home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #27 / NN_1992_27.iso / spool / bit / listserv / statl / 2023 < prev    next >
Encoding:
Text File  |  1992-11-19  |  1.6 KB  |  39 lines
  1. Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
  2. Path: sparky!uunet!zaphod.mps.ohio-state.edu!darwin.sura.net!paladin.american.edu!auvm!MATH.UNB.CA!ROLF
  3. Message-ID: <9211192026.AA10561@halmos.math.UNB.CA>
  4. Newsgroups: bit.listserv.stat-l
  5. Date:         Thu, 19 Nov 1992 16:26:43 AST
  6. Sender:       STATISTICAL CONSULTING <STAT-L@MCGILL1.BITNET>
  7. From:         Rolf Turner <rolf@MATH.UNB.CA>
  8. Subject:      Anscombe's (?) regression examples.
  9. Lines: 28
  10.  
  11. Some time ago I came across a collection of small artificially
  12. constructed bivariate data sets designed to illustrate various
  13. pitfalls of mindlessly regressing y on x without looking at the
  14. data.  They were, I recall, constructed so that one got the same
  15. results from doing a mindless regression on each data set, although
  16. the true implications were mind-bogglingly different.  I believe
  17. that these examples were due to Anscombe.
  18.  
  19. I thought I had these examples tucked away somewhere; now that I
  20. want to refer to them, I can't find them.  And our library does not
  21. have the sources in which I thought I might look for them.
  22.  
  23. Can anyone help me out, either by providing the actual data, or
  24. by providing a reference where I can definitely find them?
  25.  
  26. Thanks for any and all help.
  27.  
  28.  
  29. Rolf Turner
  30. Dep't. of Maths and Stats
  31. U.N.B., Fredericton, N.B. Canada E3B 5A3
  32. rolf@math.unb.ca
  33.  
  34. ----------------------------------------------------------------------
  35. |                                                                    |
  36. |          Nice day, isn't it?                                       |
  37. |                                                                    |
  38. ----------------------------------------------------------------------
  39.