Method of Least Square

advertisement
Method of Least Square
Consider the points (x1, y1), (x2, y2), (x3, y3), ………., (xn, yn) shown on the
graph.
x1
x2
x3
The blue line has the equation
y=mx+b
We will find m and b so that the error is least.
E = ( m * x1 + b - y1 ) 2 + ( m * x2 + b - y2 ) 2 + ( m * x3 + b - y3 ) 2 + …….
We must have:
dE
 0
dm at cons tan t b
dE
 0
db at cons tan t m
2(m*x1 + b -y1)*x1 + 2(m*x2 + b -y2)*x2 + 2(m*x3 + b -y3)*x3 + ….. = 0
and
2(m*x1 + b -y1) + 2(m*x2 + b -y2) + 2(m*x3 + b -y3) + ….. = 0
where we used the chain rule. The equations can be written as:
m ( x1*x1 + x2*x2 + x3*x3 + ……) + b ( x1 + x2 + x3 + ….) =
x1*y1 + x2*y2 + x3*y3 + …..
m ( x1 + x2 + x3 + …)
+ b ( 1 + 1 + 1 + …) = y1 + y2 + y3 +…..
Using the summation notation we can write:
m
  nk 1
m
x
xk2
 b
 b 
(n
x )    nk 1 xk yk
y
Solving for m we get:
1 n
 k 1 xk yk )  x y
m  n
1
(  nk 1 xk 2 )  x 2
n
(

If you can show that this is the same equation as the one in the
book you will get 10 points added to your score of 1000.
Download