Correlation

Analysis
Meaning of CORRELATION
 Can be applied when the two quantitative variables whose
relationship is being investigated
 To measure the strength and the direction of the relationship
between two or more quantitative variables
 It is a statistical technique which can show if and how pairs of
variables are related

2
Correlation Analysis
 The main result of such analysis is called the CORRELATION
COEFFICIENT
 The coefficient of correlation can range from -1 to 1 inclusively.
 In a nut shell, CORRELATION is a measure of the STRENGTH
and the DIRECTION of the relationship.
 NOTE: There is no such cause-effect relationship between
variables.
 The variables are NOT distinguished into dependent and
independent variable

3
Correlation Analysis
 The sign tells the direction of the relationship and the
numerical values indicate its strength.
 Example: 0.87 and -0.87 are of similar size but the sign
indicates the direction of the relationship
 The degrees of relationship between two variables are
expressed as POSITIVE or NEGATIVE perfect correlation

4
Interpreting Coefficient of
Correlation
r Descriptive Level
Perfect Correlation
Between High Correlation
Between Moderately
Moderately High
High Correlation
Correlation
Between Moderately
Moderately Low
Low Correlation
Correlation
Between Low
Low Correlation
Correlation
0.00
0.00 No
No Correlation
Correlation

5
Interpreting Coefficient of
Correlation
 The closer r to +1 or -1, the more closely the variables are
related.
 If r is close to 0, it means that there is no relationship between
the variables.
 If r is positive, it means that as one variable gets larger, the
other variable gets larger too.
 If r is negative, it means that as one gets larger, the other
variable gets smaller.

6
 Pearson Product-Moment Coefficient of
Correlation
�
 Developed
  by Karl Pearson
 Can be used when the variables are either ratio or interval
scale.
 The formula is:

7
 Pearson Product-Moment Coefficient of
Correlation
 To test the significance of relationship between two
variables, critical value will be located by determining the
level of significance and the degrees of freedom, df = n – 2
 If the obtained coefficient of correlation (r) is greater than the
tabulated value/critical value, then it indicates significance.
 That is, there exists significant relationship between the two
variables.

8
 Example:
�Is there significant relationship between the two sets of test
score in Algebra and Geometry?
Algebra (X) Geometry (Y)
18 19
15 17
13 14
16 15
13 14
10 11
13 12
15 14
10 13
14 17

9
Solution:
�1)  Ho: There is no significant relationship between the
two test scores in Algebra and Geometry
� Ha: There is a significant relationship between the
two test scores in Algebra and Geometry
�2) Level of significance: with df= 10-2 = 8
�3) Test Statistic: Pearson r
�4) Decision Rule: Reject Ho if
Pearson r.jpg

10
Solution:
�5) Computation:

11
 Solution:
�5)  Computation:
� 2045; =137; 1933;

0.81

12
Solution:
�6) Decision: Reject the null hypothesis since the value of r is
positive which is larger than the tabulated value.
�7) Interpretation/Conclusion: There is a highly significant
correlation between Algebra and Geometry scores. Hence, when
the scores in Algebra are increased (decreased) then the scores
in Geometry are also increased (decreased).

13