Вы находитесь на странице: 1из 18

Louise Laine P.

Dayao
Joanne Mae J. de Lota
III-Palladium
Correlation is a statistical measure for finding
out degree(or strength)of association
between two(or more) variables. If the
change in one variable affects a change in
other variable then these variables are said
to be correlated.
Correlation analysis attempts to
measure the strength of such
relationships between two
variables by means of a single
number called a correlation
coefficient .
LINEAR CORRELATION
A measure of the linear relationship between the two random variables X and Y,
and denote it by r. That is, r measures the extent to which the points cluster
about a straight line. Therefore, by constructing a scatter diagram for the n
pairs of measurements {( x
i
, y
i
); i= 1, 2, , n} in our random sample
(see figure1), we are able to draw certain conclusions concerning r.
Should the points follow closely a straight line of positive slope, we have a high
positive correlation between the two variables. On the other hand, if
the points follow closely a straight line of negative slope, we have a high
negative correlation between the two variables. The correlation
between the two variables decreases numerically as the scattering of points
from a straight line increases. If the points follow a strictly random pattern, we
have zero correlation and conclude that no linear relationship exists
between X and Y.

FIGURE 1
C
O
R
R
E
L
A
T
I
O
N

I
N
T
E
R
P
R
E
T
A
T
I
O
N

G
U
I
D
E
CORRELATION INTERPRETATION GUIDE
It is important to remember that the correlation coefficient between two
variables is a measure of their linear relationship, and a value of r=0 implies a
lack of linearity and not a lack of association. Hence, if a strong quadratic
relationship exists between X and Y as indicated in Figure 1d, we shall still
obtain a zero correlation even though there is a strong nonlinear relationship.
The most widely used measure of linear correlation between two variables is
called the Pearson product-moment correlation coefficient
or simply the sample correlation coefficient.


r =

)(

2
(

)
2

2
(

)
2

One must be careful in interpreting r beyond what has been stated
above. For example, values of r equal to 0.3 and 0.6 only mean that
we have two positive correlations, one somewhat stronger than the
other. It is wrong to conclude that r = 0.6 indicates a linear relationship
twice as strong as that indicated by the value r = 0.3.
On the other hand r
2
, which is usually referred to as the sample
coefficient of determination, we have a number that
expresses the proportion of the total variation in the values of the
variable Y that can be accounted for or explained by the linear
relationship with the values of the variable X.
Thus a correlation of r = 0.6 means that 0.36 or 36% of the total variation
of the values of Y in our sample is accounted by a linear relationship
with the values of X.
EXAMPLE 1. COMPUTE AND INTERPRET THE CORRELATION COEFFICIENT FOR THE
FOLLOWING DATA:
X(heigh
t)
12 10 14 11 12 9
Y(weigh
t)
18 17 23 19 20 15
x

y

x
2


y
2


xy

12 18 144 324 216
10 17 100 289 170
14 23 196 529 322
11 19 121 361 209
12 20 144 400 240
9 15 81 225 135
x = 68

y = 112

x2 =
786
y2 =2128 xy =1292



) 112 )( 68 ( ) 1292 )( 6 ( r
947 . 0
] ) 112 ( ) 2128 )( 6 ][( ) 68 ( ) 786 )( 6 [(
2 2


r
947 . 0 r
A correlation coefficient of 0.947 indicates a
very good linear relationship between X
and Y. Since r
2
= 0.90, we can say that 90%
of the variation in the values of Y is
accounted for by a linear relationship with
X.
TEST STATISTICS
After computing for the Pearson Product Coefficient, we will now determine
whether to accept or reject the null hypothesis.
To do this we will compute for the t value.




After computing for the t value, we will compare it to the tabular value
obtained by the matrix table at certain level of significance with n-2
degrees of freedom.
Decision Rule: Reject Ho if ltcl t
a/2,(n-2)
Otherwise, accept.





2
1 2 r n r t
2
9 . 0 1 2 6 947 . 0 t
35 . 4 t
SAMPLE NO. 2
Marks obtained by 5 students in algebra and trigonometry as given below:

Algebra 15 16 10 12 8
Geometry 18 11 10 20 17
Calculate the Pearson correlation coefficient.
INTERPRETATION
A correlation coefficient of -0.424
indicates a moderately small
negative relationship between X
and Y. Since r
2
= 0.18, we can say
that 18% of the variation in the
values of Y is accounted for by a
linear relationship with X.

TEST STATISTICS
76 . 0
18 . 0 1 2 5 424 . 0
1
2
2
2

t
t
r
n
r t
Individual
student
Grade in
Math (x)
x
2


Grade in
Science(y)
y
2


xy

1 85 7255 80 6400 6800
2 90 8100 89 2.____. 8010
3 87 7569 84 7056 7308
4 79 6241 86 7396 6794
5 75 1.____. 79 6241 5925
6 80 6400 86
7396 3.____.
7 88 7744 90 8100 4.____.
8 85 7225 90 8100 7650
9 86 7396 87 5.____. 7482
10 80 6400 86
7396 6.____.
n=?
7.___.

x =835

x
2
=? 8._.

y = 857

y
2
=? 9.__.

xy =?
10._.

11-13 Find the correlation coefficient
14.Coefficient of Determination
15. Interpretation

Вам также может понравиться