home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!gatech!udel!darwin.sura.net!paladin.american.edu!auvm!PO.CWRU.EDU!PAT
- Return-Path: <pat@slc4.INS.CWRU.Edu>
- Message-ID: <9301251436.AA19100@slc4.INS.CWRU.Edu>
- Newsgroups: bit.listserv.stat-l
- Date: Mon, 25 Jan 1993 09:36:07 -0500
- Reply-To: "Paul A. Thompson" <pat@po.CWRU.Edu>
- Sender: STATISTICAL CONSULTING <STAT-L@MCGILL1.BITNET>
- From: "Paul A. Thompson" <pat@PO.CWRU.EDU>
- Subject: Re: correct chi-square character
- Lines: 21
-
- >
- >
- There is another issue here as well. The chi-2 computation
-
- X2 = sum ((obs - exp)**2/exp)
-
- can be computed with any data. On the other hand, certain conditions must
- be fulfilled before this is a chi-2 r.v. These include independence, obs
- is (0, 1) normal r.v., etc. This careful distinction is clearly exhibited
- on BFH pg. 124, in which the computed value is shown as X2, and the value
- is stated to be "asymptotically distributed as chi-2 (greek letter)"
- Thus, the Roman X indicates computation result, while the Greek chi
- indicates theoretical result. We can compute X2 with any data, but
- must show conditions for chi to apply. In a recent article in Multivariate
- Behavioral Research where I used bootstrap with X2 values, I used X2 because
- chi did not hold.
-
- --
- Paul Thompson, Ph.D. | Department of Psychiatry | (216) 844-7463
- Case Western Reserve University | Cleveland, OH 44106
- -----------------------------------------------------------------
-