comp.lang.idl-pvwave archive: archive » Doing chi square and/or lognormal fits to 1D data?

Home » Public Forums » archive » Doing chi square and/or lognormal fits to 1D data?

Show: Today's Messages :: Show Polls :: Message Navigator
E-mail to friend

Re: Doing chi square and/or lognormal fits to 1D data? [message #49522 is a reply to message #49410]

Sat, 29 July 2006 22:05

swingnut
Messages: 30
Registered: September 2005

Member

So, after enough reading, I've determined that my predecessor was less
than accurate in describing his work. First, I misinterpreted what he
meant in describing his chi square fits -- he calls it a "2 parameter"
chi square distribution. After realizing this, I set off searching for
this mystical beast I had never heard of, given that your standard chi
square distribution has only one parameter, the degrees of freedom.
There is indeed a two paramter chi square distribution, the noncentral
chi square. This is generated by adding up squares of normal random
variables that are not standard, i.e., the variances of each RV is 1,
but the means are not required to be zero. (Info at
http://en.wikipedia.org/wiki/Noncentral_chi-square_distribut ion.)

At this point, I stopped to review my predecessor's thesis again. The
equation he provided is not the pdf or the probability function for the
noncentral -- it has a scale parameter, not an offset -- so I went
searching for generalizations and related distributions. Turns out the
mystery distribution is the gamma distribution
(http://en.wikipedia.org/wiki/Gamma_distribution), so I'll probably
just use Matlab's library fuction to fit that chunk of data.

[Ed. note: Written for the sake of helping future google searchers.]

Report message to a moderator

[Message index]

		Doing chi square and/or lognormal fits to 1D data? By: swingnut on Sun, 23 July 2006 14:55
		Re: Doing chi square and/or lognormal fits to 1D data? By: swingnut on Wed, 26 July 2006 03:38
		Re: Doing chi square and/or lognormal fits to 1D data? By: Paolo Grigis on Wed, 26 July 2006 00:39
		Re: Doing chi square and/or lognormal fits to 1D data? By: swingnut on Sat, 29 July 2006 22:05

Previous Topic:	STOP what you�re doing - It doesn�t work! BP02
Next Topic:	update on the promised new development environment?

-=] Back to Top [=-

[ Syndicate this forum (XML) ] [

] [

]

Current Time: Fri Oct 10 06:34:54 PDT 2025

Total time taken to generate the page: 1.35720 seconds