# Thread: Regression Analysis Non linear estimation using squares

1. ## Regression Analysis Non linear estimation using squares

Hi,
I have used Gompertz model to estimate an equation.
I have followed these two sites they explain it all.

http://www.weibull.com/RelGrowthWeb/...st_squares.htm
http://www.fao.org/DOCREP/006/X8498E/x8498e0e.htm

This method uses squares to approximate the equation.

Following from first site because the variables are different names.

I have calculated Y=((A*B)**C)**X

** means to the power of
anyways further down I have calculated G(0), Y(0), and D(0)

Problem:

I am currently calculating ^V(0) = (D(0)T * D(0))**-1) * D(0)T * Y(0)
T means Transpose D(0)
**-1 means inverse

Now this equation uses matricies to solve for ^V(0)
I have multiplied this sucessfully (D(0)T * D(0))**-1) * D(0)T
but this gives a 3 x 3 matrix in my result
and Y(0) is 1x6 matrix.
Obviously cannot multiply these 2 matricies.
In the example they dont elaborate on the example for this equation.
Can someone please tell me what am I doing wrong?

2. Dont worry I have solved the problem.

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts