Scribd
Upload
31 views32 pages

Topic 11 - Correlation

Uploaded by

Mu'izzuddin Mohamad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
31 views32 pages

Topic 11 - Correlation

Uploaded by

Mu'izzuddin Mohamad
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 32

STATISTICS FOR

SOCIAL SCIENCE

SHAR 2053

CORRELATION
CORRELATION

This chapter will focus on:

❑The Pearson Correlation


❑Using and Interpreting the Pearson Correlation
❑Hypothesis Tests with the Pearson Correlation
IMPORTANT TERMINOLOGIES

Direction
Form
Degree
Scatterplot
Correlation Coefficient
Pearson Correlation
MEASURING AND DESCRIBING
RELATIONSHIPS BETWEEN VARIABLES

A correlation is a statistical method used to


measure and describe the relationship between
two or more variables (continuous variables).
A relationship exists when changes in one variable
tend to be accompanied by consistent and
predictable changes in the other variable.
A correlation typically evaluates three
aspects of the relationship:
the direction
the form
the degree
The direction of the relationship is
measured by the sign of the correlation
Two variables may correlate to each other in 3
possible ways:

✓ Positive Relationship:
Both variables vary in the same direction - as
one goes up, the other goes up
eg.
salary and years of education are positively correlated because
the people who make the highest salaries tend to be the ones
who have gone to school the longest
✓ Negative Relationship:
Two variables vary in the opposite direction - as one goes up, the
other goes down. e.g:
The number of daily hassles and the amount of immunoglobulin A in a person's
system are negatively correlated because as the number of hassles goes up, the
amount of immunoglobulin A tends to go down.

✓ Zero/not significant Relationship:


Two variables vary with freely without any kind of rules or
form of relationship. e.g:
The relationship between personality fluctuations and the movement of
distant stars has a zero correlation. Contrary to strong beliefs in astrology
held by a surprising number of people, studies have found that there is
absolutely no correlation between the position of stars at the time you are
born and the true nature of your personality
The most common form of relationship is a
straight line or linear relationship which is
measured by the Pearson correlation.

Other forms of relationships include:


Point Bi-serial
Spearman
Phi Coeffecient
Degree of Correlation: How Strongly Are
Variables Correlated?

The degree of correlation between two variables can


be investigated using the combination of two
methods:

Scatterplot – a graph with plotted values for two


variables being compared
Correlation Coefficient
The degree of relationship (or the strength or
consistency of the relationship) is measured by
the numerical value called correlation coefficient
(denoted by r or rXY).
The value of r vary between -1 and +1 i.e.
-1 ≤ r ≤ 1
r = 1 indicates a perfect positive relationship between variables (i.e. the
changes of values (pairs) of variables follow a specific positif linear rule)
r = -1 indicates a perfect negative relationship between variables (i.e.
the changes of values (pairs) of variables follow a specific negative linear
rule)
r = 0 indicates no relationship between variables (i.e. the changes of
values (pairs) of variables occur in no specific rule)
Y Y

X X

Y Y

X X
Scatterplot of Family Income vs Student’s Average Grade
COMPUTING CORRELATION
COEFFICIENT r

To compute a correlation you need pair of


scores of variables being investigated
(normally denoted by X and Y) for each
individual in the sample.
The computation of r depends on the form of
correlation used.
THE PEARSON CORRELATION

The Pearson correlation measures the


direction and degree of linear (straight
line) relationship between two variables.
Pearson correlation applies when the
scores be in numerical values from an
interval or ratio scale of measurement.
THE PEARSON CORRELATION

• The Pearson Correlation, r

where
PERFORMING HYPOTHESIS TESTING WITH
PEARSON CORRELATION
The Recommended Steps (manual computation)

Step 1 - State the hypothesis


H0: p = 0 (there is no correlation between variables)
H1: p = 0 (there is significant correlation between variables)

Step 2 - Determine the p-value (0.05) and df=n-2 value

Step 3 - Find the critical value of r, refer to table of Pearson correlation

Step 4 - Compute

Step 5 - Make decision (compare r-value in step 4 with r-critical value in step 3)
EXAMPLE
Given is a set of scores.
a. Draw a scatter plot
b. Make a preliminary estimation of the correlation.
c. Calculate the Pearson Correlation and test the hypothesis
EXAMPLE

Looking at the
scatter plot, it
appears that there is
a very good (but not
perfect) positive
correlation. You
should expect an
approximate value of
r = +.8 or +.9.

Step 1
Ho : r = 0 (there is no population correlation)
H1 : r  0 (there is a population correlation)
Step 2 - p-value
(0.05), with two tail,
df = 3.

Step 3 - r-critical
value = 0.878

The greater the


sample size/df value,
the lower r-critical
value needed to
reject the null
hypothesis.
Step 4
To calculate the Pearson Correlation, find the SSX, SSY, and SP for a
sample of n = 5 pairs of scores

Mx=6 My=4

Using the values from Table, the Pearson correlation is:

Step 5
With n=5 pairs of X and Y values the test has df=3. For a two-tailed test with α = .05, the
critical value is 0.878. Because our correlation is smaller than this value, we fail to reject
the null hypothesis and conclude that the correlation is not significant.
TRY IT OUT!

Student X Y
The table shows 8
pairs of data
(measuring X and Y) A 11 14
are taken from a
B 6 7
sample. Draw a
scatter plot and C 16 15
perform
appropriate D 4 7
hypothesis testing
to see if there is E 1 3
significant
F 10 9
relationship
between the two G 5 9
variables.
H 3 8
Student X Y X-Mx Y-My (X-Mx)2 (Y-My)2 (X-Mx)(Y-My)

A 11 14

B 6 7
C 16 15
D 4 7
E 1 3
F 10 9
G 5 9
H 3 8
Mx= My= SSx = SSy = SP =
THE HYPOTHESES:

Ho : ρ/r = 0 (there is no population correlation)


H1 : ρ/r  0 (there is a population correlation)
SCATTERPLOT OF X VERSUS Y
Analyze Using SPSS

Click Analyze - Correlate - Bivariate - Insert the


mean of variables - click ok
Reporting Results:
The significant value

• Reject Ho as p < α , i.e. A correlational analysis reveals


that scores X and Y are significantly related, r = 0.94,
n = 8 , p<0.05 level with two-tailed.

• Finding shows that there is a significant relationship


between X and Y (r=0.94, p<0.05). The relationship is
strong and positive in which the increase of X
associated with the increase of Y. Thus accepting the
alternative hypothesis in this study.
Reporting Results:
Level and Direction of Relationship
• Direction of the relationship can be determined
based on the r-value itself, or simply analyse the
scatterplot.
• Previous researcher have different opinion on
the level of relationship, one of the rule of
thumb that can be referred are shown in the
table below
SPSS Step-BY-Step
• Pearson Correlation by Dr Irza Hanie
https://www.youtube.com/watch?v=ZG3iRrPoJZ
Q&feature=youtu.be

• Regression by Dr Irza Hanie


https://www.youtube.com/watch?v=pnM0lZyO
QfA&feature=youtu.be
REFERENCES

https://cengage.vitalsource.com/#/books/9781305856424/cfi/593!/4
/4@0.00:0.00

Gravetter F J & Wallnau L B. (2013). Statistics for the Behavioral


Sciences

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy