I answer to myself: I have to generate my signal up to f1 = Fs/2 in
order to have a flat response over the entire frequency range.
Le 09/04/2024 à 19:48, laurentRhelp a écrit :
Dear RHelp-list,
I generate a swept sine signal using the signal library. I can see
using the spec.pgram command that the spectrum of this signal is
white. But when I am calculating the cumulative periodogram using the
command cpgram the process doesn't stay inside the confidence band
(cf. code below). I missed something.
May you please explain to me why the process don not stay inside the
confidence band ?
Thank you
Laurent
library(signal)
t1 <- 2
f0 <- 0
f1 <- 15000
Fs <- 44100
Ts <- 1/Fs
t <- seq(0,t1-Ts,by=Ts)
y <- signal::chirp(t=t,f0=f0,t1=t1,f1=f1
,form="linear")
y.ts <- ts(y,frequency=Fs,start=0)
par( mfrow=c(1,2))
spec.pgram(y.ts)
cpgram(y.ts)
______________________________________________
R-help@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.
--
Cet e-mail a été vérifié par le logiciel antivirus d'Avast.
www.avast.com
______________________________________________
R-help@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.