home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #16 / NN_1992_16.iso / spool / comp / ai / neuraln / 2885 < prev    next >
Encoding:
Internet Message Format  |  1992-07-23  |  2.3 KB
  1. Path: sparky!uunet!mcsun!uknet!harrier.ukc.ac.uk!eagle.ukc.ac.uk!aw3
  2. From: aw3@ukc.ac.uk (Alan Wilson)
  3. Newsgroups: comp.ai.neural-nets
  4. Subject: SImple pattern recognition problem - any answers?
  5. Message-ID: <1360@eagle.ukc.ac.uk>
  6. Date: 23 Jul 92 10:09:18 GMT
  7. Sender: aw3@ukc.ac.uk
  8. Organization: Chemical Laboratory, University of Kent at Canterbury, CT2 7NH, UK
  9. Lines: 51
  10.  
  11. Hello everyone in net-land. I hope some bright sparks can help me with
  12. a simple interpretation problem (I have been asked to process this data
  13. on behalf of a friend).
  14.  
  15. The Background: 45 questions were asked of two groups of people (5 each
  16. of A and B) Each question had six possible responses of which one was 
  17. recorded and given a score (1-6). A small data set, but I thought PR
  18. may be able to do something with it.....
  19.  
  20. The Data: A data matrix was set-up and the principal components 
  21. extracted. A plot of PC1 (x-axis) vs PC2 (y-axis) is given below
  22.  
  23.  
  24.                                      |
  25.                                      | A
  26.                                      |
  27.                                      |
  28.                                      |
  29.                                      |
  30.                                      |       A
  31.                                      |
  32.                                      |
  33.                                      |           A
  34.                                      |
  35.           --------------------------------B------------------------
  36.                                   B  |
  37.                          B           |
  38.            B      B                  |
  39.                                      |             A
  40.                                      |
  41.                                      |
  42.                                      |
  43.                                      |
  44.                                      |
  45.                                      |                   A
  46.                                      |
  47.  
  48. The QUESTION: What does this say about the data? In particular, can one
  49. infer any correlation between the responses of the two groups of people?
  50.  
  51. Any suggestions, etc... please post or e-mail.
  52.  
  53. Thanks in advance
  54.  
  55. ps I have numbers for eigenvalues, eigenvectors etc.
  56.  
  57. --
  58. Alan Wilson        (insert YOUR favourite witty remark..........)
  59.  
  60. "You would NOT believe what has been going on behind there" 
  61. ================================================================= 
  62.