| To: | s-news@lists.biostat.wustl.edu |
|---|---|
| Subject: | minimisation function question |
| From: | Eric yang <yang_eric9@yahoo.com> |
| Date: | Tue, 27 Feb 2007 08:14:51 -0800 (PST) |
| Domainkey-signature: | a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:Date:From:Subject:To:MIME-Version:Content-Type:Content-Transfer-Encoding:Message-ID; b=T07+R4V+ySV4koBnLkdEuxkFE2mjPOZL86C+ZATPmeDAGM1uCJqSr0SrLpLBufcobuB5toefPB+wdh7gHBBr6CpkDk8Jb6V/5KL7PNQt76rN5lgymMoK3ZNCO7rJj+Cu7V+rImp0fXtsqRwtNrUqjTQ7ZPdHo8mbFL28mBm+cmk=; |
|
Dear S+ users, I would like to know if there is a function in S+ that can be to minimise the distance between annual transition matrices? Essentially, I have 10 annual transition (square) matrices: 1 year, 2 year,..., 10 year. I want to almalgamate the 10 matrices into 1 matrix that is a generalization of the 10. The 10 transition matrices do not follow a linear path in time, i.e. the two year transation matrix is not crossproduct of the 1 year. The generalized matrix would be used in such a way that the 1 year = generalized matrix 2 year=[generalized matrix] to the power of 2 ... 10 year=[generalized matrix] to the power of 10. Is there a minimisation function in S+ that would enable me to achieve this? I want to minimise the distances between the consecutive matrices.
Many thanks for any help. Regards, Eric
Everyone is raving about the all-new Yahoo! Mail beta. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Trellis plots, Rich |
|---|---|
| Next by Date: | bootstrap tutorial, Patrick Burns |
| Previous by Thread: | Trellis plots, Dave Evens |
| Next by Thread: | bootstrap tutorial, Patrick Burns |
| Indexes: | [Date] [Thread] [Top] [All Lists] |