home *** CD-ROM | disk | FTP | other *** search
/ NetNews Usenet Archive 1992 #26 / NN_1992_26.iso / spool / bit / listserv / statl / 1911 < prev    next >
Encoding:
Text File  |  1992-11-08  |  1.6 KB  |  36 lines
  1. Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
  2. Path: sparky!uunet!stanford.edu!bcm!rice!newsfeed.rice.edu!wupost!zaphod.mps.ohio-state.edu!darwin.sura.net!paladin.american.edu!auvm!CCMAIL.ORST.EDU!SABINT
  3. Message-ID: <9211061028.A16042@ccmail.orst.edu>
  4. Newsgroups: bit.listserv.stat-l
  5. Date:         Fri, 6 Nov 1992 10:28:15 PST
  6. Sender:       "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
  7. From:         "Thomas E. Sabin" <sabint@CCMAIL.ORST.EDU>
  8. Subject:      Re: Precision Probability for Chi Square statistics
  9. Lines: 25
  10.  
  11. >  I have a set of chi square statistics (goodness of fit measures)
  12. >that I wish to compare.  I have used the PROBCHI function in SAS
  13. >(probability = PROBCHI (value, df)) to estimate the probability
  14. >of each chi square value.  I've run into the problem that the
  15. >function cannot produce a probability value precise enough to
  16. >distinguish between the significance of chi square values.
  17.  
  18.     Try using the PUT command instead of PROC PRINT.  For example,
  19.  
  20.     DATA _NULL_;
  21.        P = 1 - PROBCHI(25.62,1);
  22.        PUT P;
  23.     RUN;
  24.  
  25.     gives:
  26.  
  27.     4.1570832E-7
  28.  
  29.   **************************************************************************
  30.   * Tom Sabin                     |          sabin@fsl.orst.edu            *
  31.   * Statistical Consultant       \|/         (503) 737-6577                *
  32.   * Dept. Forest Science        \\|//                                      *
  33.   * Oregon State University    \\\|///                                     *
  34.   * Corvallis, Oregon 97331       |                                        *
  35.   **************************************************************************
  36.