x d1 y  gives the approximations to y using linear
regression on x with a polynomial of degree 1.  e.g.

   d1=: ] (] +/ .* %.) 1: ,. [

   x=: 10 [EMAIL PROTECTED] 100
   y=: (17 + 3 * x) + 10 [EMAIL PROTECTED] 0
   x ,. y ,. x d1 y
90 287.581 287.504
47 158.926 158.515
58 191.155 191.512
29 104.766  104.52
22 83.8745 83.5219
32 113.172 113.519
55 182.511 182.513
 5 32.1901 32.5265
55 182.752 182.513
73 236.224 236.508

If just the coefficients (the alpha and beta) are
required, %. alone does the job:

   y %. 1,.x
17.5278 2.99973

If regression using a higher degree polynomial is
required, do as follows:

   y %. x ^/ i.4
16.9363 3.05929 _0.00138775 8.9248e_6



----- Original Message -----
From: June Kim <[EMAIL PROTECTED]>
Date: Saturday, August 19, 2006 6:51 am
Subject: [Jprogramming] Linear Least Squares

> On 10E. Approximation section of J Dictionary, there is a definition
> for "linear least squares fit of x and y".
> 
> It's given as d1=: ] (] +/ .* %.) 1: ,. [
> 
> What is the expected way of using it, and what does the result 
> mean? I
> first thought it returned the least squares estimators(beta and
> alpha), but it didn't.


----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to