Sorry, did not mean to touch off a debate. There are two ways (that I know of) to project linear restrictions through the data when running a regression using the QR decomposition. I need to review my notes, but I distinctly remember needing to get the pivots so that I know which columns are 'contaminated' by the restriction... Also, in dealing with restrictions, I will need the pivots to clean up redundant restrictions. Doing a QR reduction on an arbitrary coefficient matrix will give me a reduced set of restrictions and the restrictions which are mapped to the nullity (the redundancies).
In any event, let me finish my experimentation and then I can more cleanly enunciate my needs. On Thu, Jul 21, 2011 at 10:33 AM, Phil Steitz <[email protected]> wrote: > On 7/21/11 8:07 AM, Ted Dunning wrote: > > This is upside down. > > > > Opening the JIRA and putting the patch up is the best way to determine if > > this is useful. > > > > On Thu, Jul 21, 2011 at 3:17 AM, Chris Nix <[email protected]> wrote: > > > >> I have just written a small patch that does QR Decomposition with column > >> pivoting and has a getP() method to get the resulting permutation > matrix. > >> If this is useful, I can open a JIRA issue for discussion. > >> > I think its best to understand more clearly what Greg's problem is > before taking time to prepare a patch. We have a working QR decomp > using Householder reflection. If it is useful to add another one, > we can talk about that; but I would like to understand more clearly > what, if any, problems the current implementation (and interface) has. > > Phil > > --------------------------------------------------------------------- > To unsubscribe, e-mail: [email protected] > For additional commands, e-mail: [email protected] > >
