comp.lang.idl-pvwave archive
Messages from Usenet group comp.lang.idl-pvwave, compiled by Paulo Penteado

Home » Public Forums » archive » Re: CHISQR_CVF question.
Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend 
Return to the default flat view Create a new topic Submit Reply
Re: CHISQR_CVF question. [message #67645 is a reply to message #67642] Wed, 19 August 2009 13:42 Go to previous messageGo to previous message
R.G. Stockwell is currently offline  R.G. Stockwell
Messages: 363
Registered: July 1999
Senior Member
"Paolo" <pgrigis@gmail.com> wrote in message
news:5c82e9fd-2bb3-4f1b-9ca6-8e0586a00bc0@g19g2000vbi.google groups.com...
Hi Bob,

I guess I am a bit confused as to what you are doing.

Is that it? (I hope I am not making too much a fool of myself :) )

- start with a uniform distribution x

- fourier transform: y= FFT(x)

- study histogram of real(y), imaginary(y) and abs(y),
compare with known distributions (gaussian, chisquare)?

If that is it, maybe you are having a histogram binsize problem?

That's what happens to me very often - I forget to account for
histogram bin widths.

Ciao,
Paolo
************************************

basically yes, abs(fft(ts))^2, and comparing it to chisquare from the
IDL functions.
I have worked on it, but I think the result is off by a factor of 2.
That is a factor of 2 too stringent.

The binsizes are fine (i think), they are correctly showing the
distribution,
and the cumulative distribution and I normalized wrt to the number of points
so that the histogram is in term of probability.

Perhaps you can check my understanding. If we have a 95% significance
level,
then if we make a spectrum with 1000 points, shouldnt 50 of them be above
that 95% line?

cheers,
bob
[Message index]
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: Re: Loop Multiple Files and Rename
Next Topic: Re: Voxels in IDL

-=] Back to Top [=-
[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Wed Oct 08 19:35:45 PDT 2025

Total time taken to generate the page: 0.00461 seconds