Re: Multiple Regression
- To: mathgroup at smc.vnet.net
- Subject: [mg50308] Re: Multiple Regression
- From: koopman at sfu.ca (Ray Koopman)
- Date: Thu, 26 Aug 2004 06:50:58 -0400 (EDT)
- References: <cghg7o$jgh$1@smc.vnet.net>
- Sender: owner-wri-mathgroup at wolfram.com
"Doug" <umdougmm at hotmail.com> wrote in message
news:<cghg7o$jgh$1 at smc.vnet.net>...
> [...]
> I'm trying to come up with a model of the following sort: y =
> (B0) + (B1)*(o01) + (B2)*(o02) + (B3)*(o03) + (B4)*(o04) + (B5)*(u)
> + (B6)*(v) + (B7)*(w) + (B8)*(z) + (B9)*(y) + (B10)*(x) + epsilon
> and I'm of course trying to minimize epsilon. Also, the other
> important point is that o01 to o04 are binary and can be 1 only
> exclusively (ie, if a data row has o01=1 then o02=..=o04=0, and the
> same thing goes for the other o02 to o04)
>
> The variables which are causing me much headache are the o01..o04,
> because if I include all the ~50 000 rows of data and run the Fit[]
> function as follows:
> Fit[Data,{1,o01,o02,o03,o04,u,v,w,z,y,x},{o01,o02,o03,o04,u,v,w,z,y,x}]
>
> the approximated B1=..=B4 are all equal and VERY large. [...]
Your model is singular: o01 + o02 + o03 + o04 = 1.
Drop the additive constant (1) or one of the o0i variables.