home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #27 / NN_1992_27.iso / spool / bit / listserv / statl / 2001 < prev    next >
Encoding:
Text File  |  1992-11-17  |  1.4 KB  |  37 lines
  1. Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
  2. Path: sparky!uunet!stanford.edu!bcm!convex!darwin.sura.net!spool.mu.edu!yale.edu!news.yale.edu!mars.caps.maine.edu!maine.maine.edu!cunyvm!psuvm!auvm!NEPTUNE.KINGSTON.AC.UK!BS_S467
  3. Via:           UK.AC.KING; 17 NOV 92 15:56:23 GMT
  4. X-Envelope-to: stat-l@mcgill1.bitnet
  5. X-VMS-To:      IN%"stat-l@mcgill1.bitnet"
  6. X-VMS-Cc:      BS_S467
  7. MIME-version:  1.0
  8. Content-transfer-encoding: 7BIT
  9. Message-ID: <01GR9I3ZC5SY000JOJ@neptune.kingston.ac.uk>
  10. Newsgroups: bit.listserv.stat-l
  11. Date:         Tue, 17 Nov 1992 15:55:45 +0000
  12. Sender:       "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
  13. From:         Stephen Gourlay <BS_S467@NEPTUNE.KINGSTON.AC.UK>
  14. Subject:      the meaning of transformations
  15. Lines: 20
  16.  
  17. In the discussion of testing assumptions, someone mentioned transformations.
  18.  
  19. I have always had a problem with these, namely, that whilst I know that my
  20. data represented e.g. counts of something, I cannot figure out a
  21. non-mathematical understanding of what transformed counts mean.  As a result
  22. I am very reluctant to transform data just to 'make it fit'.
  23.  
  24. Has anyone any references, discussion of this problem, explanation of what
  25. particular common transformations mean in 'ordinary' language?
  26.  
  27. I will compile any suggestions, comments mailed to me and send the result to
  28. the list.
  29.  
  30. Stephen Gourlay
  31. Senior Lecturer
  32. Kingston University
  33. Kingston on Thames
  34. UK
  35.  
  36. bs_s467@neptune.kingston.ac.uk
  37.