how to get coefficients by fitting power law for 4 variables ?

Say I have three datasets namely U, X, Y, and Z. As per literature, I have to find the relationship between the U and other three variables as given by the equation: (i.e. i have to find a, b,c, and d because i have large set of values of U, X, Y, Z : say 100 case values).

fo

please guide me how to get coefficeints using matlab code.

Thanks

Answer 1

[Matt J]

A=log([X(:),Y(:),Z(:)]);
A(:,end)=1;

abcd=A\log(U(:));  %the coefficients
abcd(1)=exp(abcd(1));

[naveen kumar s]

thanks. I will try this code.

& in last line

>> abcd(1) = exp(abcd(1)

does this line only give first coefficient right.

for other coefficients do we need to take exp(2:4).

[Matt J]

No, the model is log-linear in b,c, and d.