Re: [math] Least Squares Outlier Rejection

2014-09-17 Thread Gilles
Hello. On Tue, 16 Sep 2014 18:34:52 -0400, Evan and Maureen Ward wrote: Hi Gilles, Luc, Thanks for all the comments. I'll try to respond to the more fundamental concerns in this email, and the more practical ones in another email, if we decide that we want to include data editing in [math].

Re: [math] Least Squares Outlier Rejection

2014-09-16 Thread Evan and Maureen Ward
Hi Gilles, Luc, Thanks for all the comments. I'll try to respond to the more fundamental concerns in this email, and the more practical ones in another email, if we decide that we want to include data editing in [math]. On Fri, Sep 12, 2014 at 8:55 AM, Gilles wrote: > Hi. > > > On Fri, 12 Sep 2

Re: [math] Least Squares Outlier Rejection

2014-09-12 Thread Gilles
Hi. On Fri, 12 Sep 2014 09:16:07 +0200, Luc Maisonobe wrote: Le 12/09/2014 01:35, Gilles a écrit : Hello. On Thu, 11 Sep 2014 14:29:49 -0400, Evan Ward wrote: Hi, A while ago I had bought up the idea of adding residual editing (aka data editing, outlier rejection, robust regression) to our

Re: [math] Least Squares Outlier Rejection

2014-09-12 Thread Luc Maisonobe
Le 12/09/2014 01:35, Gilles a écrit : > Hello. > > On Thu, 11 Sep 2014 14:29:49 -0400, Evan Ward wrote: >> Hi, >> >> A while ago I had bought up the idea of adding residual editing (aka data >> editing, outlier rejection, robust regression) to our non-linear least >> squares implementations.[1] As

Re: [math] Least Squares Outlier Rejection

2014-09-11 Thread Gilles
Hello. On Thu, 11 Sep 2014 14:29:49 -0400, Evan Ward wrote: Hi, A while ago I had bought up the idea of adding residual editing (aka data editing, outlier rejection, robust regression) to our non-linear least squares implementations.[1] As the name suggests, the idea is to de-weight observat

[math] Least Squares Outlier Rejection

2014-09-11 Thread Evan Ward
Hi, A while ago I had bought up the idea of adding residual editing (aka data editing, outlier rejection, robust regression) to our non-linear least squares implementations.[1] As the name suggests, the idea is to de-weight observations that don't match the user's model. There are several ways to