home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1993 #3 / NN_1993_3.iso / spool / bit / listserv / statl / 2443 < prev    next >
Encoding:
Text File  |  1993-01-25  |  645 b   |  15 lines
  1. Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
  2. Path: sparky!uunet!paladin.american.edu!auvm!UCS.INDIANA.EDU!DWINSLOW
  3. Message-ID: <STAT-L%93012521345352@VM1.MCGILL.CA>
  4. Newsgroups: bit.listserv.stat-l
  5. Date:         Mon, 25 Jan 1993 21:34:55 EST
  6. Sender:       STATISTICAL CONSULTING <STAT-L@MCGILL1.BITNET>
  7. From:         DWINSLOW@UCS.INDIANA.EDU
  8. Subject:      X2
  9. Lines: 4
  10.  
  11. Wasn't it Sokal & Rohlf who suggested using an "ex" instead of a "chi",
  12. under the reasoning that there are other statistics (besides sum((o-e)2/e))
  13. which under some conditions approximate the chi-square(d) distribution
  14. more closely?   Donald Winslow (DWINSLOW@UCS.INDIANA.EDU)
  15.