A Research related to Youth Crimes in Kuwait during 2010 - 2014 إحصائية متعلقة بجرائم القاصرين في الكويت
Hey guys! This is my (our) research for an industrial engineering class called Probability and Statistic in Engineering II - IE330 - American University of the Middle East (AUM). It was interesting and hard to do it. We had to translate the data from Arabic to English. The problem was that the data was huge! so we had to simplify it by making it more "general".
The research was done by
1) Shouq (Me)
2) Fatemah AlMeshal
3) Want to remain anonymous
You can see the data here
Note:
My professor thinks that
1) the inferential statistic is not "logical"
2) the conclusion is not "good enough"
So keep that in consideration if you are using this as a model for your statistic2 research.
The research was done by
1) Shouq (Me)
2) Fatemah AlMeshal
3) Want to remain anonymous
You can see the data here
Abstract
The aim for this report and data is to investigate the trends of
youth crimes and the differences in crime between Kuwaitis and non-Kuwaitis
throughout 2010 until 2014. The reason why we want to investigate about youth
crimes is to know what are the most common crimes out there and try to find a way
to prevent it by raising awareness about the danger of crime and how it’s
affecting people’s life.
The pie chart above shows us that the numbers and percentages of crimes done by Kuwaiti
and Non-Kuwait youngster, as you can see, are almost exactly the same. The
percentage of Kuwaiti youngster crimes is 49.4% which is equal to 2119 crimes
throughout the years 2010 until 2014. On the other hand, the percentage of
None-Kuwaiti youngster crimes is 50.6% which is 2167 crimes. We can notice that
the number and percentage of None-Kuwaiti is slightly a bit high than Kuwaitis.
From the bar chart above, we will know the
number of crimes throughout the years from 2010 until 2014. The highest
majority of crimes happened in 2010, while the lowest number of crimes that are
done by Kuwaiti and Non-Kuwaiti youngsters was in 2011. After 2010, the highest
number of crimes, in 2011 the number of crimes decreased drastically. The years
after that, eventually, the number of crimes started increasing until it reached
the second highest amount of crimes in 2014.
Inferential statistics:
We can only use proportion for our data to
see how the problems increased and decreased through the years. What we are using
are categorical data, not numerical data, and that is the reason why we can
only use proportion and not any other method. In the following MiniTabe results,
we will be finding the result for two crime cases: crimes related to driving and Violation.
P1 = crimes
related to driving (2010+2011).
P2 = crimes
related to driving (2013+2014).
H0: P1 - P2 = 0 (There is no
difference between the number of crimes related to driving in 2010 and 2011, and the number of crimes related to driving in 2013 and 2014)
H1: P1-P2 > 0 the crimes in (2010+2011) are higher than the number of crimes in (2013+2014).
H1: P1-P2 > 0 the crimes in (2010+2011) are higher than the number of crimes in (2013+2014).
Sample X N
Sample p
1 274 5364
0.051081
2 42 5364
0.007830
Difference = p (1) - p (2)
Estimate for difference:
0.0432513
95% lower bound for difference:
0.0379252
Test for difference = 0 (vs > 0): Z = 13.36
P-Value = 0.000
By comparing
p-value with α = 0.05, we found that α which is equal to 0.05 is greater that
the p-value which equals 0.00, so we have to reject H0.
P-value < α
P-value < α
0.000 < 0.05
; reject H0
Conclusion: The crimes related to driving are increasing in
(2010+2011), However it is decreasing in (2013+2014). From the study above, we
realize that some changes have been done to laws related to, and this have
caused some improvement in the crimes related to the last two years compared to
the first two years (2010+2011). All of that have reduced the number of
problems happening.
P1 = Violation in (2010+2011).
P2 = Violation in (2013+2014).
H0: p1 - p2 = 0 (There is no
difference in violation in 2010 and 2011, and violation in 2013 and 2014.)
H1: p1 - p2 < 0 (violation in 2010 and 2011 is less than violation in 2013 and 2014)
H1: p1 - p2 < 0 (violation in 2010 and 2011 is less than violation in 2013 and 2014)
Sample X N
Sample p
1 94 5364
0.017524
2 233 5521
0.042202
Difference = p (1) - p (2)
Estimate for difference:
-0.0246783
95% upper bound for difference:
-0.0193404
Test for difference = 0 (vs < 0): Z = -7.60
P-Value = 0.000
By comparing
p-value with α = 0.05, we found that α which is equal to 0.05 is greater that
the p-value which equals 0.00, so we have to reject H0.
P-value < α
P-value < α
0.000 < 0.05
; reject H0
Conclusion: We can obtain that there was lower number of violation in
(2010+2011), while it is increasing in (2013+2014). In addition to that, we realized
that the number of law violation is increasing throughout the years, because
there is no improvement in laws. If there were more strict laws, it may stop
and prevent people from breaking the law. The government has to make some
changes on the rules to make the country safer, by finding different ways to
decrease the number of crimes happening all around the country.
In conclusion we
did a research and collected the data about Kuwaiti
and Non-Kuwaiti youngster people to know
the most common crime that our society face in last few years. In addition;
we noticed that "attacking / helping to escape" was the highest crime
in Kuwait which was 40.4 % of youngest people, and the second highest crime was
"related to stealing" and was 31.8%. Therefore; we collected this
data to deal with the problem and find solutions for this disaster, because for every problem there is a solution.
resource(s):
My professor thinks that
1) the inferential statistic is not "logical"
2) the conclusion is not "good enough"