home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!paladin.american.edu!auvm!IRLEARN.UCD.IE!RCONROY
- Message-ID: <STAT-L%93010605170684@VM1.MCGILL.CA>
- Newsgroups: bit.listserv.stat-l
- Date: Wed, 6 Jan 1993 10:08:06 GMT
- Sender: STATISTICAL CONSULTING <STAT-L@MCGILL1.BITNET>
- From: Ronan M Conroy <RCONROY@IRLEARN.UCD.IE>
- Subject: calculators and computers: precision
- Lines: 14
-
- Dave Arday is interested in comparing the precision of his
- calculator and computer. Phil Miller mentioned 69! as the
- biggest factorial that the PC will handle. This, by less than
- a coincidence, is the limit of what my Sharp EL-506H and my Tandy
- (submerged on the desk, no doubt, at the moment) will handle.
- 69!/68! is correctly evaluated by them both as being 69. 70!
- simply produces an error. But Fisher's exact test is a good case
- in point: even with frequencies less than 69, the calculation
- will overflow if you multiply out the top of the line and then
- the bottom, before dividing. Anyone who has done this test by hand
- will know that a little factor finding often reduces the calculation
- to the very manageable.
-
- ronan
-