From mboxrd@z Thu Jan 1 00:00:00 1970 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on polar.synack.me X-Spam-Level: X-Spam-Status: No, score=0.1 required=5.0 tests=BAYES_05,INVALID_MSGID autolearn=no autolearn_force=no version=3.4.4 X-Google-Language: ENGLISH,ASCII-7-bit X-Google-Thread: 103376,b2f46302cf6a9a2f X-Google-Attributes: gid103376,public From: tmoran@bix.com (Tom Moran) Subject: Re: Using ARRAYS for grade reporting? Date: 1998/04/21 Message-ID: <353d2d0a.9823778@SantaClara01.news.InterNex.Net>#1/1 X-Deja-AN: 346467913 References: <6hdfoc$h6i@lotho.delphi.com> Organization: InterNex Information Services 1-800-595-3333 Newsgroups: comp.lang.ada Date: 1998-04-21T00:00:00+00:00 List-Id: >it is not clear that the rather >soft statistics that come from such studies can conculsively demonstrate >anything I'd hate to think we were telling people "X is better than Y. I have no evidence, and the difference between X and Y is so small as to not be measurable, but, hey, I just happen to believe X is better than Y". What is it that makes the "soft statistics that come from such studies" so useless? What needs to be changed to get conclusive demonstrations of propositions? And I wouldn't demand "conclusive" in the sense of "less than 1% chance of the null hypothesis", but would be quite happy with a "75% chance you'll save money, and 25% chance you'll save a bundle of money" type of statement..