Re: [R] How Can SVD Reconstruct a Matrix

2014-08-15 Thread Peter Brady
On 15/08/2014 2:40 am, Peter Langfelder wrote: > On Wed, Aug 13, 2014 at 11:57 PM, Peter Brady > wrote: >> > Hi All, >> > >> > I've inherited some R code that I can't work out what they've done. It >> > appears to work and give sort of reasonable answers, I'm just trying to >> > work out why they

Re: [R] How Can SVD Reconstruct a Matrix

2014-08-14 Thread Peter Langfelder
On Wed, Aug 13, 2014 at 11:57 PM, Peter Brady wrote: > Hi All, > > I've inherited some R code that I can't work out what they've done. It > appears to work and give sort of reasonable answers, I'm just trying to > work out why they've done what they have. I suspect that this is a > simple vector

Re: [R] How Can SVD Reconstruct a Matrix

2014-08-14 Thread Martyn Byng
Peter Brady Sent: 14 August 2014 07:58 To: r-help@r-project.org Subject: [R] How Can SVD Reconstruct a Matrix Hi All, I've inherited some R code that I can't work out what they've done. It appears to work and give sort of reasonable answers, I'm just trying to work out why th

Re: [R] How Can SVD Reconstruct a Matrix

2014-08-14 Thread Richard M. Heiberger
This looks like a variant of the Woodbury formula http://en.wikipedia.org/wiki/Woodbury_matrix_identity On Thu, Aug 14, 2014 at 2:57 AM, Peter Brady wrote: > Hi All, > > I've inherited some R code that I can't work out what they've done. It > appears to work and give sort of reasonable answers,

[R] How Can SVD Reconstruct a Matrix

2014-08-14 Thread Peter Brady
Hi All, I've inherited some R code that I can't work out what they've done. It appears to work and give sort of reasonable answers, I'm just trying to work out why they've done what they have. I suspect that this is a simple vector identity that I've just been staring at too long and have forgot