Hello.
> Is it possible to determine time delay with other function's output or
I
> can choose any random value?
There are several ways to estimate time delay in chaotic time series
analysis.
Please refer to the book "Nonlinear time series analysis" by Holger
Kantz
and Thomas Shreiber.
http://www.amazon.com/Nonlinear-Time-Analysis-Holger-Kantz/dp/0521529026
http://www.amazon.com/Nonlinear-Time-Analysis-Holger-Kantz/dp/0521529026
For example, time delay is defined as the time when average mutual
information reaches the first local minimum.
Using the package "tseriesChaos", it is estimated as follows:
> library(tseriesChaos)
> x.mu <- mutual(x, plot=FALSE)
> x.mu.d <- diff(x.mu)
> d <- min(which(x.mu.d > 0)) - 1
The last two can also be simplied.> d <- which.min(x.mu) - 1
Recently, in Japan, a book has been published on useful packages of R.
http://www.amazon.co.jp/R%E3%83%91%E3%83%83%E3%82%B1%E3%83%BC%E3%82%B8%E3%82%AC%E3%82%A4%E3%83%89%E3%83%96%E3%83%83%E3%82%AF-%E5%B2%A1%E7%94%B0-%E6%98%8C%E5%8F%B2/dp/448902097X
http://www.amazon.co.jp/R%E3%83%91%E3%83%83%E3%82%B1%E3%83%BC%E3%82%B8%E3%82%AC%E3%82%A4%E3%83%89%E3%83%96%E3%83%83%E3%82%AF-%E5%B2%A1%E7%94%B0-%E6%98%8C%E5%8F%B2/dp/448902097X
I wrote an article on the packages "RTisean" and
"tseriesChaos".
There, I showed an example of estimating the maximum Lyapunov exponent,
using the NH3 laser data.
The source code is available from the following website.
https://gist.github.com/4efa66686c24f158f7e9
https://gist.github.com/4efa66686c24f158f7e9
I would be happy to be of any service to you.
--
View this message in context:
http://r.789695.n4.nabble.com/problem-with-library-tseriesChaos-tp3449830p3473028.html
Sent from the R help mailing list archive at Nabble.com.