Re: Solve, D, and summations
- To: mathgroup at smc.vnet.net
- Subject: [mg64164] Re: Solve, D, and summations
- From: Paul Abbott <paul at physics.uwa.edu.au>
- Date: Fri, 3 Feb 2006 01:03:51 -0500 (EST)
- Organization: The University of Western Australia
- References: <dri7ji$9u4$1@smc.vnet.net>
- Sender: owner-wri-mathgroup at wolfram.com
In article <dri7ji$9u4$1 at smc.vnet.net>, misha <iamisha1 at comcast.net>
wrote:
> I am (still) a new user of Mathematica and want to solve for the
> (easiest case) least squares estimators.
>
> As usual, I want to choose b_0 and b_1 to minimize S, where S is the sum
> of squared differences. i.e.,
>
> In [1]:= S = sum{1,...,n}[y_i - b_0 - (b_1)*x_i]^2
>
> Out [1]= sum{1,...,n}[y_i - b_0 - (b_1)*x_i]^2
>
> After defining this function as above, which gave me the expression as I
> expected, I then wrote,
>
> In [2]:= Solve[{D[S, b_0]==0, D[S, b_1]==0}, {b_0, b_1}]
>
> But got
>
> Out [2]= {}
>
> I also tried it this way:
>
> In [3]:= S[b_0, b_1] = sum{1,...,n}[y_i - b_0 - (b_1)*x_i]^2
>
> Out [3]= sum{1,...,n}[y_i - b_0 - (b_1)*x_i]^2
>
> In [4]:= Solve[{D[S, b_0]==0, D[S, b_1]==0}, {b_0, b_1}]
>
> But got
>
> Out [4]= {{}}
>
> Is it the 'n' in the summation that is giving me the problem?
Not really. The problem is that Sum does not expand the summand or map
over its arguments, nor do constants get factored out. Clearly,
Mathematica can solve for the least squares estimators for arbitrary n,
given the expanded and simplified equations:
eqns = {
a n + b Sum[Subscript[x, i], {i, 1, n}] -
Sum[Subscript[y, i], {i, 1, n}] == 0,
a Sum[Subscript[x, i], {i, 1, n}] +
b Sum[Subscript[x, i]^2, {i, 1, n}] -
Sum[Subscript[x, i] Subscript[y, i], {i, 1, n}] == 0
}
Solve[eqns, {a, b}]
Note also, that the equations can be put in matrix form using
<<LinearAlgebra`
LinearEquationsToMatrices[eqns, {a,b}]
Cheers,
Paul
_______________________________________________________________________
Paul Abbott Phone: 61 8 6488 2734
School of Physics, M013 Fax: +61 8 6488 1014
The University of Western Australia (CRICOS Provider No 00126G)
AUSTRALIA http://physics.uwa.edu.au/~paul