Академический Документы
Профессиональный Документы
Культура Документы
Number: 001350-0036
Candidate
Internal Assessment
May 2016
Mathematical Studies-Standard level
Topic title: Modeling the temperature for a week for various cities in the world.
Candidate
Acknowledgements
I would like to sincerely acknowledge:
Mrs. Angelin, my math teacher who guided me through the project and
research process.
My IB coordinator, Mrs. Vimala Rani Jacob for providing me with reviews on
my work.
Candidate
Table of contents:
No.
Topic
Page No.
1.
Acknowledgements
2.
Table of contents
3.
Introduction
4.
Collection of data
5.
6.
7.
8.
9.
10.
11.
12.
13.
Introduction:
Candidate
I have decided to do my project on the topic: modeling the temperature for seven different
cities. I have picked various cities across the globe for my statistical project randomly. I have
started recording the temperature of various cities at seven different points on the globe. I
chose this topic to check whether there is a model equation for the temperature changes
across the globe. It was interesting for me to find that all my graphs showed either a cubic or
quartic shape of the curve, which actually surprised me. I had done correlation and regression
to check the linearity of the equation but mostly it is not a positive one. So I had tried doing
CUBIC regression for my curve of best fit. Then to check if the population between the
temperatures were equal or not I have carried out the one-way anova if it is used to figure out
if there are any noteworthy contrasts between the means for three or more independent
groups. Consequently, the hypothesis is accepted, which expresses that the population means
are all equivalent. There was not much contrast in the means for the temperatures. If there is
an equation found like this then I think the future predictions of climate shift can be found
well in advance.
I am going to collect temperatures of seven different cities from different time zones. I
proceeded with my project work through the below stages:
STAGE 1:
Mathematics Studies SL-May 2016
Candidate
In the first stage of my project I have recorded the temperature of various cities daily,
calculated in Celsius. While choosing the different cities I had taken consideration of the
different time zones and picked cities from different time zones. I have accumulated the data
from http://www.timeanddate.com/weather/.
STAGE 2:
In the second stage of my project from the data I have accumulated I have done 2DIMENSIONAL line scatter graph for each city to know the type of graph and to study and
understand the concavity of the lines in the 2-D line scatter graph.
STAGE 3:
In the third stage of my project I have copied the accumulated data into a new excel sheet,
then I had used the function (=CORREL) to find the correlation for two consecutive days
until I had done it for seven days. This process had been done for all the seven cities that I
have chosen in my statistical project.
STAGE 4:
In the fourth stage of my project I have named each day starting from Saturday(X1) to the
next Saturday(X8) respectively. Then I calculated the mean for X1, X2 and the highest
CORREL for the set of data for every city that I have chosen.
STAGE 5:
Table 1: The first table contains the temperature of Kuala Lumpur recorded for a week.
Candidate
Then a scatter graph for each day comparing with Saturday of the data below has been plotted
to analyze whether it follows linear or cubic regression analysis.
Kuala
Lumpur
Saturd
ay
Sunda
y
27
27
26
26
26
26
26
26
26
27
28
30
31
33
34
34
34
26
24
25
25
26
26
26
26
26
26
26
26
26
25
25
26
27
30
31
33
34
35
35
31
30
30
29
29
29
28
28
Mond
ay
27
27
26
26
26
26
26
26
27
28
30
30
31
30
32
31
27
27
27
27
26
26
26
26
Tuesd
ay
26
26
26
26
25
25
25
25
25
27
29
31
32
33
34
33
32
30
29
27
27
27
27
27
Wednesd
ay
Thursd
ay
27
27
27
26
26
26
26
26
26
28
30
31
33
34
34
30
29
29
29
29
28
28
28
28
28
28
27
27
27
27
27
27
27
27
28
30
28
30
31
32
33
32
31
31
30
30
29
28
Friday
28
27
27
26
26
25
25
25
26
28
31
32
33
34
34
34
33
33
32
31
30
30
29
29
Saturd
ay
29
29
28
28
28
27
27
27
26
27
29
31
32
33
33
32
28
28
29
28
28
28
27
27
Candidate
Kuala Lumpur
40
30
20
10
0
22
24
26
28
30
32
34
Sunday
Polynomial (Sunday)
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
36
The above graph even though shows a pattern of cubic regression its not so clear. So,
Separate scatter graphs of each day compared with Saturday has been plotted below:-
Kuala Lumpur-Saturday-Sunday
Sunday
40
35
30
25
20
15
10
5
0
22
24
26
28
30
Saturday
32
34
36
Candidate
Kuala Lumpur-Saturday-Monday
40
30
Monday
20
10
0
22
24
26
28
30
32
34
36
Saturday
Monday
Polynomial (Monday)
Kuala Lumpur-Saturday-Tuesday
40
30
Tuesday
20
10
0
22
24
26
28
30
32
Saturday
Tuesday
Polynomial (Tuesday)
34
36
Candidate
Kuala Lumpur-Saturday-Wednesday
40
30
Wednesday
20
10
0
22
24
26
28
30
32
34
36
Saturday
Wednesday
Polynomial (Wednesday)
Thursday
20
10
0
22
24
26
28
30
32
Saturday
Thursday
Polynomial (Thursday)
34
36
Candidate
Kuala Lumpur-Saturday-Friday
40
30
Friday
20
10
0
22
24
26
28
30
32
34
36
Saturday
Friday
Polynomial (Friday)
Each graph above shows a clear cubic regression equation as a best fit for the data.
Candidate
When an online calculator is used to check whether the graph values plotted above are correct
or not. It gave the same perfect value.
TABLE2:
The table 2 contains the temperatures recorded for a week in Amsterdam. The
R2
values
of each of the graph is also showing positive correlation .Now, to check whether the same
happens to other countries, some random graphs had been plotted below.
Saturd
ay
Amsterda
m
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
12
13
13
13
13
Sunday
10
11
10
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
11
10
10
10
10
10
10
Monda
y
8
8
8
8
7
7
6
6
6
4
4
4
3
4
5
7
8
8
9
10
10
9
11
11
12
Tuesda
y
3
3
3
2
2
2
1
1
1
1
1
2
3
4
4
4
5
5
5
7
8
8
9
10
11
Wednesda
y
Thursda
y
5
4
5
5
5
5
5
4
4
4
4
4
4
5
5
5
6
7
8
9
10
11
10
11
10
5
5
5
4
4
5
5
5
7
7
7
7
6
6
7
8
9
9
10
10
11
9
12
12
12
Friday
6
7
7
7
6
7
7
7
6
6
7
5
5
6
7
8
8
9
9
9
10
10
10
11
10
Saturd
ay
7
6
6
5
5
5
5
4
4
4
3
4
4
4
5
5
7
9
8
9
10
11
11
12
12
10
10
11
10
10
10
10
10
10
10
10
10
10
10
9
9
9
9
9
9
10
12
12
13
11
12
11
11
11
10
11
10
9
9
8
7
7
6
6
5
Candidate
11
11
11
9
9
10
10
11
11
10
11
10
10
10
9
9
8
7
7
7
11
11
11
11
9
9
10
11
11
10
11
10
10
10
9
9
8
7
7
7
12
13
13
12
13
13
14
13
13
12
12
12
12
11
10
9
8
8
7
7
11
12
11
12
11
12
12
12
11
11
12
11
10
11
10
9
8
8
8
8
11
13
13
14
13
14
14
14
14
13
13
12
13
13
12
12
11
11
10
11
Amsterdam-Saturday-Sunday
15
10
Sunday
5
0
10
11
12
13
14
Saturday
Sunday
Polynomial (Sunday)
15
16
Candidate
Amsterdam-Saturday-Tuesday
15
10
Tuesday
5
0
10
11
12
13
14
15
16
Saturday
Tuesday
Polynomial (Tuesday)
Amsterdam-Saturday-Wednesday
15
10
Sunday
5
0
10
11
12
13
14
15
16
Saturday
Wednesday
Polynomial (Wednesday)
It is very clear that it follows a cubic regression equation with moderate positive correlation.
TABLE3:
The table 3 contains the temperatures recorded for a week in London.
Saturd
ay
Londo
n
11
11
Sunda
y
Monda
y
Tuesda
y
11
10
6
5
6
5
Wednesd
ay
7
7
Thursda
y
5
5
Frida
y
7
6
Saturda
y
7
5
9
9
8
8
7
7
8
9
9
10
10
10
10
11
11
11
11
9
7
7
6
6
4
4
3
3
4
5
7
9
9
9
10
12
12
12
12
12
11
11
9
8
7
6
Candidate
4
4
3
3
4
5
7
9
9
11
12
12
12
13
12
12
11
10
9
9
8
8
7
7
7
7
8
9
9
11
9
10
9
11
12
13
14
13
12
11
9
8
7
6
5
5
4
4
6
7
9
11
11
12
14
14
13
13
13
13
12
12
10
10
8
7
6
6
6
6
6
7
8
9
10
11
12
12
12
12
12
11
11
10
9
9
8
7
London-Saturday-Sunday
15
10
Sundauy
5
0
10
11
12
13
14
15
16
Saturday
Sunday
Polynomial (Sunday)
17
18
19
5
6
6
6
6
7
8
9
10
12
13
14
14
13
13
12
11
11
10
9
9
8
Candidate
London-Saturday-Wednesday
15
f(x) = 0.04x^3 - 1.66x^2 + 24.99x - 116.31
R = 0.76
10
Wednesday
5
0
10
11
12
13
14
15
16
17
18
19
18
19
Saturday
Wednesday
Polynomial (Wednesday)
London-Saturday-Thursday
15
f(x) = 0.06x^3 - 2.86x^2 + 45.5x - 228.83
R = 0.93
10
Thursday
5
0
10
11
12
13
14
15
16
17
Saturday
Thursday
Polynomial (Thursday)
Even in this case the equation is a cubic one but there is a slight decrease in the value of co
efficient of determination which says that it has a very moderate positive correlation.
TABLE4:
The table 4 contains the temperatures recorded for a week in Madrid.
Saturd
ay
Madri
d
16
16
15
17
21
23
Sunda
y
Monda
y
Tuesda
y
15
13
13
16
19
22
14
14
13
18
21
23
16
16
16
18
23
23
Wednesd
ay
19
17
17
18
21
24
Thursd
ay
17
17
16
18
20
24
Saturd
Friday ay
18
16
14
18
22
23
17
17
15
18
21
22
21
16
Candidate
20
17
23
20
22
19
22
18
18
17
Madrid-Saturday-Sunday
40
Sunday 20
0
14
22
23
24
22
23
24
22
23
24
Saturday
Sunday
Polynomial (Sunday)
Madrid-Saturday-Tuesday
40
Tuesday 20
0
14
Saturday
Tuesday
Polynomial (Tuesday)
Madrid-Saturday-Thursday
40
Thursday 20
0
14
16
17
18
19
20
21
Saturday
Thursday
Polynomial (Thursday)
21
20
Candidate
Here again, Madrid is having a strong positive correlation but following the same cubic
regression .
Table 5:
The table 5 contains the temperatures recorded for a week in Melbourne.
Saturd
ay
Melbourn
e
13
13
13
13
13
12
Sunda
y
11
11
11
11
11
10
Monda
y
Tuesda
y
Wednesda
y
Thursda
y
10
10
10
10
10
10
10
10
10
10
10
9
8
7
7
8
9
9
8
8
7
7
8
6
Friday
8
8
8
8
8
8
Saturd
ay
13
13
13
13
16
14
10
10
10
10
10
9
9
10
10
10
10
10
11
11
12
12
13
12
13
15
14
15
14
14
14
13
13
13
12
12
12
11
11
11
11
11
10
10
10
10
10
10
10
10
10
10
10
10
10
10
11
11
11
13
13
14
14
14
14
14
14
14
14
14
14
14
14
13
13
13
13
12
12
11
10
11
11
11
11
11
Candidate
9
9
8
8
8
9
9
9
9
9
9
10
10
11
12
12
14
14
14
14
14
14
14
15
14
13
14
13
12
11
12
12
12
11
12
11
9
9
8
7
9
8
8
8
8
7
6
6
6
7
11
11
13
13
14
14
15
16
16
16
16
17
17
17
16
15
15
15
13
12
11
11
11
11
9
8
8
8
8
7
6
6
6
6
6
6
6
6
8
9
11
13
13
14
15
16
17
18
18
18
19
19
19
18
18
17
15
14
13
13
12
12
11
10
10
10
9
10
9
8
7
7
7
6
5
5
7
9
14
17
19
20
21
21
21
22
22
22
22
22
22
21
20
19
18
17
16
16
13
13
13
12
13
13
13
15
14
14
14
13
15
15
15
15
15
15
15
16
15
15
15
15
16
16
16
17
16
17
19
19
20
20
20
21
21
22
22
21
20
19
18
18
17
17
15
17
15
14
13
13
Candidate
Melbourne-Saturday-Sunday
20
15
f(x) = 0.08x^3 - 2.45x^2 + 26.41x - 86.23
R = 0.58
Sunday 10
5
0
9.5
10
10.5
11
11.5
12
12.5
13
13.5
14
14.5
14
14.5
14
14.5
Saturday
Sunday
Polynomial (Sunday)
Melbourne-Saturday-Monday
15
f(x) = 0.13x^3 - 4.38x^2 + 51.04x - 188.69
R = 0.31
10
Monday
5
0
9.5
10
10.5
11
11.5
12
12.5
13
13.5
Saturday
Monday
Polynomial (Monday)
Melbourne-Saturday-Wednesday
20
15
Wednesday 10
5
0
9.5
10
10.5
11
11.5
12
12.5
13
13.5
Saturday
Wednesday
Polynomial (Wednesday)
Candidate
Table 6:
The table 6 contains the temperatures recorded for a week in Bangalore.
Saturd
ay
Sunda
y
21
22
29
30
20
20
19
18
20
20
24
27
30
22
23
22
Bangal
ore
Mond
ay
Tuesd
ay
22
21
23
28
30
29
26
24
Wednesd
ay
23
23
24
28
31
30
27
25
Thursd
ay
24
23
25
29
32
25
24
22
21
21
24
29
32
22
21
21
Friday
21
20
24
30
33
31
27
25
Banglore-Saturday-Sunday
40
Sunday 20
0
16
18
20
22
24
26
28
30
32
30
32
Saturday
Sunday
Polynomial (Sunday)
Banglore-Saturday-Wednesday
40
f(x) = 0.07x^3 - 4.84x^2 + 110.41x - 802.38
R = 0.43
Wednesday 20
0
16
18
20
22
24
26
28
Saturday
Wednesday
Polynomial (Wednesday)
Saturd
ay
24
22
24
29
32
22
23
22
Candidate
Banglore-Saturday-Friday
40
f(x) = 0.1x^3 - 6.82x^2 + 151.03x - 1066.93
R = 0.5
Friday 20
0
16
18
20
22
24
26
28
Saturday
Friday
Polynomial (Friday)
30
32
Candidate
Table 7:
Saturd
ay
Beijin
g
14
12
19
26
31
30
26
24
Sunda
y
Monda
y
21
16
19
26
30
30
26
23
Tuesda
y
20
19
21
24
27
27
22
19
Wednesd
ay
17
17
19
22
23
25
22
18
Thursda
y
16
14
18
22
26
26
23
21
20
17
20
25
28
29
26
24
Frida
y
19
18
19
20
26
20
15
14
Beijing-Saturday-Sunday
40
30
Sunday 20
10
0
10
20
25
30
35
Saturday
Sunday
Polynomial (Sunday)
Beijing-Saturday-Monday
30
20
Monday
10
0
10
15
20
25
Saturday
Monday
Polynomial (Monday)
30
35
Saturda
y
15
14
18
22
23
23
21
19
Candidate
Beijing-Saturday-Friday
30
20
Friday 10
0
10
15
20
25
30
35
Saturday
Friday
Polynomial (Friday)
Since most of the scatter plots are following cubic equation as a best curve of fit. The next
step is to check whether the coefficients of the cubic regression equation found by the Excel
sheet is correct or not. So, Kuala Lumpurs data Saturday and Sunday has been chosen for
this calculation.
Grouping all the values of R 2 for Kuala Lumpur in a table
Sat- sun
Saturday
(x)
27
27
26
26
R = 0.7199
Sunday
(y)
26
26
26
26
Candidate
26
26
25
25
26
27
30
31
33
34
35
35
31
30
30
29
29
29
28
28
Substituting for
24
24
Substituting for
- Equation A
-Equation-1
27
27
Substituting for
-Equation- 2
31
31
Substituting for
Candidate
-Equation-3
33
33
-Equation-4
We get
by subtracting Equation1Equation 4
Candidate
We get
a=
11
277
2681
10182
b=
c=
d=
189
54
18
7
d=1454.57
Kuala Lumpur
40
f(x) = - 0.05x^3 + 4.73x^2 - 138.31x + 1362.9
R = 0.72
30
Sunday 20
10
0
22
24
26
28
30
32
34
36
Saturday
To check more on the relationship between the temperature for the days of Kuala Lumpur.
Mann-Whitney U test: is conducted to check whether there is any significant difference in
their temperatures. Same data from Kuala Lumpur is taken to test this behavior.
Let the variables denote:
U=MannWhitney U variable .
Candidate
n1=Sample saturday .
n2=Sample sunday .
Ri=Rank of the sample
H o=There is significant differencetheir temperatures .
H 1=There isno signifcant differencetheir temperatures .
T x = Highest rank total.
N x =
The formula for Mann-Whitney U test is
n
n2 ( n2+1)
Ri
2
i=n +1
2
U=n1 n 2+
For the test first I ranked x and y into different columns without
considering the categories and then if multiple times it had the same
temperatures then I added the ranks and then divided it by the respected
number of ranks. Then I added up the ranks of x to get
up the ranks for y to get
it is
t2
t2
t1
then I added
after which I have used a table of critical U values for the Mann-
Saturday rank x
(x)
27
25.5
27
25.5
26
14.5
26
14.5
26
14.5
26
14.5
larger
Tx
26
14.5
rank26
14.5
Nx
26
14.5
27
25.5
28
29
30
32.5
31
36
33
38.5
34
41.5
34
41.5
34
41.5
26
14.5
24
1
25
3.5
25
3.5
26
14.5
26
14.5
26
14.5
t1
504.5
Sunday
rank y
(y)
26
14.5
26
14.5
26
14.5
26
14.5
26
14.5
26
14.5
626.5
25
3.5
25
3.5
24
26
14.5
27
25.5
30
32.5
31
36
33
38.5
34
41.5
35
44.5
35
44.5
31
36
30
32.5
30
32.5
29
32
29
32
29
32
28
29
28
29
t2
626.5
Candidate
25
626.5
2
U calculated =249.5
5 level of significance
U table value(24, 24)=201 )
U Calc <U Table
Therefore, we reject the null hypothesis and
accept that there is no significance difference
between the temperatures of the two days in
Kuala Lumpur.
One-way Anova: is used to determine whether there are any significant differences between
the means of three or more independent groups.
Defining the variables for One-way Anova:
H o : Sun =Sat =Mon= Tue=Wed =Thurs = Fri =Sat
Candidate
M =Number of columns .
K=Number of rows .
n=mk=columns rows .
K
U
A
L
A
Saturday
Sunday
Monday
Tuesday
27
26
27
26
27
26
27
26
26
26
26
26
26
26
26
26
26
26
26
25
26
26
26
25
26
25
26
25
26
25
26
25
26
26
27
25
27
27
28
27
28
30
30
29
30
31
30
31
31
33
31
32
33
34
30
33
34
35
32
34
34
35
31
33
34
31
27
32
26
30
27
30
24
30
27
29
L
U
M
P
Candidate
Wednesday
27
27
27
26
26
26
26
26
26
28
30
31
33
34
34
30
29
29
29
Thursday
Friday
Saturday
28
28
29
28
27
29
27
27
28
27
26
28
27
26
28
27
25
27
27
25
27
27
25
27
27
26
26
27
28
27
28
31
29
30
32
31
28
33
32
30
34
33
31
34
33
32
34
32
33
33
28
32
33
28
31
32
29
67
6
67
6
67
6
62
5
67
6
72
9
67
6
78
4
67
6
67
6
67
6
62
5
67
6
72
9
62
5
72
9
TAB
LE
OF
TH
E
SU
M
OF
SQ
UA
RE
S
Saturday
K Sunday
U
A Monday
L
A Tuesday
Wednesd
L ay
U
M Thursday
P
U Friday
R
Saturday
72
9
67
6
72
9
67
6
72
9
78
4
78
4
84
1
72
9
67
6
72
9
67
6
72
9
78
4
72
9
84
1
67
6
67
6
67
6
67
6
72
9
72
9
72
9
78
4
67
6
67
6
67
6
67
6
67
6
72
9
67
6
78
4
67
6
62
5
67
6
62
5
67
6
72
9
62
5
72
9
67
6
62
5
67
6
62
5
67
6
72
9
62
5
72
9
67
6
67
6
72
9
62
5
67
6
72
9
67
6
67
6
72
9
72
9
78
4
72
9
78
4
72
9
78
4
72
9
78
4
90
0
90
0
84
1
90
0
78
4
96
1
84
1
900
961
900
961
961
900
102
4
961
961
108
9
108
9
115
6
961
102
4
108
9
900
108
9
115
6
115
6
122
5
102
4
115
6
115
6
784
108
9
102
4
900
115
6
108
9
961
115
6
108
9
115
6
122
5
961
108
9
900
102
4
115
6
102
4
Candidate
The table below denotes the number of rows and columns of the data above.
M
K
N
24
8
19
2
N=M K
SS T =1570825468 5468 192=1358
Source of
variation
Degrees of
freedom (df)
Between
temperatures
K 1
SS B
Within
temperatures
N K
SS W
Total
N 1
SS T
Source of variation
Between Groups
Within Groups
Total
Df
7
18
4
19
1
Sum of
squares (SS)
SS
73.3333333
3
1284.58333
3
1357.91666
7
Mean of
Squares
(MSS)
SS B
(K1)
SS W
(NK )
MS
S
Ratio
1.50057921
10.5
3
6.98
73.33
=10.5
7
F-ratio
SS B /(K 1)
SSW /( N K)
FRatio=
Candidate
1284.583
=6.98
184
10.5
=1.500579213
6.98
CONCLUSIONS:
Therefore as most of the scatter plots follow the cubic regression equation as a best curve of
fit I did a physical calculation by taking the points which fall on the curve and the ultimate
answer matched that of a scatter plot. In order to check their relationship and the strength of it
Mann Whitney U test was conducted and results were calculated. I rejected the null
hypothesis and accept alternate hypothesis which states that there is not any significance
difference amid the temperatures of the first two days in Kuala Lumpur. Then to check the
above test result , One-way Anova was done in which the null hypothesis is not rejected
which shows that the population means remain all equal at most of the time( even between
the days ) as there remained a very slight change in the means of the temperatures.