g02caf
g02caf
© Numerical Algorithms Group, 2002.
Purpose
G02CAF Simple linear regression with constant term, no missing values
Synopsis
[result,ifail] = g02caf(x,y<,ifail>)
Description
The routine fits a straight line of the form
y=a+bx
to the data points
(x ,y ),(x ,y ),...,(x ,y ),
1 1 2 2 n n
such that
y =a+bx +e , i=1,2,...,n(n>2).
i i i
The routine calculates the regression coefficient, b, the
regression constant, a (and various other statistical quantities)
by minimizing
n
-- 2
> e .
-- i
i=1
The input data consist of the n pairs of observations
(x ,y ),(x ,y ),...,(x ,y )
1 1 2 2 n n
on the independent variable x and the dependent variable y.
The quantities calculated are:
(a) Means:
n n
_ 1 -- _ 1 --
x= - > x ; y= - > y
n -- i n -- i
i=1 i=1
(b) Standard deviations:
_______________ _______________
/ n / n
/ 1 -- _ 2 / 1 -- _ 2
s = / --- > (x -x) ; s = / --- > (y -y)
x / n-1 -- i y / n-1 -- i
\/ i=1 \/ i=1
(c) Pearson product-moment correlation coefficient:
n
-- _ _
> (x -x)(y -y)
-- i i
i=1
r= ----------------------------
______________________
/ n n
/ -- _ 2 -- _ 2
/ > (x -x) > (y -y)
/ -- i -- i
\/ i=1 i=1
(d) The regression coefficient, b, and the regression constant,
a:
n
-- _ _
> (x -x)(y -y)
-- i i
i=1 _ _
b= ----------------; a=y-bx
n
-- _ 2
> (x -x)
-- i
i=1
(e) The sum of squares attributable to the regression, SSR, the
sum of squares of deviations about the regression, SSD, and
the total sum of squares, SST:
n n
-- _ 2 -- 2
SST= > (y -y) ; SSD= > (y -a-bx ) ; SSR=SST-SSD
-- i -- i i
i=1 i=1
(f) The degrees of freedom attributable to the regression, DFR,
the degrees of freedom of deviations about the regession,
DFD, and the total degrees of freedom, DFT:
DFT=n-1; DFD=n-2; DFR=1
(g) The mean square attributable to the regression, MSR, and
the mean square of deviations about the regression, MSD:
MSR=SSR/DFR; MSD=SSD/DFD
(h) The F-value for the analysis of variance:
F=MSR/MSD
(i) The standard error of the regression coefficient, se(b),
and the standard error of the regression constant, se(a):
____________
/ MSD
se(b)= / -----------; se(a)
/ n
/ -- _ 2
/ > (x -x)
/ -- i
\/ i=1
____________________
/ ( _2 )
/ ( 1 x )
= / MSD( -+ -----------)
/ ( n n )
/ ( -- _ 2)
/ ( > (x -x) )
/ ( -- i )
\/ ( i=1 )
(j) The t-value for the regression coefficient, t(b), and the t
-value for the regression constant, t(a):
b a
t(b)= -----; t(a)= -----.
se(b) se(a)
Parameters
g02caf
Required Input Arguments:
x (:) real
y (:) real
Optional Input Arguments: <Default>
ifail integer -1
Output Arguments:
result (20) real
ifail integer