1: Introduction: The data provided to me is the data taken from 50 people and the data is the

Annual Greenhouse Gas Emissions and Population for 10 Large Nations. The data set represents
the Annual greenhouse gas emissions (Total Greenhouse Gas Emissions (kt of CO2 equiv /
100,000) and population (Population / 10,000,000) for 10 nations for years 1970-1974.Nations:
Brazil, Canada, China, Germany, France, UK, India, Japan, Mexico, US. Both variables are
continuous variables as they are infinite number of values and their data is in decimals.

2: Methodology:
A: No of Classes: 2k>n
2k>50
26>50
K=6
No of classes (For both the variables) = 6
Finding class interval: h= highest value – lowest value
k
For Data A: 59.13- 2.11 For Data B: 90.04 – 2.13
6 6
For A Class interval= 10 For Data B Class interval=15

1, Frequency Distribution

For Data A for Data B

Class Midpoint(x) Class Midpoint(x)

Intervals Frequency(F) Intervals Frequency(F)
2-12 7 35 2-16 9 35
13-23 18 9 17-31 24 5
24-34 29 0 32-46 39 0
35-45 40 0 47-61 54 0
46-56 51 2 62-76 69 5
57-67 62 4 77-91 84 5
∑F= 50 ∑F= 50
 Frequency(F)
Frequency(F) 40
40
35
35
30
30
25
25
20
20
15
15
10 10

5 5
0 0
7 18 29 40 51 62 9 24 39 54 69 84

DATA A Data B

Interpretation: Both variables have slightly same graphs with some different variable A have
slightly tuff curve and variable b have slightly easy curve.
Key: The median is indicated with the blue line and the mode is indicated with red line in both
graphs.

2: Measures of Central Tendency

Mean, median and Mode
For Data A

Class Freque Midpoints(x C.F Class limits X- F(X- (X- F(X-

Fx
Intervals ncy(F) ) mean mean) Mean) mean)22

2-12 35 7 245 35 1.5-12.5 8.14 284.9 66.25 2318.75

13-23 9 18 162 44 12.5-23.5 2.86 25.74 8.17 73.53
24-34 0 29 0 44 23.5-34.5 13.86 0 192.1 0
35-45 0 40 0 44 34.5-45.5 24.86 0 618 0
46-56 2 51 102 46 45.5-56.5 35.86 71.72 1285.1 2570.2
50 56.5-67.5 46.86 187.44 2195.8 8783.4
57-67 4 62 248 5
∑F(X- ∑F(X-
∑F mean)= mean)2=
∑X=207 ∑Fx= 757
= 50 569.8 13745.8
8

Mean= ∑Fx
∑F
Mean= 757/50 = 15.14
median= L + h/f n/2-c
Median class = n/2 = 50/2 = 25 (lies in 1st row (2-12)
Median= 1.5 + 11/35 25-35
Median=1.5+3.142
Median = 4.642
Mode= L + fm – f1 *h
(fm-f1) + fm-f2)-
Modal class = Highest frequency class =35= 2-12
Mode= 1.5 + 35-0 * 11
(35-0) + (35-44)
Mode=1.5 + 14.80
Mode= 16.307

The data is symmetrical as the mean is higher than the median which is less than the mode. I. e
(15.14<4.642<16.307)
Mean is the best appropriate measure for the central tendency as this data is continuous and
have no outliners. So, mean poses the best measure for central tendency.

Measures of Dispersion:
1:Range: largest value – lowest value
Range=59.13 -2.11
 Range=57.02
Coefficient of Range = L – S
L+S
Coefficient of range = 59.13- 2.11
59.13+2.11
Coefficient of range= 57.02
61.24
Coefficient of range = 0.931
Quartile deviation
Quartile Deviation = Q3 – Q1
2
Q3= L + h/f (3(n/4 – C)
Quartile class = n/4 = 50/4= 12.5 (lies in 2st class 13-23)
Q3= 12.5 + 11/9 (3(12.5-35)
Q3= 12.5 +1.22(37.5 -35)
Q3= 15.55
Q1= L + h/f (n/4- C)
Q1= 1.5 + 11/35(12.5-0)
Q1= 5.428
Quartile Deviation = Q3 – Q1
2
Q.D = 15.55 – 5.428
2

Q.D = 5.061
Coefficient of Quartile deviation: Q3-Q1
Q3+Q1

= 15.55-5.428
 15.55+5.428
= 10.122
20.978
=0.48
Mean Deviation (About mean) = ∑F(X-mean) = 569.8/50 = 11.396
∑F
Coefficient of Mean deviation= mean deviation = 11.396 = 0.752
Mean 15.14
Standard Deviation: Σ𝑓(𝑋-Mean)2 =√13745.88= 50.74 = 16.58
Σ𝑓 50
Coefficient of Variance= S/Mean * 100 = 16.58/15.14 * 100 = 109.51%

𝑠𝑘=𝑚𝑒𝑎𝑛−𝑚𝑜𝑑𝑒 = 15.14 – 16.307 = - 0.07

𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 16.58

The value of skewness indicates that the data is negatively skewed.

Standard deviation is best measure for dispersion for the data as it gives clear view
about the skewness of data.
Moments
X - Mean F(x-mean) F (X – Mean)2 F (X – Mean)3 F(X-Mean)4

-8.14 -284.9 2319.08 -18877.311 153661.31

-2.86 -25.74 73.61 -210.52 602.08
-13.86 0 0 0 0
24.86 0 0 0 0
35.86 25.72 2571.87 92227.25 3307269
46.86 287.44 8783.43 411591 19287154.26
∑F(X-mean) =2.26 ∑F(X- ∑F(X-mean)3= ∑F(X-mean)4=
mean)2=13747.91 -484730.419 22748686.39
M1=∑F(X-mean) = 2.2/50 = 0
∑F
M2=∑F(X-mean)2 = 13747.91/50 = 274.95
∑F
M3=∑F(X-mean)3 = 484730.419/50 = -9694.60
 ∑F
M4= ∑F(X-mean)4 = 22748686.39/50 = 454973.73
∑F

By calculating the first four moments about mean it shows that the data is
negatively skewed and the results coincide with the mean, median and mode
of the data.
𝑏 1 = 𝑚3 2 = - 9694.60 2= 93985269= 4.521

𝑚2 3 274.95 3 20785533.31

𝑏 2 = 𝑚4 = 454973.73 = 6.01

𝑚2 2 274.952

the distribution is said to be more peaked and the curve is leptokurtic as b2>3.

Data: B
Class Frequency(F MIDPONTS C. Class X- F(X-Mean) (X- F(X-Mean)2
Fx
Intervals ) X F limits Mean Mean)2
2-16 35 1.5- 12.24 428.4 149.817 5243.595
35
9 315 16.5
40 16.5- 2.76 13.8 7.6176 38.088
17-31 5
24 120 31.5
40 31.5- 17.76 0 315.41 0
32-46 0
39 0 46.5
40 46.5- 32.76 0 1073.21 0
47-61 0
54 0 61.5
45 61.5- 47.76 143.28 2281.01 6843
62-76 5
69 207 76.5
50 76.5- 62.76 313.8 3938 19690
77-91 5
84 420 91.5
∑F(X- ∑F(X-
2
∑F= 50 ∑Fx= mean)=899.2 mean) =31814.68
1062 8

Mean= ∑Fx
∑Fs
 Mean= 1062/50 = 21.24
Median class = n/2 = 50/2 = 25 (lies in 1st row (2-16)
Median= 1.5 + 14/35 (25-0)
Median=11.5
Mode= L + fm – f1 *h
(fm-f1) + fm-f2)
Modal class = Highest frequency class =35= 2-16

Mode= 1.5+ 35-0 * 14

(35-0) + (25-5)
Mode=1.5 + 8.90
Mode= 10.409
The data is skewed to the left as the mean is greater than the median which is greater than the
mode. I. e (21.24<11.5<10.409).
Mean is the best appropriate measure for the central tendency as this data is continuous and
have no outliners. So, mean poses the best measure for central tendency.

Measures of Dispersion:
Range: largest value – lowest value
Range:90.04-2.13
Range:87.91
Coefficient of Range = L – S
L+S
Coefficient of range = 90.04 – 2.13
90.04 + 2.13
Coefficient of range= 87.91
92.17
Coefficient of range = 0.953

Quartile Deviation = Q3 – Q1
 2
Q3= L + h/f (3(n/4 – C)
Quartile class = 3n/4 = 50/4= 37.5 (lies in 2nd class 17-31)
Q3= 16.5+ 14/5 (3(12.5-13)
Q3= 16.5 + 2.8(37.5 -35)
Q3= 23.5
Q1= L + h/f (n/4- C)
Q1= 1.5+ 14/35(12.5-0)
Q1= 6.5
Quartile Deviation = Q3 – Q1
2
Q.D = 23.5-6.5
2
Q.D = 8.5
Coefficient of Quartile deviation: Q3-Q1
Q3+Q1
Coefficient of Q.D = 23.5-6.5
23.5 + 6.5
Coefficient of Q. D= 0.566
Mean Deviation (About mean) = ∑F(X-mean) = 899.28/50 = 17.98
∑F
Coefficient of mean deviation: = mean deviation = 17.98 = 0.8465
Mean 21.24
Standard Deviation: Σ𝑓(𝑋-Mean)2 =√ 31814.68 = 25.21
Σ𝑓 50
Variance = S/Mean * 100 = 25.21/21.24 * 100 = 118.69

Skewness
 𝑠𝑘=𝑚𝑒𝑎𝑛−𝑚𝑜𝑑𝑒 = 21.24 – 10.409 = 0.429
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 25.21

The value of skewness indicates that the data is positively skewed

Standard deviation is best measure for dispersion for the data as it gives clear view
about the skewness of data.
Moments
X - Mean F(x-mean) F (X – Mean)2 F(X – Mean)3 F(X-Mean)4

-12.24 -428.4 5243.61 -64181.78 785575

-2.76 -138 380.88 -1051.8 2902.678
17.76 0 0 0 0
32.76 0 0 0 0
47.76 238.8 11405 544702 26014967
62.76 313.8 19684 1235367 77531632
∑F(X-mean) =-0 ∑F(X-mean)2=- ∑F(X-mean)3= ∑F(X-mean)4=
36713 -1714837.84 104335076

M1=∑F(X-mean) = -0/50 = 0
∑F
M2=∑F(X-mean)2 = 36713/50 = 734.26
∑F
M3=∑F(X-mean)3 = -1714837/50 = -34296
∑F
M4= ∑F(X-mean)4 = 104335076/50 = 2086701
∑F

By calculating the first four moments about mean it shows that the data is
negatively skewed, and the results coincide with the mean, median and mode of the
data.
𝑏 1 = 𝑚3 2 = -343962 118287844= 0.30

𝑚2 3 734.263 395867282.55

𝑏 2 = 𝑚4 = 2086701= 2086701 = 3.878

 𝑚2 2 734.262 539137

the distribution is said to be more peaked and the curve is leptokurtic as b2>3 .
Variable B have data closer to normal distribution as its value is closer to 4 and normal
distributing has value of 4.
Conclusion: I study the data and applied various measures such as measures of central tendency
(Mean, Median, Mode). Measures of dispersion (Quartile deviation) etc. And further the
skewness was calculated which found to be negative for set A and positive for Set B.