Mailing-List: contact dev-help@commons.apache.org; run by ezmlm
Precedence: bulk
Reply-To: "Commons Developers List" <dev@commons.apache.org>
Received-SPF: pass (nike.apache.org: domain of phil.steitz@gmail.com
 designates 209.85.210.41 as permitted sender)
Message-ID: <4E27BBD9.9060805@gmail.com>
Date: Wed, 20 Jul 2011 22:40:41 -0700
From: Phil Steitz <phil.steitz@gmail.com>
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6;
 rv:5.0) Gecko/20110624 Thunderbird/5.0
MIME-Version: 1.0
To: Commons Developers List <dev@commons.apache.org>
Subject: Re: [math] Pivoting in QR decomposition
References: 
 <CACMPRi27OvcXC_LPd=n_1D2BGOCgSfTnB2fZF5St5M_DiJx_Xw@mail.gmail.com>
In-Reply-To: 
 <CACMPRi27OvcXC_LPd=n_1D2BGOCgSfTnB2fZF5St5M_DiJx_Xw@mail.gmail.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit

On 7/20/11 9:27 PM, Greg Sterijevski wrote:
> Hello,
>
> In attempting to build constrained ols into the OLSMultipleLinearRegression
> class, I rediscovered the fact that to keep the regression coefficients in
> their canonical order, I need to know how the QR decomposition pivoted. In
> other words, while I get the correct constrained parameters, their order is
> changed. Is there any way to get this info out (pivot order)?

Can you explain a little more exactly what you are trying to do?  
How exactly is the parameter vector getting permuted?  The QRDecomp
solver certainly should not do that.  See the QRDecomp sources for
what is exposed in the public API.  We can talk about adding more,
but we should be careful about exposing more implementation details.
You can now get the Householder reflection vectors and obviously the
decomp itself.  As you can see from the sources, the current OLS
impl just uses the solver.

Phil
>
> Thanks,
>
> -Greg
>


---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@commons.apache.org
For additional commands, e-mail: dev-help@commons.apache.org