[R] Application of rolling window in entropy analysis

[Eric Berger]

How about something like this:

ts= India[-1,]   #####For deleting the year row
N<-ncol(ts)
width <- 500
M <- nrow(ts) - width
r<-matrix(0, ncol = N, nrow = M)
library(pracma)
for (i in 1:N){
       r[,i]<-rollapply( data=ts[,i], width=width, FUN=approx_entropy, edim
= 2, r = 0.2*sd(ts[,i]), elag = 1, align="right")
}

Best,
Eric



On Fri, Nov 2, 2018 at 12:15 PM Subhamitra Patra <subhamitra.patra using gmail.com>
wrote:

> Thank you for the clarification. I checked and there was a small
> mistakes in the code. Now my code is
>
> ts= India[-1,]   #####For deleting the year row
> N<-ncol(ts)
> r<-matrix(0, ncol = N, nrow = 1)
> library(pracma)
> for (i in 1:N){
>        r[i]<-approx_entropy(ts[,i], edim = 2, r = 0.2*sd(ts[,i]), elag = 1)
> }
>
> Even with this code also, I am unable to apply rollapply function.
>
> Kindly help me.
>
>
> [image: Mailtrack]
> <https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality5&> Sender
> notified by
> Mailtrack
> <https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality5&> 11/02/18,
> 3:44:26 PM
>
> On Fri, Nov 2, 2018 at 3:42 PM Eric Berger <ericjberger using gmail.com> wrote:
>
>> Hi,
>> You have some problems with your setup. You set N based on the number of
>> rows in ts, but then in the call to approx_entropy you write ts[,i].
>> Note that ts[,i] is the i'th column of ts, whereas your definition of i
>> implies it is based on row numbers.
>>
>> Maybe this is leading you to see problems elsewhere. From the rollapply
>> documentation I don't see any reason why it would not work with the
>> approx_entropy function.
>>
>> Best,
>> Eric
>>
>>
>> On Fri, Nov 2, 2018 at 11:16 AM Subhamitra Patra <
>> subhamitra.patra using gmail.com> wrote:
>>
>>> Dear all R users,
>>>
>>> I want to apply the entropy methods in rolling window analysis. I tried
>>> with the rollapply function, but it is not working. For your
>>> convenience, I
>>> am providing my code so that you can easily suggest me the application of
>>> rolling window in the particular methodology. Here is my code
>>>
>>> N<-nrow(ts)
>>> r<-matrix(0, nrow = N, ncol = 1)
>>> for (i in 1:N){
>>>      r[i]<-approx_entropy(ts[,i], edim = 2, r = 0.2*sd(ts[,i]), elag = 1)
>>> }
>>>
>>> Kindly suggest me how to apply rolling window size of 500 in the
>>> particular
>>> time series model?
>>>
>>> I expect positive help from you.
>>>
>>> Thanks in advance.
>>>
>>> --
>>> *Best Regards,*
>>> *Subhamitra Patra*
>>> *Phd. Research Scholar*
>>> *Department of Humanities and Social Sciences*
>>> *Indian Institute of Technology, Kharagpur*
>>> *INDIA*
>>>
>>>
>>> [image: Mailtrack]
>>> <
>>> https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality5&
>>> >
>>> Sender
>>> notified by
>>> Mailtrack
>>> <
>>> https://mailtrack.io?utm_source=gmail&utm_medium=signature&utm_campaign=signaturevirality5&
>>> >
>>> 11/02/18,
>>> 2:44:12 PM
>>>
>>>         [[alternative HTML version deleted]]
>>>
>>> ______________________________________________
>>> R-help using r-project.org 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.
>>>
>>
>
> --
> *Best Regards,*
> *Subhamitra Patra*
> *Phd. Research Scholar*
> *Department of Humanities and Social Sciences*
> *Indian Institute of Technology, Kharagpur*
> *INDIA*
>

	[[alternative HTML version deleted]]