Valery Khamenya
2015-Nov-23 10:04 UTC
[R] Spectral density estimations for irregular time-series
Jeff, many thanks for your answer. On Sun, Nov 22, 2015 at 8:40 PM, Jeff Newmiller <jdnewmil at dcn.davis.ca.us> wrote:> Since you seem to have trouble reading (the Posting Guide warns you to post here using plain text format emails.. doing so will be to your benefit when we can see what you posted clearly),the body of the email sent by me has had both plain-text and html representations. I found no clear confrontation with the Posting Guide for this case.> perhaps it is not clear to you that the Task View is referring to contributed packages that have their own documentation.that's clear. To my understanding primary purpose of a Task View is giving a (over)view about the R-packages that one could use while addressing the respective task. The Task View this time was not enough to locate the needed package, so I had to admit I need a help. If the r-help mail-list isn't the right place to ask for a help to locate a relevant R-package then I'm a bit confused, but would kindly ask for redirecting me to a mail-list that is more relevant for my question.> Also, please be aware that a significant hurdle to applying spectral analysis in any calculation tool is familiarity with the underlying theory. Doing so with irregular samples is going to be even more challenging, and this is not an appropriate forum for learning such topics.I do confirm, that my focus was and is to locate an R-package that provides at least one function in its API to estimate power spectrum for the irregular time series. kind regards and thanks in advance for any help, Valery.> On November 22, 2015 10:23:34 AM PST, Valery Khamenya <khamenya at gmail.com> wrote: >> >> Hi, >> >> I fail to find libraries to estimate the spectral density for irregular >> time-series. >> >> This entry from "CRAN Task View: Time Series Analysis": >> >> [...]Various packages implement irregular time series based on "POSIXct" >> time stamps, intended especially for financial applications. These include >> "its" from its, "irts" from tseries, and "fts" from fts. [...] >> >> is rather not that much helping. >> >> best regards >> -- >> Valery >> >> [[alternative HTML version deleted]] >> >> ________________________________ >> >> R-help at 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. > > > -- > Sent from my Android device with K-9 Mail. Please excuse my brevity.
Jeff Newmiller
2015-Nov-23 16:23 UTC
[R] Spectral density estimations for irregular time-series
Well, that response was much more clear than your original email was. 1. The automatically-generated plain text component of an email is usually much less intelligible than a directly-generated text. In particular, line breaks and faux highlighting corrupt example code in the plain text version. Since the mailing list usually strips the html we don't even have the option to see it as you saw it in many cases, so don't even start there if you want reliable communication. As the Posting Guide says, this is a plain-text mailing list. 2. Looks like the Task View is out of date. .. perhaps those functions were moved or removed. I Googled and found spec.ls in the cts package, though. 3. I think this is a perfectly reasonable place to ask about how to find appropriate packages, but it is less reasonable to ask for help when Google yields an answer immediately. You must be clear that that is what you are doing, and you should indicate which search strategies failed you, and how they failed, because such efforts are USUALLY successful. Note that I did not know about cts until I used Google to search for "irregular time series fourier transform r package", which doesn't seem so difficult to me, but if you had been more clear about attempts you had made I would have just shared that option. Reporting that none of the mentioned packages even include a mention of spectral analysis also seems appropriate here, but you left that to our imagination. Thank you for your improved efforts to communicate clearly. On November 23, 2015 2:04:28 AM PST, Valery Khamenya <khamenya at gmail.com> wrote:>Jeff, many thanks for your answer. > >On Sun, Nov 22, 2015 at 8:40 PM, Jeff Newmiller ><jdnewmil at dcn.davis.ca.us> wrote: > >> Since you seem to have trouble reading (the Posting Guide warns you >to post here using plain text format emails.. doing so will be to your >benefit when we can see what you posted clearly), > >the body of the email sent by me has had both plain-text and html >representations. I found no clear confrontation with the Posting Guide >for this case. > > >> perhaps it is not clear to you that the Task View is referring to >contributed packages that have their own documentation. > >that's clear. To my understanding primary purpose of a Task View is >giving a (over)view about the R-packages that one could use while >addressing the respective task. The Task View this time was not enough >to locate the needed package, so I had to admit I need a help. If the >r-help mail-list isn't the right place to ask for a help to locate a >relevant R-package then I'm a bit confused, but would kindly ask for >redirecting me to a mail-list that is more relevant for my question. > > >> Also, please be aware that a significant hurdle to applying spectral >analysis in any calculation tool is familiarity with the underlying >theory. Doing so with irregular samples is going to be even more >challenging, and this is not an appropriate forum for learning such >topics. > >I do confirm, that my focus was and is to locate an R-package that >provides at least one function in its API to estimate power spectrum >for the irregular time series. > >kind regards and thanks in advance for any help, >Valery. > >> On November 22, 2015 10:23:34 AM PST, Valery Khamenya ><khamenya at gmail.com> wrote: >>> >>> Hi, >>> >>> I fail to find libraries to estimate the spectral density for >irregular >>> time-series. >>> >>> This entry from "CRAN Task View: Time Series Analysis": >>> >>> [...]Various packages implement irregular time series based on >"POSIXct" >>> time stamps, intended especially for financial applications. These >include >>> "its" from its, "irts" from tseries, and "fts" from fts. [...] >>> >>> is rather not that much helping. >>> >>> best regards >>> -- >>> Valery >>> >>> [[alternative HTML version deleted]] >>> >>> ________________________________ >>> >>> R-help at 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. >> >> >> -- >> Sent from my Android device with K-9 Mail. Please excuse my brevity.-- Sent from my Android device with K-9 Mail. Please excuse my brevity. [[alternative HTML version deleted]]