You are on page 1of 16


In Education 107B.
(Assess of student learning)
Mahardika Institute of Technology inc.
Illmoh Street, Bongao ,Tawi-Tawi

Submitted by:
Rhimaiza J. Hji Jainal Abidin
Katrina D. Madisa
Jaafar Timbassal

Submitted to:
Mrs. Vicitasion Alfad
Course Instructress
I- Learning Objectives: At the end of the lesson
the learners can able to:

a. Defined what is correlation.

b. Give their own examples on what does
topic taught to them.
c. Appreciate the correlation.
d. Relates in their daily life.

II- Subject matter:

Topic: (chapter 14) CORRELATION

Page: 283-296
III- Learning materials: Laptop, overhead
projector( power point presentation)

IV- Learning content/ procedural:

a. Activity:

 Greetings
 Ice breaker
 Checking attendance.

b. Abstraction:

Class our topic for today is all about the

c. Analysis:

A statistic called a correlation
coefficient(symbolized by r) helps us address
general issues lie those just mentioned or
answer specific questions like those that
Are athletes really poor scholars?

If you do poorly on the verbal portion of the

SAT, are you likely to do poorly on the
quantitative portion?

Do students with high grades in high school

really tend to get high grades in college?

As we have seen, distributions can

correlate positively or negatively. They
may also not correlate at all! The
correlation coefficient (r) tells us ay a
glance the strength and direction
(positive or negative) of the relationship
between distributions. Correlation
coefficients range from -1.0 to +1.0. the
closer the coefficient gets to -1.0 or +1.0,
the stronger the relationship. The sigh
of the coefficient tells us whether the
relationship is positive or negative.

The previous coefficients are described as

ranging from very weak to strong. You
may ask yourself, “How high must r be
for it to be strong?” well, there is no cut
and dried answer to this question
because an r = .40 may be considered
strong for one set of data (for example,
correlation of IQ scores and “happiness”)
and very weak for another (for example,
correlation of scores from two
standardized achievement tests).

A common example of positive correlation

is the relationship between height and
weight. As people increase in height, they
tend to increase in weight, and vice
versa. A real life example of negative
correlation is the relationship between
the number of cigarettes smoked per day
and life expectancy. As the number of
cigarettes smoked per day increases,
life expectancy decreases, and vice
versa. Fortunately, for those who are
smokers, the correlation is not very

As we have noted, the strength and

direction of a relationship between two
distributions can be determined by a
correlation coefficient. Scatterplots
also enable us to determine the strength
and direction of a correlation, but in a
less formal manner. A scatterplot is
nothing more than a graphical
representation of the relationship
between two variables representing the
scores in two distributions.
1. Correlation refers to the extent to which two
distributions are related or associated. That is, it
refers to the extent in which sores in one distribution
vary depending on the variation of scores in the other

2. The extent of correlation is indicated numerically by a

correlation coefficient(r) and graphically by a scatter

3. When high scores in one distribution tend to be

associated with low scores in another distribution,
and vice versa, the correlation is negative.

4. When high scores in one correlation tend to be

associated with high scores in another distribution
(with the same being true for low and moderate
scores), the correlation is positive.

5. Correlation coefficients may range from -1.0(perfect

positive correlation) to +1.0 (perfect positive
correlation) . A correlation of .00 indicate an
absence of relationship or association.
6. The size of the number of the correlation
coefficient indicates the strength of the
correlation (higher numbers indicates stronger
correlation), and the sigh indicates the direction
(positive or negative).

7. Scatterplots range from straight lines

indicative of a perfect correlation to ellipses
that approach circles. The tighter the
ellipses, the stronger the correlation; the
more circular the ellipses, the weaker the

8. The fact that two variables are correlated

with each other does not necessarily mean
that one variables causes the other . Often
the correlation is the result of the effects of
a third variable.
9. To compare the relative strength of correlation
coefficients it is necessary to square the
coefficients are not percentages; coefficients of
determination are.

10. When two distributions are linear related,

scores increase or decrease across the range
of scores.

11. When two distributions have a curvilinear

relationship, scores in one distribution may
increase and then decrease , or vice versa,
while scores in the other distribution
consistently increase or decrease.
12 Since a linear correlation coefficient will
underestimate the strength of a curvilinear
relationship, it is wise to construct a scatterplot
before computing a correlation coefficient.

13. When only a portion of the entire range of

scores for a distribution is considered (for
example, only high or low scores) in computing
a correlation coefficient, the strength of the
correlation coefficient decreases. This
effect is due to use of a truncated range of
scores, rather than the entire range of
d. Application:

A. Drills:
For practice

1. After pairing each X score with each Y

score in the order given, construct a
scatterplots of the data.

B. Evaluation:
Direction: Answer the following questions.

1. Does the scatterplot in question 1

indicate that the data are linear or
curvilinear? If X represents age and Y
represents average annual income in
thousands of dollars, describe this
relationship in words.

2. Using the formula given in Appendix B,

compute a Pearson Product-Moment
Correlation for the following data.
X: 10,8,14,6,4,8,7,3,7,10
Y: 12,7,13.8,7,6,6,4,9,11
c. Assignment:

Direction: Answer and explain the following


1. A researcher find a high positive

correlation between shoe size and
vocabulary size in elementary school
pupils. The researcher concludes that
big feet cause big vocabularies. Do you
agree or disagree? If so, why? If not,
why not?

2. Explain why the use of a truncated

range of scores will result in a lower
correlation between the variables in
question than if the distribution were
not truncated.