2. Suppose the Acme Drug Company develops a new drug, designed to prevent colds.

The company states that the drug is

equally effective for men and women. To test this claim, they choose a a simple random sample of 100 women and 200
men from a population of 100,000 volunteers. At the end of the study, 38% of the women caught a cold; and 51% of the
men caught a cold.

a. Based on these findings, can we reject the company's claim that the drug is equally effective for men and
women? Use a 0.05 level of significance.
b. Based on these findings, can we conclude that the drug is more effective for women than for men? Use a 0.01
level of significance.

3. In a study of patients on sodium-restricted diets, 55 patients with hypertension were studied. Among these,
24 were on sodium-restricted diets. Of 149 patients without hypertension, 36 were on sodium-restricted diets.
We would like to know if we can conclude that, in the sampled population, the proportion of patients on
sodium-restricted diets is higher among patients with hypertension than among patients without hypertension.

L#22 Correlation and Regression

 Correlation analysis is a method used to measure the strength of relationship between two or more
variables.
 The correlation calculation only works well for relationships that follow a straight line. Correlation Is Not
Good at Curves
 "Correlation Is Not Causation" ... which says that a correlation does not mean that one thing causes
the other (there could be other reasons the data has a good correlation).

A. Scatter Diagram: Consider the grades of five students in English and Mathematics

Student Eng (x) Math (y)

100
A 55 69
E C
B 64 85 75 B
M
C 96 99 A 50 A
D 44 52 T D
H 25
E 83 89
25 50 75 100
ENGLISH
Types of Correlation
A. Direction (sign)
1. POSITIVE. High scores in one variable are associated with high scores in the second variable. (v.versa)
2. NEGATIVE. High scores in one variable are associated with low scores in the second variable. (v.versa)
3. ZERO. Scores in one variable tend to score neither systematically high nor low in the other variable.

B. Coefficient

1 is a perfect Value of correlation r Interpretation positive correlation

0 is no ±0.80 < r < ±0.99 High correlation
-1 is a ±0.60 < r < ±0.79 Moderately high perfect negative correlation
±0.40 < r < ±0.59 Moderate
C. Scatter ±0.20 < r < ±0.39 Low Diagram
±0.01< r < ±0.19 negligible

1
A. Pearson Product-Moment Correlation
There are five assumptions that are made with respect to Pearson's correlation:
1. The variables must be either interval or ratio measurements
2. The variables must be approximately normally distributed (
3. There is a linear relationship between the two variables
4. Outliers are either kept to a minimum or are removed entirely.
5. There is homoscedasticity of the data.

Problem 1
Below are the data for six participants giving their number of years
in college (X) and their subsequent yearly income (Y). Income here
is in thousands of Pesos. Test whether there is a relationship
with Alpha = .05.

Step 1 Ho: There is no significant linear correlation between years of education and income
Ha: There is a significant linear correlation between years of education and income
Step 2 α = 0.05
Step 3 rcritical = + 0.811
Step 4 Reject Ho if r < - 0.811 or r > 0.811
Step 5

Step 6 There is a significant relationship between years spent in college and income. The more years of school,
the more the subsequent income. (The relation is significant; the result is not due to chance alone).
Problem 2 Problem 3
A teacher wants to find out if students’ scores in English are A teacher wants to know if the number of hours X
correlated with the scores in Filipino. Use α = 0.01 spent in studying X is correlated with the score
obtained in an examination Y
Studen Scores in Scores in XY X2 Y2 Student X Y XY X2 Y2
t English X Filipino Y A 3.0 20
1 28 27 B 2.7 34
2 22 2 C 3.8 19
3 18 14 D 2.6 10
4 16 25 E 3.3 24
5 30 15 F 3.4 31
6 25 23
7 19 17
8 12 10 2
9 13 22
10 24 14
B. Spearman Rank Correlation Coefficient
 It is also known as the "spearman rho" or "spearman r correlation".
 Correlation coefficient between the ranks (ordinal level). The correlation coefficient is sometimes
denoted by rs.
 Spearman's correlation determines the strength and direction of the monotonic relationship between
your two variables rather than the strength and direction of the linear relationship between your two
variables, which is what Pearson's correlation determines.

Pic 1 is monotonic and linear

Pic 2 is monotonic but not linear
Pic 3 is neither monotonic nor linear

Problem 1
Ten teaching styles were ranked by ABM students and Stem students. The data are tabulated in the table below
where the highest rank(most preferred) is 1 and the lowest rank(least preferred) is 5. Is there a significant relation
between the ranking of ABM and Stem at α= 0.10
Teaching
Style
ABM STEM d d2 Step 1 Ho: There is no significant difference between the preferences of ABM
A 6 5 against STEM.
B 3 2 Ha: There is a significant difference between the preferences of ABM
against STEM.
C 1 3
Step 2 α = 0.10
D 8 6
Step 3 C.V. = ±0.600
E 4 7
Step 4 Reject H0 if rs < - 0.6 or H0 if rs > 0.6
F 2 1
Step 5
G 10 9
H 9 8
I 5 4
J 7 10 Step 6 ___________________________________________________________

Problem 2 Problem 3
The following table shows the rating of a group of five The table below shows the evaluations of the services
Students who have been evaluated independently for of the canteen. Evaluations were done by the faculty
leadership on a scale of 1 to 10 by the principal and a members and the students. Determine if there is a
faculty member. Calculate rs if there is a correlation difference between the two evaluations.
between the two evaluations.
Service Faculty Students
Students Principal area Faculty
A 4 A 7 8 6
B 6 B 8 9 8
C 7 C 6 7 8
D 7 D 9 6 7
E 5 E 7 6 5
F 5 9
G 8 4

C. REGRESSION ANALYSIS
If two variables are correlated, then it is possible to predict or estimate a variable based on the changes
or movements of the other variable. Let X and Y be the correlated variables, the regression equation can be
represented by Y = a + bX, where b ≠ 0.
3
a
  Y   X     X   XY 
2

b
n  XY     X   Y 
n X    X  n X 2    X 
2 2 2

Problem1.
The following table shows the number of weeks six persons have work at an automobile inspection station and
the number of cars each one inspected on a given day.
a. Determine the regression equation
b. Predict the number of cars inspected by someone who has been working for 10 week.
Employee No. of No. of cars XY X2
weeks (X) inspected (Y)
A 2 13
B 7 21
C 9 23
D 1 14
E 5 15
F 12 21
X = Y =  XY = X 2
=

Problem 2 Problem 3
The table below shows the number of hours 9 The table below shows the final grades of 7
employees have spent working and the number randomly selected SHS students in English(X)
of defective products they made. Determine the and Mathematics (Y). Write the regression
regression equation. Estimate the number of equation.
defective products made by an employee who
worked for 8 hours.

Employee No. of No. of XY X2 Students English Math XY X2

hrs defective(Y) X Y
(X) 1 78 84
A 1.0 13 2 89 75
3 85 77
B 1.5 14 4 87 72
5 84 76
C 2.5 16
6 81 78
D 2.1 14 7 95 70

E 3.5 15

F 4.5 20

G 4.0 18

H 5.5 18

i 6.0 20

4
5
Critical value: SPEARMAN RANK ORDER CORRELATION COEFFICIEN
(DEGREE OF FREEDOM: n - 2