Name- Ahel Kundu MS-EXCEL Gr-8
Roll No. STAT02 1st data set
5 7 6
6 8 6
9 7 6
6 7 6
7 8 5
6 8 6
6 6 7
7 7 8
6 7 9
7 4 8
6 6 6
8 6 8
7 5 7
8 8 8
7 7 6
5 7 7
9 6 7
7 7 7
6 4 7
8 6 8
6 9 6
6 9 9
7 6 7
8 7 8
8 7 9
6 8 7
5 7 5
9 7 8
6 6 8
8 7 7
9 8 5
6 8 8
8 8 9
9 8 6
8 5 8
6 5 7
8 7 7
7 4 5
6 8 4
7 8 6
6 7 9
9 6 9
5 6 7
6 7 8
9 7 5
8 7 4
8 7 8
6 6 7
9 8 8
8 8 7
Max value: 9
Min value: 2
Sample size(y): 900
Now I will try to fit the truncated binomial distribution for the guven data set
We know if X follows Bin(n,p) then the pmf of X is,
Now, if we truncate the values of X over the interval [2,m] i.e. if X' follows {0,1} Truncated
P(X=x) = { nCxpx(1-p)n-x /(1 - (P(X=0)+P(X=1))) for x=2,3,4….n
0 otherwise
Now,
E(Xr) = np(1−qn−1 )
Here, from the given data we can see that n=9.
Now, by Method of Moments we get, E(X')=
Here to estimate the value of p we will use fixed point iteration method,
For that we will take φ(p) = (6.882222222∗[1−(1−p)^9−9p(1−p)^8])/9*(1-((1-p)^8)) su
Now, since pϵ(0,1) so we take p=0.5 as our initial guess for estimating the value of p
Table 1.1.2
p φ(p)
0.5 0.752696199443137
0.752696199443137 0.764626933909879
0.764626933909879 0.764647293994791
0.764647293994791 0.764647323306109
0.764647323306109 0.764647323348295
Table 1.1.3
Observed Frequency Observed Value(x) Estimated Probability Mass(P(X'=x))
1 2 0.000841953178904
8 3 0.006382734155715
28 4 0.031105704730873
84 5 0.10106064717713
211 6 0.218893490143278
255 7 0.304788158885091
232 8 0.247559803381356
81 9 0.089367508347653
Total 900 1
Fig:1.1.2 Fitted frequency polygon(for expected frequency) for Tr
Distribution together with a column diagram(for observed frequ
dataset
Column diagram(for observed frequency) Frequency polygon(for expected freq
300
Fig:1.1.2 Fitted frequency polygon(for expected frequency) for Tr
Distribution together with a column diagram(for observed frequ
dataset
Column diagram(for observed frequency) Frequency polygon(for expected freq
300
FREQUENCY→
250
200
150
100
50
0
1 2 3 4 5 6
OBSERVED VALUE →
Registration Number: 19214110002
UG SEM 3
9 7 6 8 6 7
8 6 8 3 8 7
6 9 8 6 9 8
8 6 9 5 7 8
8 8 5 8 4 9
8 6 4 6 7 8
8 8 5 9 9 7
6 8 7 7 8 6
8 9 6 8 6 7
7 5 6 6 6 8
4 8 8 7 6 5
8 8 6 5 6 8
8 8 6 7 8 6
5 8 5 8 7 2
4 8 5 5 6 6
7 8 7 5 7 5
5 8 7 5 7 5
6 6 8 7 6 8
7 7 5 8 9 6
8 6 6 9 7 7
7 6 7 9 9 5
6 9 6 9 8 8
9 6 9 4 6 6
8 7 8 5 7 6
6 7 4 7 8 9
6 7 8 3 4 7
6 8 6 7 7 8
6 7 7 7 8 9
8 6 7 9 7 7
5 8 8 6 7 8
8 8 6 9 8 7
6 5 5 8 7 7
7 6 7 8 7 6
7 6 6 6 7 7
6 7 6 8 7 8
7 6 8 7 9 5
6 9 6 3 3 8
8 6 6 5 7 8
5 7 7 6 5 5
3 7 4 8 5 4
7 5 4 5 8 7
6 5 7 5 5 7
9 8 6 6 8 7
8 7 8 7 6 7
8 7 6 4 6 5
7 6 8 7 8 6
6 5 6 7 8 8
8 5 5 5 8 8
4 8 8 8 9 8
7 6 8 7 8 7
Table 1.1.1
Frequency distribution of 900 observations
Observation (xi) Frequency(fi) xifi xi2fi
2 1 2 4
3 8 24 72
4 28 112 448
5 84 420 2100
6 211 1266 7596
7 255 1785 12495
8 232 1856 14848
9 81 729 6561
Total 900 6194 44124
tion for the guven data set
P(X=x) = nCxpx(1-p)n-x when x=0,1,2,….n
al [2,m] i.e. if X' follows {0,1} Truncated Bin(n,p) then, the pmf of X' is,
or x=2,3,4….n
otherwise
6.8822222222 (The mean of the data set)
oint iteration method,
−p)^9−9p(1−p)^8])/9*(1-((1-p)^8)) such that p=φ(p)
uess for estimating the value of p
Here in the last step we observe that |p-φ(p)|<0.0000000001 i.e.
Hence we can approximate the value of p by p' = 0.764647323
Fig:1.1.1 Scatter diagram showing the estimated probability mass a
Expected Frequency (y*P(X'=x))
0.757757861013384
of the given dataset for the fitted Truncated Binomial Distribution
5.74446074014366
27.9951342577853
90.9545824594173
0.35
197.00414112895
274.309342996582
0.3
222.803823043221
80.430757512888
0.25 900
Estimated Probability Mass
0.2
0.15
0.1
0.05
0
1 2 3 4 5 6 7
Observed Values
pected frequency) for Truncated Binomial
gram(for observed frequency) on the given
Frequency polygon(for expected frequency)
pected frequency) for Truncated Binomial
gram(for observed frequency) on the given
Frequency polygon(for expected frequency)
Comment:
From fig:1.1.2 we can see
5 6 7 8
RVED VALUE →
7 8 8 4 8 7 8 7
7 7 6 6 6 7 6 7
9 7 8 7 8 8 7 5
6 7 9 5 6 6 3 7
8 7 6 8 7 7 4 4
8 8 5 6 6 7 5 6
6 7 6 8 6 8 8 7
7 6 6 7 6 7 7 7
9 8 6 7 7 8 9 7
7 4 8 7 7 7 6 7
8 7 8 8 8 6 6 9
8 7 6 7 6 5 7 8
8 6 7 9 7 6 9 6
6 7 6 7 7 7 7 5
9 7 8 9 8 7 7 7
4 5 6 7 6 8 6 6
6 8 7 8 7 7 6 8
6 7 7 9 9 7 7 8
8 5 7 7 7 6 7 7
8 8 8 8 7 7 6 8
5 6 5 5 7 7 9 7
8 9 7 6 6 8 7 8
8 6 8 7 7 9 8 6
9 8 8 7 6 8 9 7
8 6 8 7 8 8 5 8
9 6 9 7 8 7 7 6
7 5 7 6 7 6 7 8
8 8 8 9 6 7 8 8
7 6 9 7 5 6 9 9
6 9 7 6 6 6 7 8
7 8 8 7 6 7 8 5
4 6 7 8 8 7 7 8
9 8 8 5 8 6 7 5
8 7 6 7 8 7 5 6
7 6 6 9 9 8 8 5
6 8 6 6 5 6 7 7
6 7 6 6 6 8 8 6
7 8 7 7 9 3 7 7
9 7 8 6 9 5 6 9
6 7 9 8 7 6 7 6
4 4 8 8 7 6 5 7
3 8 6 8 6 8 8 8
7 7 6 8 8 8 8 6
8 5 8 6 9 8 6 4
8 6 8 6 6 5 9 6
6 9 7 8 8 7 7 7
4 9 6 6 7 5 7 7
5 6 6 8 7 5 7 8
7 6 4 9 5 9 7 7
7 7 6 6 5 9 7 5
Mean : 6.88222222
Variance: 1.66168395
Standard Deviation : 1.28906321
en x=0,1,2,….n (where, pϵ[0,1] be the success probability and nϵ{0,1,2,…..} be the no. of trials)
φ(p)|<0.0000000001 i.e. both are almost same values
p by p' = 0.764647323
obability mass against the observed values
al Distribution
6 7 8 9 10
lues
From fig:1.1.2 we can see that the frequency polygon of the truncated binomial distribution fits on the column diagram of the given dat
6
8
6
9
7
6
7
8
5
6
8
7
7
8
7
9
7
8
8
7
8
7
6
7
6
6
6
8
8
5
5
9
6
8
7
8
7
7
7
8
8
7
6
5
5
7
7
8
8
6
n diagram of the given data very well i.e. we can assume that our given data has been taken from a {0,1} truncated binomial (n=9,p=0.7
ated binomial (n=9,p=0.764647) probability distribution(or population).
Now we will try and fit a Truncated Poisson distribution to the given dataset
We know that if X follows Poi(λ) then the pmf of X is:-
P(X=x) ={ (e-λ λx)/x! For x=1,2,3,4…∞
0 otherwise
Now, if we truncate the values of X over the interval [2,9] i.e. if Z follows Truncated Poi(λ) distribution
P(Z=z) = { ((e-λ λx)/x! )/(Σ𝑒(e−λ λi)/i! ) for i=2,3,..9
0 otherwise
Now we know that the ,
E(Z) = λ(1-(λ8/9!))/(Σ𝑒(e−λ λi)/i! ) where i=2,3…9
Now by the method of moments we get ,
E(Z) = 6.8822222222
Here to estimate the value of λ we will use fixed point iteration method,
For that we will take φ(λ) = 6.88222222 - (1-(λ8/9!))/(Σ𝑒(e−λ λi)/i! ) where i=2,3…9 such that λ=φ(λ)
Now, since λ>0 so we can take any positive real number λ as our initial guess for estimating the value
But, we know if X follows Poi(λ) then, E(X) = λ
Hence, here though X follows truncated poisson but we can take λ=6.882 (=E(Z))as a good initial gues
Table 1.2.1
λ φ(λ)
6.882 7.63178372566
7.6317837257 8.02793303617
8.0279330362 8.25996958845
8.2599695885 8.40264808263
8.4026480826 8.49274024983
8.4927402498 8.55052328989
8.5505232899 8.58794130264
8.5879413026 8.61231864607
8.6123186461 8.62826173685
8.6282617369 8.63871484011
8.6387148401 8.64557959595
8.6455795959 8.65009261411
8.6500926141 8.65306162584
8.6530616258 8.65501576534
8.6550157653 8.65630232488
8.6563023249 8.65714953312
8.6571495331 8.65770749821
8.6577074982 8.65807500141
8.6580750014 8.65831707072
8.6583170707 8.65847652439
8.6584765244 8.65858156081
8.6585815608 8.65865075224
8.6586507522 8.65869633172
8.6586963317 8.65872635716
8.6587263572 8.65874613648
8.6587461365 8.6587591662
8.6587591662 8.65876774959
8.6587677496 8.65877340396
8.658773404 8.65877712881
8.6587771288 8.65877958259
8.6587795826 8.65878119903
8.658781199 8.65878226387
8.6587822639 8.65878296535
8.6587829653 8.65878342745
8.6587834274 8.65878373186
8.6587837319 8.6587839324
8.6587839324 8.6587840645
8.6587840645 8.65878415152
8.6587841515 8.65878420885
8.6587842089 8.65878424662
8.6587842466 8.6587842715
8.6587842715 8.65878428788
8.6587842879 8.65878429868
8.6587842987 8.65878430579
8.6587843058 8.65878431048
8.6587843105 8.65878431356
8.6587843136 8.6587843156
8.6587843156 8.65878431694
8.6587843169 8.65878431782
8.6587843178 8.6587843184
Here, from the last step of table:1.2.1 we can observe that |φ(λ) - λ|
Hence, we can approximate the value of λ as, λ̂ = 8.658783
Observed Frequency
1
8
28
84
211
255
232
81
Total 900
Fig:1.2.2 Fitted frequency polygon(for expec
Distribution together with a column diagram
Column diagram(for observed frequency)
300
Frequency →
250
200
150
100
50
0
1 2 3
Observed V
100
50
0
1 2 3
Observed V
s Truncated Poi(λ) distribution over the interval [2,9] then, the pmf of Z is,
or i=2,3,..9
otherwise
re i=2,3…9 such that λ=φ(λ)
guess for estimating the value of λ.
2 (=E(Z))as a good initial guess for estimating the value of λ.
we can observe that |φ(λ) - λ|< 0.000000001 i.e. two consecutive guesses are almost same
of λ as, λ̂ = 8.658783
Table 1.2.2
Observed value(z) (λ^z)/z! Estimated Probability Mass(P(Z=z)) Expected Frequency(n*P(Z=z))
2 37.4873 0.010319884618221 9.28789615639847
3 108.19802092 0.02978588049807 26.8072924482628
4 234.21579605 0.06447736892418 58.0296320317616
5 405.60475064 0.111659109185083 100.493198266575
6 585.34058659 0.161138666067823 145.024799461041
7 724.04816005 0.199323534627249 179.391181164524
8 783.67198743 0.215737404141292 194.163663727163
9 753.96063137 0.207558151938083 186.802336744275
3632.5272 1 900
polygon(for expected frequency) for Truncated Poisson
a column diagram(for observed frequency) on the given dataset
am(for observed frequency) Frequency polygon(for expected frequency)
3 4 5 6 7 8
Observed Values of the given dataset →
3 4 5 6 7 8
Observed Values of the given dataset →
2 0.01031988462
Fig:1.2.1 Scatter diagram showing the estimated probability mass
3 0.0297858805
given dataset for the fitted Truncated Poisson Distribution
4 0.06447736892
0.25
Fig:1.2.1 Scatter diagram showing the estimated probability mass
given dataset for the fitted Truncated Poisson Distribution
5 0.11165910919
0.25
6 0.16113866607
7 0.19932353463
8 0.21573740414
Estimated Probability Mass ->
0.2
9 0.20755815194
0.15
0.1
0.05
0
1 2 3 4 5 6
Observed Value of data set ->
Comment: From fig:1.2.2 we can see that the frequency polygon of the truncated poisson
ted probability mass against the observed values of the
Distribution
ted probability mass against the observed values of the
Distribution
5 6 7 8 9 10
served Value of data set ->
y polygon of the truncated poisson distribution does not fit on the column diagram of the given data i.e. it is clear that our given data has n
r that our given data has not taken from a truncated poisson population.
