AHMEDABAD

STATISTICS
 RECORD OF WORK DONE
SR. EXPERIMENTS DATE SIGNATURE
NO. OF
EXPERI.
1
2
3
4
5
6
7
8
9
10
11
12
 Karl Pearson Correlation Coefficient

Case Studies on Plotting Bivariate Data: Scatter Diagrams and Activities

Practical 6.1: Study Hours and Exam Scores

Context: A statistics professor wants to investigate whether the number of hours students spend studying for
a final exam influences their exam scores. Data was collected from 10 randomly selected students.

Dataset:

Student Study Hours (x) Exam Score % (y)

A 5 70

B 10 85

C 2 50

D 8 80

E 12 90

F 3 60

G 7 75

H 15 95

I 4 65

J 9 82

Activity:

1. Plotting: Construct a scatter plot with "Study Hours" on the x-axis (independent variable) and
"Exam Score %" on the y-axis (dependent variable). Use graph paper or software like Excel or
Python.
 Study Hours vs Exam Score
110
Exam Score % 100
90
80
70
60
50
40
0 5 10 15 20

Study Hours

2. Analysis:

Student - x̄ -ȳ (x - x̄ )(y - ȳ) - x̄ squared (y - ȳ) square

-2.5 -5.2 13 6.25 27.04
2.5 9.8 24.5 6.25 96.04
-5.5 -25.2 138.6 30.25 635.04
0.5 4.8 2.4 0.25 23.04
4.5 14.8 66.6 20.25 219.04
-4.5 -15.2 68.4 20.25 231.04
-0.5 -0.2 0.1 0.25 0.04
7.5 19.8 148.5 56.25 392.04
-3.5 -10.2 35.7 12.25 104.04
1.5 6.8 10.2 2.25 46.24
0 -2.8E-14 508 154.5 1773.6
Pearson Correlation coefficient
(r) = 0.970447

o Describe the form of the relationship (linear or non-linear).

Linear form

o Identify the direction (positive, negative, or no trend).

Positive direction

o Assess the strength of the relationship (strong, moderate, weak) by observing how closely
the points cluster around a line.

Strong Relationship

3. Discussion: Does the scatter plot suggest that study hours could predict exam scores?

Yes, the scatter plot suggest that study hours could predict exam scores.
Practical 6.2: Temperature and Ice Cream Sales

Context: A local ice cream shop owner wants to understand how daily temperature affects ice cream sales.
Data was collected over 12 summer days.

Dataset:

Day Temperature (°C) (x) Ice Cream Sales (Units) (y)

1 25 50

2 30 70

3 22 40

4 35 90

5 28 60

6 20 30

7 32 80

8 27 55

9 33 85

10 24 45

11 29 65

12 31 75

Activity:

1. Plotting: Create a scatter plot with "Temperature (°C)" on the x-axis and "Ice Cream Sales (Units)"
on the y-axis.
 a scatter plot with "Temperature
(°C)" and "Ice Cream Sales (Units)"
100
Ice cream sales

80
60
40
20
15 20 25 30 35 40

Temperature

2. Analysis:

day (X-XBAR) (Y-YBAR) (X-XBAR)(Y-YBAR) (X-XBAR)SQUARE (Y-YBAR)SQUARE

1 -3 -12.08333333 36.25 9 146.0069444
2 2 7.916666667 15.83333333 4 62.67361111
3 -6 -22.08333333 132.5 36 487.6736111
4 7 27.91666667 195.4166667 49 779.3402778
5 0 -2.083333333 0 0 4.340277778
6 -8 -32.08333333 256.6666667 64 1029.340278
7 4 17.91666667 71.66666667 16 321.0069444
8 -1 -7.083333333 7.083333333 1 50.17361111
9 5 22.91666667 114.5833333 25 525.1736111
10 -4 -17.08333333 68.33333333 16 291.8402778
11 1 2.916666667 2.916666667 1 8.506944444
12 3 12.91666667 38.75 9 166.8402778
0 -2.36848E-15 940 230 3872.916667
Pearson Correlation Coefficient (r)= 0.995966795

o Determine if the relationship is linear or non-linear.

Linear Form

o Identify the direction of the trend.

Positive Direction

o Evaluate the strength of the relationship.

Strong Relationship

3. Discussion: Is there a potential causal relationship between temperature and ice cream sales?

Yes.
Practical 6.3: Advertising Budget and Product Sales

Context: A company wants to analyze the relationship between its monthly advertising budget and product
sales to optimize marketing strategies.

Dataset:

Month Advertising Budget (₹1000s) (x) Product Sales (Units) (y)

Jan 10 200

Feb 15 250

Mar 8 180

Apr 20 300

May 12 220

Jun 25 350

Jul 18 280

Aug 22 320

Sep 14 240

Oct 16 260

Activity:

1. Plotting: Plot a scatter diagram with "Advertising Budget (₹1000s)" on the x-axis and "Product
Sales (Units)" on the y-axis.
 400

350
Product Sales

300

250

200

150
5 10 15 20 25 30

Advertising Budget

2. Analysis:

MONTH (X-XBAR)
(Y-YBAR) (X-XBAR)(Y-YBAR) (X-XBAR)SQUARE (Y-YBAR)SQUARE
JAN -6 -60 360 36 3600
FEB -1 -10 10 1 100
MAR -8 -80 640 64 6400
APR 4 40 160 16 1600
MAY -4 -40 160 16 1600
JUN 9 90 810 81 8100
JUL 2 20 40 4 400
AUG 6 60 360 36 3600
SEP -2 -20 40 4 400
OCT 0 0 0 0 0
0 0 2580 258 25800
Pearson Correlation Coefficient (r)=1

o Classify the form, direction, and strength of the relationship.

Form- Linear

Direction- Positive

Strength- Strong

o Identify any outliers that deviate from the general trend.

Here, no any outliers that deviate from the general trend.

3. Discussion: Can the advertising budget reliably predict sales?

 Yes , the advertising budget reliably predict sales.

Practical 6.4: Exercise Frequency and Blood Pressure

Context: A health researcher is studying whether the frequency of weekly exercise sessions impacts systolic blood
pressure in adults aged 30–40.

Dataset:

Individual Exercise Sessions per Week (x) Systolic Blood Pressure (mmHg) (y)

140

130

145

120

135

125

115

138

132

122

Activity:

1. Plotting: Construct a scatter plot with "Exercise Sessions per Week" on the x-axis and "Systolic
Blood Pressure (mmHg)" on the y-axis.
 a scatter plot with "Exercise Sessions per
Week" and "Systolic Blood Pressure
(mmHg)"
150
145
140
135
Systolic Blood Pressure

130
125
120
115
110
0 1 2 3 4 5 6 7

Exercise Sessions per week

2. Analysis:

Individual (X-XBAR) (Y-YBAR) (X-XBAR)(Y-YBAR) (X-XBAR)SQUARE (Y-YBAR)SQUARE

1 -2.1 9.8 -20.58 4.41 96.04
2 -0.1 -0.2 0.02 0.01 0.04
3 -3.1 14.8 -45.88 9.61 219.04
4 1.9 -10.2 -19.38 3.61 104.04
5 -1.1 4.8 -5.28 1.21 23.04
6 0.9 -5.2 -4.68 0.81 27.04
7 2.9 -15.2 -44.08 8.41 231.04
8 -1.1 7.8 -8.58 1.21 60.84
9 -0.1 1.8 -0.18 0.01 3.24
10 1.9 -8.2 -15.58 3.61 67.24
0 1.13687E-13 -164.2 32.9 831.6
Pearson correlation coefficient (r)= -0.992699867

o Describe the form, direction, and strength of the relationship.

Form –Linear Direction-

Negative Strength-

Weak

3. Discussion: Could other factors (e.g., diet, stress) influence the observed relationship? How might
you account for these in a study?

Practical 6.5: Internet Usage and Academic Performance

Context: A university study explores whether daily internet usage affects students’ GPA. Data was collected from
10 students.
Dataset:

Student Internet Usage (Hours/Day) (x) GPA (y)

A 4 3.0

B 2 3.5

C 6 2.8

D 1 3.8

E 5 2.9

F 3 3.2

G 7 2.5

H 2 3.6

I 4 3.1

J 5 2.7

Activity:

1. Plotting: Create a scatter plot with "Internet Usage (Hours/Day)" on the x-axis and "GPA" on the
y- axis.

a scatter plot with "Internet Usage

(Hours/Day)" and "GPA"
4

3.5
GPA

2.5

2
0 1 2 3 4 5 6 7 8

Internet Usage

2. Analysis:

Student (X-XBAR) (Y-YBAR) (X-XBAR)(Y-YBAR) (X-XBAR)SQUARE (Y-YBAR)SQUARE

A 0.1 -0.11 -0.011 0.01 0.0121
 B -1.9 0.39 -0.741 3.61 0.1521
C 2.1 -0.31 -0.651 4.41 0.0961
D -2.9 0.69 -2.001 8.41 0.4761
E 1.1 -0.21 -0.231 1.21 0.0441
F -0.9 0.09 -0.081 0.81 0.0081
G 3.1 -0.61 -1.891 9.61 0.3721
H -1.9 0.49 -0.931 3.61 0.2401
I 0.1 -0.01 -0.001 0.01 0.0001
J 1.1 -0.41 -0.451 1.21 0.1681
0 -3.1E-15 -6.99 32.9 1.569
Pearson Correlation Coefficient(r)= -0.972898995

o Identify the form, direction, and strength of the relationship.

Form- Linear

Direction- Negative

Strength- Weak

o Check for any outliers and hypothesize their causes.

3. Discussion: Does the scatter plot suggest that internet usage impacts academic performance?
What limitations might this dataset have?