Re: How to visualize multiple variables correlation

demiourgos_at_gmail.com
Date: 03/27/05 

Date: 27 Mar 2005 13:28:32 -0800

My data is actually a spectra (physical observations), therefore they
are
1. ordered
2. consecutive variables should be highly correlated.

I don't believe that apart from (2) there are groups of items that have
a lot in common.
There are three kinds of "features" in this data - continuum (slope and
average) and
emission/absorbtion lines (without going into too much detail these are
just "features"
of the spectrum that have "width" of 2-3 variables), which is a reason
I believe consecutive
variables should be correlated.

Thanks for all the advices so far. Just to summarize, too approaches
that seem interesting
to me which I'm going to check
1. viewing correlation matrix as an image
2. autocorrelation

Thanks a lot, more comments are welcome.

Relevant Pages

  • Re: Feature Selection
    ... I don't know the features they were analyzing but it might be better ... Now they might be fine with throwing out some measurements because ... excluding features with a correlation higher than 0.4. ... What does it mean by "excluding features with a correlation higher ...
    (sci.image.processing)
  • Re: Feature Selection
    ... Should I exclude both of them? ... "The original data set consists of features that are partly highly ... excluding features with a correlation higher than 0.4. ...
    (sci.image.processing)
  • Re: Feature Selection
    ... On Feb 24, 9:09 am, Martin Leese ... "The original data set consists of features that are partly highly ... excluding features with a correlation higher than 0.4. ...
    (sci.image.processing)
  • Re: Feature Selection
    ... "The original data set consists of features that are partly highly ... What does it mean by "excluding features with a correlation higher ...
    (sci.stat.math)
  • Re: Data correlation and fitting help needed
    ... and correlation with maldi-tof spectra. ... I have analyzed my spectra, done a baseline fitting, and detected signals, ... expected signals, and minimizing the error. ...
    (sci.math)