home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: sci.math.research
- Path: sparky!uunet!usc!sdd.hp.com!ux1.cso.uiuc.edu!news.cso.uiuc.edu!usenet
- From: rossini@biosun4.harvard.edu (Anthony Rossini)
- Subject: Cramer'-Wold device
- Message-ID: <ROSSINI.92Jul24122513@biosun4.harvard.edu>
- Sender: Daniel Grayson <dan@math.uiuc.edu>
- Followup-To: sci.math.stat
- X-Submissions-To: sci-math-research@uiuc.edu
- Organization: Biostat Dept, HSPH, Boston MA, USA.
- X-Administrivia-To: sci-math-research-request@uiuc.edu
- Approved: Daniel Grayson <dan@math.uiuc.edu>
- Date: Fri, 24 Jul 1992 16:25:13 GMT
- Lines: 20
-
-
-
- The Cramer'-Wold device is useful for showing the asymptotic normality of
- estimators, for a fixed dimension K, by saying that if all linear
- combinations of components of a vector are asymptotically normal, then the
- vector is asymptotically normal as well. I've been trying to prove (no luck
- yet, either way) that it holds for K -> \infty (i.e. the number of
- parameters estimated goes to infinity). Does anyone have a reference,
- ideas, or a counter-example for this?
-
- (I'm not sure where this problem really belongs, but it seems more like
- probability than statistics at this point!)
-
- thanks,
- -tony
- --
- Anthony Rossini - rossini@biostat.harvard.edu
- Department of Biostatistics, Harvard School of Public Health
- 677 Huntington Ave, Boston MA 02115 617-432-1056
-
-