STATISTICAL TOOLS
LINEAR CORRELATION AND SIMPLE
LINEAR REGRESSION ANALYSIS
Prof. Katherine J. Layag
Instructor
OBJECTIVES:
1. Identify independent and dependent variables;
2. Determine appropriate statistical tool to use given
the variables under study;
3. Determine signif ic ant relationships between
variables; and
4. Predict outcomes using correlation and regression
analysis
Independent and Dependent Variables
• Independent Variable: T he variable that is
manipulated or controlled to obser ve its
e ect on the dependent variable.
• Dependent Variable: T he variable being
tested and measured in an experiment.
EXAMPLE #1
A researcher is studying the ef fect of study
hours on exam scores.
Independent variable: Number
hours.
of study
Dependent variable: Exam scores
EXAMPLE #2
A teacher investigates whether using visual
aids in the classroom impacts students'
retention of information.
Independent variable: Use of visual aids
Dependent variable: Students' retention
of information
EXAMPLE #3
A scientist examines the ef fect of dif ferent
fe ilizer types on plant growth.
Independent variable: Type of fe ilizer
Dependent variable: Plant growth (height
or biomass)
EXAMPLE #4
A company tests whether employee
productivity increases after implementing a
exible work schedule.
Flexible
Independent variable: schedule work
Dependent variable: Employee
productivity
EXAMPLE #5
A medical researcher studies how a new
drug af fe cts blood pressure levels in
patients.
Independent variable: Drug dosage
Dependent variable: Blood pressure
levels
Determining the Appropriate
Statistical Tool
Types of Variables
• Quantitative Variables:
Measurable (e.g., test scores, heights,
weights).
• Qualitative Variables:
Categorical (e.g., gender, satisfaction
levels).
Tool Selection Guidelines:
• T-test for comparing means between two
groups.
• Chi-square test for categorical data.
• Correlation for analyzing relationships between
two continuous variables.
• Regression for predicting the value of one
variable based on another.
EXAMPLE #1
Variables: Hours spent studying and
exam scores
What statistical tool would be appropriate to
determine the relationship?
Correlation and Regression
EXAMPLE #2
Variables: Temperature and ice cream
sales
Correlation and Regression
EXAMPLE #3
Variables: Age and annual sala
Correlation
EXAMPLE #4
Variables: Employee work experience (in
years) and monthly pe ormance rating
Correlation and Regression
EXAMPLE #5
Variables: Adve ising budget and
company revenue
Regression Analysis
Analyzing Signi cant
Relationships
Correlation Coef ficient (r): A value between -1
and 1 that indicates the strength and direction of
the relationship between two variables.
Positive correlation (r > 0) – variables move
in the same direction.
Negative correlation (r < 0) – variables move
in opposite directions.
No correlation (r ≈ 0) – no relationship
between variables.
EXAMPLE
Hours Exam
Student Studied Score
A 2 55
B 3 60
C 4 65 How to Calculate and
D 5 70 Interpret a Correlation
E 6 75 (Pearson's r)
F 7 80
https:
G 8 85 //[Link]/lVOzlHx_15s?
H 9 90 si=m8PSETNZsC9YiFqb
I 10 95 EXCEL COMPUTATION
EXAMPLE #1
Is there a relationship between the number of years
of experience and salar yamong employees in a
tech company?
Years of Experience: [1, 3, 5, 7, 10]
Sala (in thousands): [40, 50, 60, 70, 90]
Correlation Score (Pearson’s r): 0.97
A correlation score of 0.95 indicates a ver ystrong positive
correlation between years of experience and salar y. T his
suggests that as years of experience increase, salaries tend to
increase as well.
EXAMPLE #2
Is there a relationship between the number of hours
studied and the f inal exam scores among college
students?
Number of Hours Studied: [2, 4, 6, 8, 10]
Final Exam Scores: [60, 65, 70, 80, 85]
Correlation Score (Pearson’s r): 0.95
A correlation score of 0.95 indicates a ver ystrong positive
correlation between number of hours studied and the f inal exam
scores . T his suggests that as the students studied long hours,
they may get high exam scores.
EXAMPLE #3
Is there a relationship between daily water intake
and energy levels repo ed by individuals?
Daily Water Intake (liters): [1, 2, 3, 4, 5]
Energy Levels (self-repor ted on a scale of 1-10): [4,
5, 6, 7, 8]
Correlation Score (Pearson’s r): 0.98
A correlation score of 0.98 indicates an extremely strong positive
correlation between daily water intake and repor ted energy
levels. T his suggests that higher water intake is associated with
higher repo ed energy levels.
EXAMPLE #5
Is there a relationship between the number of
marketing hours and sales revenue for a product?
Marketing Hours: [10, 20, 30, 40, 50]
Sales Revenue (in thousands): [15, 25, 35, 45, 60]
Correlation Score (Pearson’s r): 0.93
A correlation score of 0.93 indicates a strong positive correlation
between marketing hours and sales revenue. T his suggests that
as marketing hours increase, sales revenue tends to increase as
well.
REGRESSION
Simple Linear Regression:
ANALYSIS
A method to predict the value of a dependent variable based on the
independent variable. How to Interpret a
Regression Equation:
REGRESSION (Pearson's r)
https:
y=mx+b //[Link]/ZsSf1F8IHds?
si=4M16Oe19aI2hsYXG
where y is the predicted outcome, m is the slope, x is the
independent variable, and b is the intercept.
WHEN TO USE?
Regression is used when you want to examine the
relationship between a dependent variable
(outcome) and one or more independent variables
(predictors). It helps in predicting the value of the
dependent variable based on the independent
variables.
EXAMPLE
Let's assume a dataset where students test scores depend on
’
the number of hours they studied.
Hours Test Score
Studied
2 50
4 60
6 65
8 80
10 85
EXAMPLE
Let's assume a dataset where students test scores depend on the
’
number of hours they studied.
Hours Test
Studie Score
d
2 50
4 60
6 65
8 80
10 85
EXAMPLE
Let's assume a dataset where students test scores depend on the
’
number of hours they studied.
Hours Test
Studie Score
d
2 50
4 60
6 65
8 T 80he model shows a strong positive relationship between hours studied and
10 test85 scores. Each additional hour of study is expected to increase the test score
by 4.5 points.
KEY POINTS
• Independent Variable: T he factor that is manipulated
or controlled in a study (cause).
• Dependent Variable: T he factor that is measured or
obser ved in response to changes in the independent
variable (e ect).
Example: In a study of how exercise af fe cts weight,
exercise is the independent variable, and weight is the
dependent variable.
KEY POINTS
• Correlation: Measures the strength and direction of
the relationship between two continuous variables
(e.g., height and weight).
• Regression: Predicts the value of one variable based
on the value of another (e.g., predicting sales based
on temperature).
KEY POINTS
• Simple Linear Regression: A mathematical model
used to predict the value of a dependent variable (y)
based on the independent variable (x).
• Regression Equation: 𝑦=𝑚𝑥+𝑏
m: Slope (rate of change)
b: Intercept (sta ing point).
• Regression helps forecast future values based on
historical data, such as predicting sales from
temperature trends.