home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #20 / NN_1992_20.iso / spool / bit / listserv / statl / 1552 < prev    next >
Encoding:
Text File  |  1992-09-15  |  1.8 KB  |  32 lines
  1. Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
  2. Path: sparky!uunet!gatech!paladin.american.edu!auvm!NIKE.HEIDELBERG.EDU!DIXON
  3. Message-ID: <9209151317.AA20258@nike.heidelberg.edu>
  4. Newsgroups: bit.listserv.stat-l
  5. Date:         Tue, 15 Sep 1992 09:17:24 EDT
  6. Sender:       "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
  7. From:         Wally Dixon <dixon@NIKE.HEIDELBERG.EDU>
  8. Subject:      Heywood cases
  9. Lines: 21
  10.  
  11. I frequently run into Heywood cases and since the topic came up I wish to
  12. answer a question that's been nagging at me.  What is the current thinking in
  13. the statistical field about them?  If one gets Heywood cases, does that mean
  14. that one has "bad" data and should discontinue further analyses?  Does it mean
  15. that one should use a noniterative procedure and to just "ignore" them? Are
  16. they statistical artifacts sometimes, that should just be constrained at 1?
  17. Is it OK to proceed anyway, and just inform readers that a Heywood case was
  18. obtained?  Are there any papers written for nonstatisticians that address the
  19. issue from a theoretical/practical standpoint?  Any help would be greatly
  20. appreciated.
  21.  
  22. _____________________________________________________________________________
  23.                                    |
  24. Wallace E. Dixon, Jr.              | "Humanity has been held to a limited and
  25. Department of Psychology           |  distorted view of itself--from its
  26. Heidelberg College                 |  interpretation of the most intimate of
  27. Tiffin, OH  44883                  |  personal emotions to its grandest vision
  28. dixon@nike.heidelberg.edu          |  of human possibilities--precisely by
  29.                                    |  virtue of its subordination of women."
  30.                                    |         -Jean Baker Miller
  31. ___________________________________|_________________________________________
  32.