In Excel have a column for Y as the dependant variable and 12 columns
for A..A^4, B..B^4, C..C^4 as the independent variables. Run the
regression tool and it will give you the result you want.
However, when I tried it on the data below the process did not work as
the matrix was singular. In any case 13 parameters is a lot to obtain
from only 18 points and is nearly deterministic rather than least
squares, so I tried just A, B & C as independent variables. This showed
that Y did not depend on B but mainly on A with a small effect from C.
The correlation was 90%.
A second run with A, A^2, B, B^2 , C and C^2 showed Y a function of A
and A^2 only, with a correlation of 95%.
In article <91715h$sbv$[EMAIL PROTECTED]>, junk <[EMAIL PROTECTED]>
writes
>Can anyone direct me to an Excel wizard or, if none is available, a formula
>to do the following. Note I do not have access to Maple, Matlab,
>Mathematica or any other statical or engineering software.
>
>Why I am trying to do is come up with a simple method of doing a
>multivariable (multidimensional ?) least squares approximation.
>
>How could I easily create:
>Y = (a1*A^4 + b1*A^3 . e1*A + f1) + (a2*B^4 .. + f2) + (a3*C^4 +.+f3)
>
>
>****Note that basic regression will not work in the real problem. Need
>multiple exponents*****
>
>
>from the data below:
>
>
>A B C Y
>paint engine amenities price
>0.1 1 6 $1000
>0.11 2 5 1200
>0.14 1 3 1150
>0.16 2 5 1200
>0.2 1 4 3000
>0.201 4 5 2700
>0.3 2 3 4000
>0.33 4 7 3500
>0.35 1 4 6000
>0.4 2 6 4650
>0.41 3 4 4400
>0.42 4 3 4750
>0.44 1 5 5360
>0.45 1 3 7500
>0.6 3 3 7400
>0.8 2 5 7700
>0.87 2 6 8500
>0.88 3 5 9000
>
>
>
>Basically, I would like to create a formula for a price estimator based on
>three input variables and one output (price). I am hoping to do something
>quick and simple in Excel.
>
>Any help would be appreciated.
>
>thanks,
>
>Nathan
>
>
>
>
--
David Wilkinson
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================