Professional Documents
Culture Documents
Unit10 Plane of Regression: Structure
Unit10 Plane of Regression: Structure
10.1 INTRODUCTION
where, b12.3 and b13.2 are the partial regression coefficients of X 1 on X 2 and
X1 on X 3 keeping the effect of X3 and X2 fixed respectively.
Taking summation of equation (1) and dividing it by N, we get
X1 a b12 . 3 X 2 b13 . 2 X 3 … (2)
Right hand side of equation (2) is called the estimate of x 1 which is denoted
by x1.23 . Thus,
b12.3 x 2 x 3 b13.2 x 32 x 1 x 3 0
… (14)
As we know that
1
i2 (x i x i ) 2 (for i 1, 2 and 3)
N
1 2
x i2 x i
N
rij
Cov( x i , x j )
x x i j
Cov(x i , x j ) rij i j … (17)
V( x i ) V( x j ) N i j
where, r12 is the total correlation coefficient between x 1 and x 2 , r13 is the
total correlation coefficient between x 1 and x 3 and similarly, r23 is the total
correlation coefficient between x 1 and x 3 . Thus, we have two equations (20)
and (21).
Solving the equations (20) and (21) for b12.3 and b13.2 , we obtained
r12 1 r23 3
r131 3
b12.3
2 r23 3
r23 2 3
r12 r23
r 1 1 r12 r13r23
b12.3 1 13 … (22)
2 1 r23
2 1 r232
r23 1
Similarly,
1 r12
r r13 1 r13 r12r23
b13.2 1 23 … (23)
3 1 r23
3 1 r232
r23 1
If we write
1 r12 r13
t r21 1 r23 … (24)
r31 r32 1
where, tij is the cofactor of the element in the i th row and jth column of t.
Substituting the values of b12.3 and b13.2 in equation (9), we get the equation
of the plane of regression of x 1 on x 2 and x 3 as
27
Regression and Multiple 1 t12 t
Correlation x1 x 2 1 13 x 3 where, a = 0
2 t11 3 t11
x1 x x
t11 2 t12 3 t13 0 … (25)
1 2 3
Similarly, the plane of regression of x 2 on x1 and x 3 is given by
x1 x x
t 21 2 t 22 3 t 23 0 … (26)
1 2 3
and the plane of regression of x 3 on x1 and x 2 is
x1 x x
t 31 2 t 32 3 t 33 0 … (27)
1 2 3
In general the plane of regression of xi on the remaining variable xj
( j i 1, 2, ..., n ) is given by
x x x x
1 t i1 2 t i 2 ... i t ii ... n t in 0; i 1,2,..., n … (28)
σ1 σ2 σi σn
Example 1: From the given data in the following table find out
(i) Least square regression equation of X1 on X 2 and X 3 .
X1 1 2 3 4 5
X2 3 4 5 6 7
X3 4 5 6 7 8
Solution: (i) Here X1, X2 and X3 are three random variables with their
respective means X1 , X 2 and X3 .
Let X1 X1 x1 , X 2 X 2 x 2 and X 3 X 3 x 3
28
Plane of Regression
S. x1= x2= x3= 2 2 2
X1 X2 X3 (x1) (x2) (x3) x1x2 x1x3 x2x3
No. X1−5 X 2−6 X3−7
1 1 3 4 −4 −3 −3 16 9 9 12 12 9
2 3 5 5 −2 −1 −2 4 1 4 2 4 2
3 4 6 6 −1 0 −1 1 0 1 0 1 0
4 7 7 9 2 1 2 4 1 4 2 4 2
5 10 9 11 5 3 4 25 9 16 15 20 12
Total 25 30 35 0 0 0 50 20 34 31 41 25
X1
X 1
25
5
N 5
X2
X 2
30
6
N 5
X3
X 3
35
7
N 5
1
12 x 12 from equation (15)
N
1
50 10
5
1 10
3.162
1
22 x 22
N
1
20 4
5
2 4 2
1
32 x 32
N
1
34 6.8
5
3 6.8
2.608
r12
x x 1 2
from equation (17)
N1 2
29
Regression and Multiple 31
Correlation 0.98
5 3.162 2
r13
x x 1 3
N1 3
41
0.994
5 3.162 2.608
r23
x x 2 3
N 2 3
25
0.959
5 2 2.608
Now, we have
1 r12 r13r23
b12.3
2 1 r232
3.162 0.98 0.994 0.959
0.527
2 1 0.959
2
1 r13 r12 r23
b13.2
3 1 r232
3.162 0.994 0.98 0.959
0.818
2.608 1 0.959
2
Thus, regression equation of x1 on x2 and x3 is
x1 5.276x 2 0.818 x 3
After substituting the value of x1, x2 and x3, we will get the following
regression equation of X1 on X2 and X3 is
X1 5 0.527 X 2 6 0.818 X 3 7
X1 3.891 5.276 X 2 0.818 X 3
E1) For the data given in the following table find out
(i) Regression equation of X1 on X 2 and X 3 .
30
Plane of Regression
X1 2 6 8 10
X2 4 5 9 12
X3 4 6 10 12
x1 b12.3 x 2 b13.2 x 3
Here, x 1 , x 2 and x 3 are measured from their respective means.
Using equation (10) in equations (11) and (13) we have following normal
equations
x e 2 1.23 0 = x 3e1.23
Similarly, normal equation for regression lines of x 2 on x1 and x 3 & x 3
on x 2 and x1 are
x e 1 2.13 0 = x 3e 2.13
x e 2 3.12 0 = x1e3.12
Property 2: The sum of the product of two residuals is zero provided all the
subscripts, primary as well as secondary, are appearing among the secondary
subscripts of second residual i.e. x 3.2 e1.23 0 , since primary as well as
secondary subscripts (3 and 2) of the first residual is appearing among the
secondary subscripts of the second residual.
Proof: We have
x e
3.2 1.23 (x 3 b32 x 2 )e1.23
( x 3e1.23 b 32 x 2e1.23 ) = 0
Similarly,
x e
2.3 1.23 0
Property 3: The sum of the product of any two residuals is unaltered if all
the secondary subscript of the first occur among the secondary subscripts of
the second and we omit any or all of the secondary subscripts of the first. 31
Regression and Multiple Proof: We have
Correlation
x e
1.2 1.23 x e
1 1.23 ,
i.e. Right hand side and left hand side are equal even
x e
1.2 1.23 ( x1 b12 x 2 )e1.23
= x1e1.23
x x x
1 2 3 0 and we get a = 0 and regression equation becomes
x1 b12.3 x 2 b13.2 x 3
and
1
σ12.23 e12.23 ...(29)
N
1
N
(x 1 b12.3 x 2 b13.2 x 3 )(x 1 b12.3 x 2 b13.2 x 3 )
1
N
x 1 (x 1 b12.3 x 2 b13.2 x 3 )
32
Plane of Regression
1
−
N
b12.3 x 2 (x1 b12.3 x 2 b13.2 x 3 )
1
N
b13.2 x 3 ( x1 b12.3 x 2 b13.2 x 3 )
1
12.23 ( x 12 b12.3 x 1 x 2 b13.2 x 1 x 3 )
N
1
−
N
(b12.3 x 2 x1 b122 .3 x 22 b12.3b13.2 x 2 x 3 )
1
N
(b 13.2 x 3 x 1 b13.2 b 12.3 x 3 x 2 b132 .2 x 32 )
We know that
b 12.3 x 22 b13.2 x 2 x 3 x 1 x 2 0
and
b 12.3 x 2 x 3 b13.2 x 32 x 1 x 3 0
12
12.23 2
(1 r232 r122 r132 2 r12 r23r13 )
1 r23 … (30)
10.6 SUMMARY
In this unit, we have discussed:
1. The Yule’s notation for trivariate distribution;
2. The plane of regression for trivariate distribution;
3. How to get normal equations for the regression equation of
x 1 on x 2 and x 3 ;
4. The properties of residuals;
5. The variance of residuals; and
6. How to find the estimates of dependent variable of regression
equations of three variables.
33
Regression and Multiple
Correlation
E1) (i) Here X1, X2 and X3 are three random variables with their
respective means X1 , X 2 and X 3 .
Let X1 X1 x 1 , X 2 X 2 x 2 and X 3 X 3 x 3
x1 b12.3 x 2 b13.2 x 3
From equation (22) and (23), we have
r r r
b12.3 1 12 132 23
2 1 r23
and
r r r
b13.2 1 13 122 23
3 1 r23
σ1, σ2, σ3, r12 r13 and r23 can be obtained through the following table.
Total 26 30 32 0 0 0 35 41 40 35 36 40
X1
X 1
26
6 .5
N 4
X2
X 2
30
7.5
N 4
X3
X 3
32
8
N 4
1
12 x12 from equation (15)
N
1
35 8.75
4
1 35 2.958
34
Plane of Regression
1
22 x 22
N
1
41 10.25
4
2 10.25 3.202
1
32 x 32
N
1
40 10
4
3 10 3.162
r12
x x 1 2
from equation (17)
N1 2
35
0.924
4 2.958 3.202
r13
x x 1 3
N1 3
36
0.962
4 2.958 3.162
r23
x x 2 3
N 2 3
40
0.988
4 3.202 3.162
Now, we have
1 r12 r13r23
b12.3
2 1 r232
2.958 0.924 0.962 0.988
1
3.202 1 0.988
2
1 r13 r12 r23
b13.2
3 1 r232
2.958 0.962 0.924 0.988
1.9
3.162 1 0.988
2
Thus, regression equation of x1 on x2 and x3 is
x 1 x 2 1 .9 x 3
After substituting the value of x1, x2 and x3, we will get the following
regression equation of X1on X2 and X3 is 35
Regression and Multiple X1 6.5 X 2 7.5 1.9X 3 8
Correlation
X1 1.2 X 2 1.9 X3
(ii) Substituting X 2 6 and X 3 8 in regression equation
X1 1.2 X 2 1.9 X 3
we get estimated value of X1 i.e. X1 8
36