
>parameters.
>I have read Kennel, Brown, and Abarbanel�s paper. There the authors
>suggest two criteria for the embedding dimension looking at the FNN.
>One is the ratio between the distances in d and d+1 dimensions,
>respectively. If such ratio is bigger than a threshold R_tol, then one
>has a false neighbor.
>The second criterio is that R_{d+1} > A_{tol} x fractal size then one
>has a FNN.
>What these thresholds  R_{tol} and A_{tol}  have to do  with the escape
>factor and the eps?
>
>
>I hope someone can help me.
>Thanks
>
> [[alternative HTML version deleted]]

--
Sent from my phone. Please excuse my brevity.

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.