[Date Index] [Thread Index] [Author Index]

Re: simultaneous nonlinear regression of a lot of data

• To: mathgroup at smc.vnet.net
• Subject: [mg65491] Re: simultaneous nonlinear regression of a lot of data
• From: "dantimatter" <dantimatter at gmail.com>
• Date: Wed, 5 Apr 2006 06:55:32 -0400 (EDT)
• References: <200603311109.GAA15091@smc.vnet.net><e0o5g8$21f$1@smc.vnet.net>
• Sender: owner-wri-mathgroup at wolfram.com

Thanks all!  this is what i ended up doing:

estvar[t_?NumericQ] :=
Total[EstimatedVariance /.
Table[NonlinearRegress[croppedcorrelation[[i]],
1/nn(y / (1 + t/m1) + (1 - y) / (1 + t/m2) ), t, {nn, y},
RegressionReport -> EstimatedVariance], {i, Length[gooddata]}];

then i found the minimum of estvar with respect to t.  it worked pretty
well.  thanks!