home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #16 / NN_1992_16.iso / spool / bit / listserv / statl / 1231 < prev    next >
Encoding:
Text File  |  1992-07-31  |  1.1 KB  |  30 lines

  1. Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
  2. Path: sparky!uunet!paladin.american.edu!auvm!POLISCI.WISC.EDU!FRANKLIN
  3. X-VMS-To: IN%"stat-l@mcgill1.bitnet",FRANKLIN
  4. Message-ID: <22073108564214@ps.polisci.wisc.edu>
  5. Newsgroups: bit.listserv.stat-l
  6. Date:         Fri, 31 Jul 1992 08:56:00 CDT
  7. Sender:       "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
  8. From:         "Charles H. Franklin" <FRANKLIN@POLISCI.WISC.EDU>
  9. Subject:      Re: tetrachoric correlation
  10. Lines: 18
  11.  
  12. brobinso@LEVEN.APPCOMP.UTAS.EDU.AU writes:
  13. >
  14. >Can anyone please supply a good reference to tetrachoric and/or polychoric
  15. >correlation coefficients? I have a colleague who has consulted 20
  16. >statistics texts without success.
  17. >
  18. An old, but classic, reference is Kendall and Stuart, _The Advanced
  19. Theory of Statistics_, Vol II, pp. 304-307 (tetrachoric) and
  20. p. 561 (polychoric). The original polychoric reference appears to be
  21. Lancaster and Hamdan (1964) "Estimation of the correlation coefficient
  22. in contingency tables with possibly nonmetrical characters",
  23. _Psychometrika_ 29:383ff.
  24.  
  25. \chf
  26.  
  27.  
  28. Charles H. Franklin......University of Wisconsin--Madison
  29. Internet: FRANKLIN@POLISCI.WISC.EDU   Voice: 608.263.2022
  30.