You are on page 1of 39

FACULTY OF CIVIL AND ENVIRONMENTAL ENGINEERING

BFC34303
CIVIL ENGINEERING
STATISTICS
SEMESTER 1 SESSION 2019/2020

PROJECT REPORT
Parking violation of cars that illegally parking at UTHM,
G3 lecture complex
LECTURER’S NAME MADAM NOORLIYANA BINTI OMAR
SECTION 5
GROUP 1
NAME MATRIC NO.
1. ADRIN BIN AHMAD CF180004
BUDIN
2. DAELZEE VEENNA BONG DF170030
GROUP MEMBERS 3. DYEANNA DONNIS CF180125
4. FARAH NASTASYA BINTI CF180147
MOHD REDZUAN
5. NURSHAFIQA BINTI CF180148
LUDIN
SUBMISSION DATE 18TH DECEMBER 2019
TABLE OF CONTENT

CHAPTER 1: INTRODUCTION

1.0 Introduction 1

1.1 Case Study Area 2

1.2 Problem Statement 3

1.3 Objective 3

CHAPTER 2: THEORY

2.0 Theory 4

CHAPTER 3: METHODOLOGY

3.0 Methodology 5

3.1 Data Collection Method 5

3.2 Flowchart 6

3.3 Data Presentation 7

CHAPTER 4: DATA ANALYSIS

4.0 Data Analysis 9

4.1 Discrete Statistics 9

4.2 Probability 15

4.2.1 Probability distribution function 16

4.2.2 Special Probability Distribution 18

4.3 Inferential Statistics 24

4.3.1 F Distribution 15

4.3.2 One-Way ANOVA Test 26

4.4 Hypotesis Testing 29


4.5 Discussion 31

4.5.1 Result Presentation 31

CONCLUSION 33

REFERENCE 35

ATTACHMENTS 36
CHAPTER 1

INTRODUCTION

1.0 Introduction

Parking spaces are an important facilities for a building system in ensuring the proper
placement and facilitation of the transportation used by the people to access the building.
Moreover, parking is consider an essential part of the transportation system generally linkage
to the building system in a proper environment of accessibility and functionality for the
owners, tenants, or people conducting activities within the building. Besides, it provides
convenience to the building users generally in providing a safe and convenient spaces for
them to park their vehicles [1]. However, illegal car parking has become a problem in dues to
the increasing numbers of vehicles transportation and lack of facilities. Apart from that, the
underlying conception of the ‘culture’ of illegal car parking among Malaysians particularly
within the city center and developed townships. The parking violation act are such motorist
double or triple-park, parking on the pavements and walkways in public areas as well as
along public roads with yellow lines [2].

Statistics is the method of dealing with collecting, classifying, presenting, describing,


analyzing and interpreting data to ensure us to derive conclusions and making reasonable
decisions [3]. Statistic data in engineering is useful in various forms of conduct especially in
the regards of our study in traffic engineering of the sub-field of the civil engineering. The
method of statistically interpreting the data on the research is very important in determining
and finding the pattern that depends accordingly to its purpose and understanding whether to
be utilized in the improvement or as additional information from the conclusion derived.

Thus, in this study, the statistical data is collected and applied in conducting the case
study on the parking violation of the cars that illegally parking at UTHM, G3 lecture
complex. This study is done for a period of 2 days with each day taking a total of 3 hours in
15 minutes interval of observation and data collection. The data is taken during week days

1
generally during university lecture day to observe the usage of the parking spaces at G3
lecture complex. In University Tun Hussein Onn Malaysia (UTHM), parking spaces are an
important facilities for the smooth progression of the daily activities within the institution as
the main transportation means of the university staffs and some students is vehicles mainly
cars and motorcycle. Furthermore, the main case study area is at G3, lecture complex where
the students and lecturer undergoes their daily activities of lecture or classes. As a result,
through this case study, we will be analyzing and statistically determining the conclusive
solution to the problem statement that will achieve our aims of study.

1.1 Case Study Area

The case study is conducted at G3 lecture complex, UTHM parking lot area.

G3 Lecture
Complex

Figure 1.0: Location of G3 lecture complex.

2
Figure 1.1: Satellite image of the G3 lecture complex.

1.2 Problem statement

i. The numbers of parking violation at G3 lecture complex.


ii. The correlation between the numbers of parking violation and parking spaces
available at G3 lecture complex.
iii. The parking spaces to accommodate users at G3 lecture complex.

1.3 Objective

The objectives of this project is;

i. To study the numbers of parking violation at G3 lecture complex.


ii. To investigate the correlation between the numbers of parking violation and parking
spaces available at G3 lecture complex.
iii. To determine the parking spaces to accommodate users at G3 lecture complex.

3
CHAPTER 2

THEORY

2.0 Theory

In everyday life, everything that involves travelling by car will involve parking
somewhere. No matter what the purpose of the trip is, be it leisure or business, still someone
will need a place where to leave the car. In every location and situation there are different
needs when it comes to parking (Litman 2006).
The study on the inefficiency of parking monitoring methods combines
knowledge and understanding from fields/subjects such as Science and Technology,
Transportation, Economics, Accounting and Management. Science and Technology can
be directly seen in analysing suggested methods in arriving to efficient monitoring of the
parking lots. Applying the knowledge of Science and Technology can help to arrive to
solutions which are user as well as environmental friendly easing the whole parking
chain, while at the same time ensuring less human intervention. The knowledge of
economics and management is important in analysing costs, man power as well as
accuracy of the current solutions focusing on how we can adjust all the parameters and
hence have optimal solutions. The transportation sector is the source of these
complications since it is through transportation, that problems involving parking arise.
The knowledge is vital because parking patterns can alter the flow of traffic depending on
how the vehicles are parked (e.g. diagonal, perpendicular or parallel to the traffic flow)
(Chick 1996). On-street parking is mainly by default and may be subject to terms such as
a payment, short time free parking or not allowed to park at all. These are called parking
restrictions (Driving School Manual 2010 73-82). Even though parking lots are monitored
such that users must adhere to the rules, still monitoring methods are porous and give
chances to violation of the rules and regulations set by the governing bodies.

4
CHAPTER 3

METHODOLOGY

3.0 Methodology

3.1 Data Collection Method

In this project, the method that is use to collect data is by observing and recording for
2 days with 3 hours each. The collected data is the number of cars illegally park at G3
Lecture Complex. The data recorded will be used to calculate cumulative, mean, variance and
standard deviation. The data will be recorded in the table below:

Time (every 0.25 hour)


Plate No.
0 0.25 0.50 0.75 1.00 1.25 1.50 1.75 2.00 2.25 2.50 2.75

∑ Total no.
of car
Table 3.0 Data collection table.

5
3.2 Flowchart

START

Identify the variable and time.


- Cars parked illegally
- 6 hours

Collect data at G3.


- Collect data manually
- Record data on data table

Present data.
- Outcome of collected data.

Data calculation.
- Mean, variance and standard
deviation.

Data analysis.

END

Chart 3.0 Working progress.

6
3.3 Data Presentation
Location : G3 Lecture Complex
Date : 26 November 2019
Time : 1.00PM – 4.00PM (3 hours)

Time (every 0.25 hour)


Plate No.
0 0.25 0.50 0.75 1.00 1.25 1.50 1.75 2.00 2.25 2.50 2.75
478 / / / / - - - - - - - -
960 / / / - - - - - - - - -
820 / / / / / / / / / / / /
444 / - - - - - - - - - - -
154 - - - - / / / / / / / /
651 / - - - - - - - - - - -
665 / / - - - - - - - - - -
555 - - - - - / / / / / / /
981 / - - - / / / / / / / /
451 / / / / / / / / / / / /
866 / - - - - - - - - - - -
666 / - - - - - - - - - - -
734 / / / / / / / / / / / /
435 / - - - - - - - - - - -
312 - - - - / / / / / / / /
891 / / / / / / / / - - - -
944 / - - - - / / / / / / /
187 / - - - - - - - - - - -
578 - - - - / / / / / / / /
704 - - - - - / / / / / / /
911 / - - - - - - - - - - -
373 - - - - / / / / / / / /
689 / - - - - - - - - - - -
∑ Total no. 7 6 5 9 12 12 12 11 11 11 11
17
of car
Table 3.1(a) Data collected on 26 November 2019.

7
Location : G3 Lecture Complex
Date : 27 November 2019
Time : 8.00AM – 11.00AM (3 hours)

Time (every 0.25 hour)


Plate No.
0 0.25 0.50 0.75 1.00 1.25 1.50 1.75 2.00 2.25 2.50 2.75
274 / / / / / / / / - - - -
806 / / / / / / / / - - - -
722 / / / / / / / / / / / /
295 - - / / / / - - - - - -
173 - - / / / / / / / / / /
297 - - / / / / / / / / / /
735 - - / / / / / - - - - -
908 - - / / / / / / / / / /
900 - - / / / / / / - - - -
152 - - / / / - - - - - - -
275 - - / / - - - - - - - -
147 - - / / - - - - - - - -
712 - - - / / / / / / / / /
844 - - - / / / / / / / / /
944 - - - / / / / / / / / /
840 - - - / / / / / / / / /
465 - - - - / / / / / / / /
∑ Total no. 3 12 16 15 14 14 12 9 9 9 9
3
of car
Table 3.1(b) Data collected on 27 November 2019.

8
CHAPTER 4

DATA ANALYSIS

4.0 Data Analysis

4.1 Discrete Statistics

Location : G3 Lecture Complex


Date : 26 November 2019
Time : 1.00PM – 4.00PM (3 hours)

Time class Midpoint, 𝒙 Frequency, 𝒇 𝒇𝒙 𝒙𝟐 𝒇𝒙𝟐 (𝒇𝒙)𝟐


0 – 0.25 0.125 17 2.125 0.016 0.272 4.516
0.25 – 0.50 0.375 7 2.625 0.141 0.987 6.891
0.50 – 0.75 0.625 6 3.750 0.391 2.346 14.063
0.75 – 1.00 0.875 5 4.375 0.766 3.83 19.141
1.00 – 1.25 1.125 9 10.125 1.27 11.43 102.516
1.25 – 1.50 1.375 12 16.500 1.891 22.692 272.25
1.50 – 1.75 1.625 12 19.500 2.641 31.692 380.25
1.75 – 2.00 1.875 12 22.500 3.516 42.192 506.25
2.00 – 2.25 2.125 11 23.375 4.516 49.676 546.391
2.25 – 2.50 2.375 11 26.125 5.641 62.051 682.516
2.50 – 2.75 2.625 11 28.875 6.891 75.801 833.766
2.75 – 3.00 2.875 11 31.625 8.266 90.926 1000
∑ Total 18 124 191.5 35.946 393.895 4368.55

9
Midpoint, Frequency, Cumulative Cumulative percentage
Time class
𝒙 𝒇 frequency of frequency (%)
0 – 0.25 0.125 17 17 13.71
0.25 – 0.50 0.375 7 24 19.36
0.50 – 0.75 0.625 6 30 24.20
0.75 – 1.00 0.875 5 35 28.23
1.00 – 1.25 1.125 9 44 35.49
1.25 – 1.50 1.375 12 56 45.17
1.50 – 1.75 1.625 12 68 54.85
1.75 – 2.00 1.875 12 80 64.53
2.00 – 2.25 2.125 11 91 73.40
2.25 – 2.50 2.375 11 102 82.27
2.50 – 2.75 2.625 11 113 91.14
2.75 – 3.00 2.875 11 124 100

Cumulative percentage of frequency (%) againts midpoint


120
Cumulative percentage of frequency (%)

100

80

60

40

20

0
0 0.5 1 1.5 2 2.5 3 3.5
Midpoint

Graph 4.1(a): Cumulative percentage of frequency against midpoint

10
Mean:

∑ 𝑓𝑥 191.5
𝜇= = = 1.53
𝑛 124

Median:

1
× 124 = 62
2

∴ 𝐶𝑙𝑎𝑠𝑠 𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙 = 1.25 − 1.50

Mode:

𝐿𝑚 = -0.5

𝑑1 = 17

𝑑2 = 10

𝑑1 17
𝐿𝑚 + ( ) 𝑐 = −0.5 + ( ) = 3.28
𝑑1 + 𝑑2 17 + 10

Variance:

(∑ 𝑓𝑥)2 4368.55
∑ 𝑓𝑥 2 − (393.895 − 124 )
∑𝑓
𝑠2 = = = 2.92
(∑ 𝑓) − 1 124 − 1

Standard deviation:

(∑ 𝑓𝑥)2
∑ 𝑓𝑥 2 −
√ ∑𝑓
𝑠= = √2.92 = 1.71
(∑ 𝑓) − 1

11
Location : G3 Lecture Complex
Date : 27 November 2019
Time : 8.00AM – 11.00AM (3 hours)

Time class Midpoint, 𝒙 Frequency, 𝒇 𝒇𝒙 𝒙𝟐 𝒇𝒙𝟐 (𝒇𝒙)𝟐


0 – 0.25 0.125 3 0.375 0.016 0.048 0.141
0.25 – 0.50 0.375 3 1.125 0.141 0.423 1.266
0.50 – 0.75 0.625 12 7.500 0.391 4.692 56.250
0.75 – 1.00 0.875 16 14.000 0.766 12.256 196.000
1.00 – 1.25 1.125 15 16.875 1.270 19.050 284.766
1.25 – 1.50 1.375 14 19.250 1.891 26.474 370.563
1.50 – 1.75 1.625 13 21.125 2.641 34.330 446.266
1.75 – 2.00 1.875 13 24.375 3.516 45.708 594.141
2.00 – 2.25 2.125 12 25.500 4.516 54.192 650.250
2.25 – 2.50 2.375 9 21.375 5.641 50.769 456.891
2.50 – 2.75 2.625 9 23.625 6.891 62.019 558.141
2.75 – 3.00 2.875 8 23.000 8.266 66.128 529.000
∑ Total 18 127 198.125 35.946 376.089 4143.675

Midpoint, Frequency, Cumulative Cumulative percentage


Time class
𝒙 𝒇 frequency of frequency (%)
0 – 0.25 0.125 3 3 2.36
0.25 – 0.50 0.375 3 6 4.72
0.50 – 0.75 0.625 12 18 14.17
0.75 – 1.00 0.875 16 34 26.77
1.00 – 1.25 1.125 15 49 38.58
1.25 – 1.50 1.375 14 63 49.61
1.50 – 1.75 1.625 13 76 59.84
1.75 – 2.00 1.875 13 89 70.07
2.00 – 2.25 2.125 12 101 79.53
2.25 – 2.50 2.375 9 110 86.61
2.50 – 2.75 2.625 9 119 93.70
2.75 – 3.00 2.875 8 127 100

12
Cumulative percentage of frequency (%) against midpoint
120
Cumulative percentage of frequency (%)

100

80

60

40

20

0
0 0.5 1 1.5 2 2.5 3 3.5
Midpoint

Graph 4.1(b): Cumulative percentage of frequency against midpoint

Mean:

∑ 𝑓𝑥 198.125
𝜇= = = 1.56
𝑛 127

Median:

1
× 127 = 63.5
2

∴ 𝐶𝑙𝑎𝑠𝑠 𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙 = 1.25 − 1.50

Mode:

𝐿𝑚 = 0.70

𝑑1 = 3

𝑑2 = 0

𝑑1
𝐿𝑚 + ( ) 𝑐 = 6.7
𝑑1 + 𝑑2

13
Variance:

(∑ 𝑓𝑥)2 4143.675
∑ 𝑓𝑥 2 − (376.089 − 127 )
∑𝑓
𝑠2 = = = 2.73
(∑ 𝑓) − 1 127 − 1

Standard deviation:

(∑ 𝑓𝑥)2
∑ 𝑓𝑥 2 −
√ ∑𝑓
𝑠= = √2.73 = 1.65
(∑ 𝑓) − 1

14
4.2 Probability

Frequency,
Time class Probability
𝒇
0 – 0.25 17 0.137
0.25 – 0.50 7 0.056
0.50 – 0.75 6 0.048
0.75 – 1.00 5 0.040
1.00 – 1.25 9 0.073
1.25 – 1.50 12 0.097
1.50 – 1.75 12 0.097
1.75 – 2.00 12 0.097
2.00 – 2.25 11 0.089
2.25 – 2.50 11 0.089
2.50 – 2.75 11 0.089
2.75 – 3.00 11 0.089
∑ Total 124 1.0

Frequency,
Time class Probability
𝒇
0 – 0.25 3 0.024
0.25 – 0.50 3 0.024
0.50 – 0.75 12 0.094
0.75 – 1.00 16 0.126
1.00 – 1.25 15 0.118
1.25 – 1.50 14 0.110
1.50 – 1.75 13 0.102
1.75 – 2.00 13 0.102
2.00 – 2.25 12 0.094
2.25 – 2.50 9 0.071
2.50 – 2.75 9 0.071
2.75 – 3.00 8 0.063
∑ Total 127 1.0

15
4.2.1 Probability Distribution Function

From table 1.0 :

P(𝑥 < 5 ) = 0

P(5) = P(𝑥 ≤ 5 ) = 0.040

P(6) = P(𝑥 ≤ 6 ) = 0.048 + 0.040 = 0.088

P(7) = P(𝑥 ≤ 7 ) = 0.088 + 0.056 = 0.144

P(9) = P(𝑥 ≤ 9 ) = 0.144 + 0.073 = 0.217

P(11) = P(𝑥 ≤ 11 ) = 0.217 + 0.089(4) = 0.573

P(12) = P(𝑥 ≤ 12 ) = 0.573 + 0.097(3) = 0.864

P(17) = P(𝑥 ≤ 17 ) = 0.864 + 0.137 = 1.0

Therefore, the cumulative distribution function of table 1.0 is :

F(𝑥) = 0, 𝑥<5

0.040, 5 ≤ 𝑥 < 6

0.088, 6 ≤ 𝑥 < 7

0.144, 7 ≤ 𝑥 < 9

0.217, 9 ≤ 𝑥 < 11

0.573, 11 ≤ 𝑥 < 12

0.864, 12 ≤ 𝑥 < 17

1.0, 𝑥 ≥ 17

16
From table 2.0 :

P(𝑥 < 3 ) = 0

P(3) = P(𝑥 ≤ 3 ) = 0.024(2) = 0.048

P(8) = P(𝑥 ≤ 8 ) = 0.048 + 0.063 = 0.111

P(9) = P(𝑥 ≤ 9 ) = 0.111 + 0.071(2) = 0.253

P(12) = P(𝑥 ≤ 12 ) = 0.253 + 0.094(2) = 0.441

P(13) = P(𝑥 ≤ 13 ) = 0.441 + 0.102(2) = 0.645

P(14) = P(𝑥 ≤ 14 ) = 0.645 + 0.110 = 0.755

P(15) = P(𝑥 ≤ 15 ) = 0.755 + 0.118 = 0.873

P(16) = P(𝑥 ≤ 16 ) = 0.873 + 0.126 = 1.0

Therefore, the cumulative distribution function of table 2.0 is :

F(𝑥) = 0, 𝑥<3

0.048, 3 ≤ 𝑥 < 8

0.111, 8 ≤ 𝑥 < 9

0.253, 9 ≤ 𝑥 < 12

0.441, 12 ≤ 𝑥 < 13

0.645, 13 ≤ 𝑥 < 14

0.755, 14 ≤ 𝑥 < 15

0.873, 15 ≤ 𝑥 < 16

1.0, 𝑥 ≥ 16

17
4.2.2 Special Probability Distribution

By using Binomial:

From the data that we have collected, there is a total 40 numbers of cars that commit parking
violation at G3 in the 2 days of observation. 17 cars in day 1 and 23 cars in the following next
day. We also find out that 41.18% cars in day and 34.78% cars in day 2 are the number of
cars that illegally parking which from the food vendors/restaurant staffs. Thus, the mean,
variance and standard deviation of the cars that illegally parking at UTHM, G3 lecture
complex from the food vendors/restaurant staffs at day 1 and day 2 is calculated respectively
by using binomial distribution.

Day 1 :

𝑛 = 17, 𝑝 = 0.412

 X ~ B(17, 0.412)

E(X) = 𝑛𝑝 = 17(0.412) = 7.004

Var(X) = 𝑛𝑝( 1 – 𝑝 ) = 7.004( 1 – 0.412 ) = 4.118

Std (X)= √𝑛𝑝( 1 – 𝑝 )𝑛𝑝( 1 – 𝑝 ) = √4.118 = 2.029

Day 2 :

𝑛 = 23, 𝑝 = 0.348

 X ~ B(23, 0.348)

E(X) = 𝑛𝑝 = 23(0.348) = 8.004

Var(X) = 𝑛𝑝( 1 – 𝑝 ) = 8.004( 1 – 0.348 ) = 5.219

Std (X)= √𝑛𝑝( 1 – 𝑝 )𝑛𝑝( 1 – 𝑝 ) = √5.219 = 2.285

18
Central limit theorem

Frequency, Probability 𝒙. 𝑷(𝒙) 𝒙𝟐 𝒙𝟐 . 𝑷(𝒙)


Day Time class
𝒙 P(x)
0 – 0.25 17 0.068 1.156 289 19.652
0.25 – 0.50 7 0.028 0.196 49 1.372
0.50 – 0.75 6 0.024 0.144 36 0.864
0.75 – 1.00 5 0.020 0.1 25 0.5
1.00 – 1.25 9 0.036 0.324 81 2.916
1.25 – 1.50 12 0.048 0.576 144 6.912
Day 1
1.50 – 1.75 12 0.048 0.576 144 6.912
1.75 – 2.00 12 0.048 0.576 144 6.912
2.00 – 2.25 11 0.044 0.484 121 5.324
2.25 – 2.50 11 0.044 0.484 121 5.324
2.50 – 2.75 11 0.044 0.484 121 5.324
2.75 – 3.00 11 0.044 0.484 121 5.324
0 – 0.25 3 0.012 0.036 9 0.108
0.25 – 0.50 3 0.012 0.036 9 0.108
0.50 – 0.75 12 0.048 0.576 144 6.912
0.75 – 1.00 16 0.064 1.024 256 16.384
1.00 – 1.25 15 0.060 0.9 225 13.5
1.25 – 1.50 14 0.056 0.784 196 10.976
Day 2
1.50 – 1.75 13 0.052 0.676 169 8.788
1.75 – 2.00 13 0.052 0.676 169 8.788
2.00 – 2.25 12 0.048 0.576 144 6.912
2.25 – 2.50 9 0.036 0.324 81 2.916
2.50 – 2.75 9 0.036 0.324 81 2.916
2.75 – 3.00 8 0.032 0.256 64 2.048
∑ Total 251 1.0 11.772 2943 147.692

𝜇 = (𝑋) = ∑ 𝑥.(𝑋) = 11.772

(𝑥 2 ) = ∑x 2 . P(x) = 147.692

𝜎 = 𝑆𝑡𝑑 𝑋 = √𝐸 (𝑥 2 ) − [E(x)]2 = √147.692 − 11.7722 = 3.019

19
Using the central limit theorem, we can say that the sampling distribution of 𝑋̅ is
approximately normally distributed. Thus, to find the average of parking violation at G3
parking lot which is less than 12 of n = 40.

P (𝑋̅ < 12) = P (Z < z)

12 −11.772
z= 3.019 = 0.48
( )
√40

P (𝑋̅ < 12) = P (Z < 0.48)


0 0.48
P (Z < 0.48) = 0.6844

20
Day 1:

Time Numbers of car XY X² Y²


(minutes) parking
X violation, Y
15 17 255 225 289
30 7 210 900 49
45 6 270 2025 36
60 5 300 3600 25
75 9 675 5625 81
90 12 1080 8100 144
105 12 1260 11025 144
120 12 1440 14400 144
135 11 1485 18225 121
150 11 1650 22500 121
165 11 1815 27225 121
180 11 1980 32400 121
∑ Total
1170 124 12420 146250 1396

𝑛 (∑𝑋𝑌)−(∑𝑋)(∑𝑌)
r=
√[ 𝑛(∑𝑋 2 )−(∑𝑋)2 ][ 𝑛(∑𝑌 2 )−(∑𝑌)2 ]

17 (12420)−(1170)(124)
=
√[ 17(146250)−(1170)2 ][ 17(1396)−(124)2 ]

= 0.684

The value of 𝑟 = 0.684 is fairly close to 1.00, so we can conclude that there is a strong
positive relationship between time and car parking violation. An increase in time will most
likely result in an increase in car parking violation. Thus, for R² = 0.468. This is a proportion
or a percent, so we can say that 46.8% of the variation in the number of car parking violation
is explained by the variation in the number of times of observation/data collection.
21
graph of car parking violation against time
18 17

16

14
12 12 12 R² = 0.0295
12 11 11 11 11

10 9

8 7
6
6 5

0
0 20 40 60 80 100 120 140 160 180 200
time against car parking violation

Day 2:

Time Numbers of car XY X² Y²


(minutes) parking
X violation, Y
15 3 45 225 9
30 3 90 900 9
45 12 540 2025 144
60 16 960 3600 256
75 15 1125 5625 225
90 14 1260 8100 196
105 13 1365 11025 169
120 13 1560 14400 169
135 12 1620 18225 144
150 9 1350 22500 81
165 9 1485 27225 81
180 8 1440 32400 64
∑ Total
1170 127 12840 146250 1547

22
𝑛 (∑𝑋𝑌)−(∑𝑋)(∑𝑌)
r=
√[ 𝑛(∑𝑋 2 )−(∑𝑋)2 ][ 𝑛(∑𝑌 2 )−(∑𝑌)2 ]

23 (12840)−(1170)(127)
=
√[ 23(146250)−(1170)2 ][ 23(1547)−(127)2 ]

= 0.745

The value of 𝑟 = 0.745 is fairly close to 1.00, so we can conclude that there is a strong
positive relationship between time and car parking violation. An increase in time will most
likely result in an increase in car parking violation. Thus, for R² = 0.555. This is a proportion
or a percent, so we can say that 55.5% of the variation in the number of car parking violation
is explained by the variation in the number of times of observation/data collection.

graph of car parking violation against time


18
16
16 15
14
14 13 13 R² = 0.0321
12 12
12

10 9 9
8
8

4 3 3

0
0 20 40 60 80 100 120 140 160 180 200
car parking violation against time

23
4.3 Inferential Statistics

4.3.1 F Distribution

Number of car
Time class
Day 1, 𝑿𝟏 (𝑿𝟏 − 𝑿̅ 𝟏 )𝟐 Day 2, 𝑿𝟐 (𝑿𝟐 − 𝑿̅ 𝟐 )𝟐
0 – 0.25 17 44.49 3 57.46
0.25 – 0.50 7 11.09 3 57.46
0.50 – 0.75 6 18.75 12 2.02
0.75 – 1.00 5 28.41 16 29.38
1.00 – 1.25 9 1.77 15 19.54
1.25 – 1.50 12 2.79 14 11.70
1.50 – 1.75 12 2.79 13 5.86
1.75 – 2.00 12 2.79 13 5.86
2.00 – 2.25 11 0.45 12 2.02
2.25 – 2.50 11 0.45 9 2.50
2.50 – 2.75 11 0.45 9 2.50
2.75 – 3.00 11 0.45 8 6.66
∑Total 124 114.68 127 202.96

Mean and variance for Day 1 and Day 2.

Day 1:

∑ 𝑋1 124
𝑋̅1 = = = 10.33
𝑛 12

(𝑋1 − 𝑋̅1 )2 114.68


𝑠1 2 = = = 10.43 (𝑑𝑒𝑛𝑜𝑚𝑖𝑛𝑎𝑡𝑜𝑟)
𝑛−1 12 − 1

Day 2:

∑ 𝑋2 127
𝑋̅2 = = = 10.58
𝑛 12

(𝑋2 − 𝑋̅2 )2 202.96


𝑠2 2 = = = 18.45 (𝑛𝑢𝑚𝑒𝑟𝑎𝑡𝑜𝑟)
𝑛−1 12 − 1

The significance level 𝛼 is 0.05.


Degrees of freedom in the numerator (𝑣1 ) is 12 − 1 = 11 and degrees of freedom in the
denominator (𝑣2 ) is 12 − 1 = 11. Since this is a two-tailed test, 𝛼/2 is 0.025.
Therefore, from the critical F table, the critical F-value is 3.43.

24
The rejection region:

0.25 0.25

3.43

𝑠2 2 18.45
𝐹= 2= = 1.77
𝑠1 10.43

Since the calculated F (1.77) is lower than the critical F (3.43) and do not falls in the
rejection region, we accept 𝐻0 . Therefore, we reject 𝐻𝑎 .

25
By using data analysis in Excel:

4.3.2 One-Way ANOVA Test

Number of car
Day 1, 𝑿𝟏 Day 2, 𝑿𝟐
17 3
7 3
6 12
5 16
9 15
12 14
12 13
12 13
11 12
11 9
11 9
11 8

The significance level 𝛼 is 0.05.

Degrees of freedom in the numerator (𝑣1 ) is 𝑘 − 1 = 2 − 1 = 1 and,

Degrees of freedom in the denominator (𝑣2 ) is 𝑛 − 𝑘 = 24 − 2 = 22.

The F distribution for this test is one-tailed, so use 𝛼 = 0.05.

Therefore, from the critical F table, the critical F-value is 4.30.

26
Number of car
Day 1 Day 2
𝟐
𝑿 𝑿 𝑿 𝑿𝟐
17 289 3 9
7 49 3 9
6 36 12 144
5 25 16 256
9 81 15 225 Total
12 144 14 196
12 144 13 169
12 144 13 169
11 121 12 144
11 121 9 81
11 121 9 81
11 121 8 64
𝑻𝒄 251
124 127
𝒏𝒄 24
12 1396 12 1547
𝑻𝒄 𝟐 /𝒏𝒄 2625.41
1281.33 1344.08
𝑿𝟐 2943

27
𝑀𝑆𝑇 𝑆𝑆𝑇/(𝑘 − 1)
𝐹= =
𝑀𝑆𝐸 𝑆𝑆𝐸/(𝑛 − 𝑘)

(∑ 𝑋)2
2
2512
𝑆𝑆 = ∑ 𝑋 − = 2943 − = 317.96
𝑛 24

𝑇𝑐 2 (∑ 𝑋)2 2512
𝑆𝑆𝑇 = ∑ ( ) − = 2625.41 − = 0.37
𝑛𝑐 𝑛 24

𝑆𝑆𝐸 = 𝑆𝑆 − 𝑆𝑆𝑇 = 317.96 − 0.37 = 317.56

0.37/(2 − 1)
𝐹= = 0.03
317.56/(24 − 2)

ANOVA Table
Source of Degrees of
Sum of Squares Mean Square F
Variation Freedom
Treatments 0.37 1 0.37 0.03
Error 317.56 22 14.43
Total 317.96 23

Since the calculated F (0.03) lower than the critical F (4.30), we accept 𝐻0 . Therefore we
reject 𝐻𝑎 .

By using data analysis in Excel;

28
4.4 Hypotesis Testing

Frequency Mean Variance


Day 2 127 1.56 2.73
Day 1 124 1.53 2.92

By using analysis data in excel:


z-Test: Two sample for Means

Wilcoxon Signed-Rank Test

Number of car
Day 1, 𝑿𝟏 Day 2, 𝑿𝟐
17 3
7 3
6 12
5 16
9 15
12 14
12 13
12 13
11 12
11 9
11 9
11 8

29
𝐻𝑜 = numbers of car parking violation during afternoon (Day1) and morning (Day2) are
equal.

𝐻𝑎 = numbers of car parking violation during afternoon (Day1) and morning (Day2) are not
equal.

The significance level is α = 0.05 and the test is two-tailed.

Decision rule: If the calculated Wilcoxon test statistic, 𝑊 is less than or equal to the critical
Wilcoxon value, 𝑊𝑐𝑟𝑖𝑡𝑖𝑐𝑎𝑙 ⟶ Reject 𝐻𝑜

𝑊𝑐𝑟𝑖𝑡𝑖𝑐𝑎𝑙 is obtained from the Wilcoxon Signed-Rank Test Table, while 𝑊 is determined as
follows:

Number of car Difference Absolute Rank Signed rank


Day 1, Day 2, difference (Ascending R+ R-
𝑿𝟏 𝑿𝟐 order)
17 3 14 14 7 7
7 3 4 4 4 4
6 12 -6 6 5 5
5 16 -11 11 6 6
9 15 -6 6 5 5
12 14 -2 2 2 2
12 13 -1 1 1 1
12 13 -1 1 1 1
11 12 -1 1 1 1
11 9 2 2 2 2
11 9 2 2 2 2
11 8 3 3 3 3
∑ Total 18 21

𝑊 is the smaller of the two rank sums R+ and R–

⟶𝑊 = 18

30
From the table, 𝑊 given significance level 𝛼 = 0.05 and number of pairs 𝑛 = 12

⟶ 𝑊𝑐𝑟𝑖𝑡𝑖𝑐𝑎𝑙 = 13

Since 𝑊 is larger than 𝑊𝑐𝑟𝑖𝑡𝑖𝑐𝑎𝑙 , we can reject 𝐻𝑎 . Thus we accept 𝐻𝑜 , which states that the
numbers of car parking violation during afternoon(Day1) and morning(Day2) are equal. We
have evidence to conclude that the numbers of car parking violation are similar during
afternoon(Day1) and morning(Day2).

4.5 Discussion

4.5.1 Result Presentation

Value
No Analysis 26 November 2019 27 November 2019
1 Mean, µ 1.53 1.56
2 Mode 3.28 6.70
3 Median 62.00 63.50
4 Standard Deviation 1.71 1.65
5 Variance 2.92 2.73

31
From the 2 days observation the result shows that a total of 40 cars parked illegally at
G3 complex with 41.18% and 34.78% of cars respectively. Based on the graph 4.1(a), the
ogive of the cumulative percentage of frequency is vigorously increased in between the
midpoint of 1.125 and keep on increasing until the midpoint of 2.875 that it can be considered
as a straight line. The graph of 4.1(b) shows that the cumulative percentage of frequency
form a slight curve at the midpoint of 1.875 and continue to form a straight line until the end
of the time class. Thus, from both graph it shows that the frequency of the time interval that
illegal cars parked at G3 lecture complex are different according to the days. The central limit
theorem shows that the sample distribution is approximately normally distributed with a
mean of 11.772 and standard deviation of 3.019. The F distribution calculation the result of
calculated F is 1.77 and the critical F is 3.43 which shows that the calculated F lower than the
critical F. Though, the result from data analysis in excel by using F-Test Two Sample for
Variances showed different values of calculated F and critical F which is 0.947 and 0.372
respectively. Lastly, to clearly testing our hypothesis we use Wilcoxon Signed Rank Test, the
result shows that the calculated W is 18 and the critical W from the table is 13. In conclusion,
the number of illegal cars parked at G3 lecture complex are similar during the 2 days of
observation.

32
CONCLUSION

In conclusion, the objectives of this case study are achieved in the study of the
numbers of parking violation at G3 lecture complex, the investigation of the correlation
between the numbers of parking violation and parking spaces available at G3 lecture
complex, and determine the parking spaces to accommodate users at G3 lecture complex.

The study of the numbers of parking violation at G3 lecture complex are obtained that
is 40 numbers of cars that violation the parking rule in interval of 15 minutes is determine as
251 total frequency of violation within the two days of 3 hours per day case study data
collection and observation. Secondly, for the next objective fulfillment, the inferential
statistics result shown that we accept 𝐻0 as we reject 𝐻𝑎 , therefore there is no correlation
between the numbers of parking spaces to accommodate users at G3 lecture complex. Lastly,
in determining the parking spaces to accommodate users at G3 lecture complex are in
accordance with the second objective hypothesis result where there is no correlation between
the numbers of parking spaces to accommodate users at G3 lecture complex, thus the
numbers of parking spaces are sufficient to fulfilled the requirement of the car park users at
G3 lecture complex. Therefore, in summary of the 2 days data collection and observation,
based on the data collection, the numbers of cars parking violation is higher on second days
of 27 November 2019 with 127 frequency of cars parking violation compare to the first day
of 26 November 2019 with 124 frequency. In addition, the cars parking violation at G3
lecture complex were mostly committed during early hours of the second day of observation,
8.30 AM while for the first day of observation, the cars parking violation is found mostly
during peak hours which is early hours of first day observation at 1.00 PM. This can be
concluded that the peak hours of the day affected the cars parking violation at G3 as the
activities and usage of the car park area is significant with early morning for the starting
period of activities of the day such as lecture class while the peak hours at noon is the lunch
hours where the small assumption of the G3 lecture complex car parking violation due to
customers to the G3 cafeteria.

33
Other than that, through utilizing the knowledge of the statistical theory that learned
during lecture throughout the study of the course BFC34303 : Civil engineering statistics, we
have applied the theoretical knowledge of statistical computation in the practical lesson of
case study in regards with the study of cars parking violation at G3 lecture complex.
Moreover, the application of statistical method namely descriptive statistics, estimation,
ANOVA table and hypothesis testing of the collected data, have tremendously challenges our
understanding of the statistical theoretical knowledge in ensuring a proper approach and
conduct is taken to compute the appropriate measure of data analysis.

34
REFERENCES

[1] Discount Park & Ride. (January 9, 2015). The Guide to Parking Lots. Retrieved from
https://discountparkandride.com/blog/guide-to-parking-lots/ at 10 December 2019.
[2] Haslinda.A. R.Ong. Rosmah.M. (2016). Factors Influencing Haphazard Parking in
The Klang Valley, Malaysia. International Journal of Academic Research in
Business and Social Sciences. Retrieved from
http://hrmars.com/hrmars_papers/Factors_Influencing_Haphazard_Parking_in_The_
Klang_Valley,_Malaysia.pdf at 10 December 2019.
[3] Civil engineering statistics lecture notes. (2019). Chapter 1 : Descriptive statistics.
Faculty of civil and environmental engineering. BFC 34303 Civil engineering
statistics. University tun Hussein onn Malaysia.

35
ATTACHMENTS

Attachment A & B : Collecting raw data of the parking violation at G3 lecture complex

Attachment C & D : Parking violation of cars that illegally parking at UTHM, G3 lecture
complex

36

You might also like