UNIT-II: SAMPLING DISTRIBUTION

Population: Population is the set under study

Sample: A finite subset of a population is known as sample

Size: Size of the Population(sample) is number of element in the Population(sample) It is denoted by N(n)

Sampling:
Sampling is the process of drawing samples from a given Population
Large and small sampling: If 𝑛 ≥ 30 the sampling is said to be large sampling and
If 𝑛 < 30 the sampling is said to be small sampling

Statistical inference:
Statistical inference deals with the methods of arriving at valid or logical generalizations and
Predictions about the Population using the information contained in the sample alone.

Parameters :
Statistical measures or constant obtained from the population are known as Parameter i e Mean Std
Deviation and variance
It is dented by Mean =μ Std Deviation= σ

Statistics :
Statistical measures or constant obtained from the sample are known as statistics Mean std Deviation
and variance
It is dented by Mean =x̅ Std Deviation= s

TYPE OF SAMPLING
1) With Replacement (infinite population) (No of sample = Nn )
a) Mean = μx̅ = μ
σ
b) S. D = σx̅ = n
√
2) Without Replacement (finite population) (No of sample = NCn )
a) Mean = μx̅ = μ
σ N−n
b) S. D = σx̅ = √
√n N−1
SAMPLING DISTRIBUTION OF MEANS

Example-1:
A Population consist of four numbers P = {2,3,4,5}. Consider all possible distinct samples of size two
with replacement(infinite)
a) Find the population mean (μ)
b) The Population Standard Deviation (σ)
c) The sampling dist of means (x̅)
d) The Mean of the Sampling Distribution of means (Mean = μx̅ )
e) Standard Deviation of S.D of means Mean = σx̅
verify c and e directly from a and b by use of suitable formulae
solution:
a) To Find the population mean (μ)
2+3+4+5
μ= = 3.5
4
b) To find The Population Standard Deviation (σ)
(2 − 3.5)2 + (3 − 3.5)2 + (4 − 3.5)2 + (5 − 3.5)2
σ=√
4

5
σ=√
4
σ = 1.1180

c) The sampling distributions of means (x̅)

The total Number of samples with replacement is given
Nn = 42 = 16
(a,b) 2 3 4 5
2 (2,2) (2,3) (2,4) (2,5)
3 (3,2) (3,3) (3,4) (3,5)
4 (4,2) (4,3) (4,4) (4,5)
5 (5,2) (5,3) (5,4) (5,5)
Mean of each sample
a+b 2 3 4 5
(x̅ = 2 )
2 2.0 2.5 3.0 3.5
3 2.5 3.0 3.5 4.0
4 3.0 3.5 4.0 4.5
5 3.5 4.0 4.5 5.0

2 + 2.5 + ⋯ + 5 56
Mean = μx̅ = = = 3.5
16 16
e) Standard Deviation of S.D of means Mean = σx̅
(2 − 3.5)2 + (2.5 − 3.5)2 + ⋯ + (5 − 3.5)2
σx̅ = √
16
σx̅ =0.6455

Verification
Mean = μx̅ = μ = 3.5
σ N−n 1.1180 4−2
σx̅ = √ = √ = 0.3727
√n N−1 √2 4−1

Example-2:
A Population consist of four numbers 𝑃 = {2,3,4,5}. Consider all possible distinct samples of size two
without replacement(finite)
a) Find the population mean (𝜇)
b) The Population Standard Deviation (𝜎)
c) The sampling dist of means (𝑥̅ )
d) The Mean of the Sampling Distribution of means (Mean = μ𝑥̅ )
e) Standard Deviation of S.D of means Mean = σ𝑥̅
verify c and e directly from a and b by use of suitable formulae
solution:
a) To Find the population mean (𝜇)
2+3+4+5
𝜇= = 3.5
4
b) To find The Population Standard Deviation (𝜎)
(2 − 3.5)2 + (3 − 3.5)2 + (4 − 3.5)2 + (5 − 3.5)2 5
𝜎=√ =√
4 4
𝜎 = 1.1180

c) The sampling dist of means (𝑥̅ )

The total no of samples without replacement is given
𝑁𝐶𝑛 = 4𝐶2 = 6 = {(2,3), (2,4), (2,5), (3,4), (3,5), (4,5)}

Mean of each sample

𝑎+𝑏
𝑥̅ = 2 = {2.5,3,3.5,3.5,4,4.5}
2.5 + 3 + 3.5 + 3.5 + 4 + 4.5 21
Mean of means = μ𝑥̅ = =
6 6
μ𝑥̅ = 3.5

e) S.D of Sampling distribution of Mean = σ𝑥̅

(2.5 − 3.5)2 + (3 − 3.5)2 + 2(3.5 − 3.5)2 + (4 − 3.5)2 + (4.5 − 3.5)2
σ𝑥̅ = √
6
σ𝑥̅ = 0.6455
And also by direct formula
σ 1.1180
σ𝑥̅ = = = 0.7905
√n √2
Verification
Mean = μ𝑥̅ = 𝜇 = 3.5
𝜎
S. D = σ𝑥̅ = = 0.7905
√𝑛
Example-3:
Find the Mean and Standard Deviation of sampling distribution of Variances (S.D.V) for the population
𝑃 = {2,3,4,5}. by drawing samples of size two
(a) with replacement
(b) without replacement
Solution:
With replacement
1) To Find The sampling distribution Variance (𝑥̅ )
The total no of samples with replacement is given
𝑁 𝑛 = 42 = 16
(a,b) 2 3 4 5
2 (2,2) (2,3) (2,4) (2,5)
3 (3,2) (3,3) (3,4) (3,5)
 4 (4,2) (4,3) (4,4) (4,5)
5 (5,2) (5,3) (5,4) (5,5)

Mean of each sample

𝑎+𝑏 2 3 4 5
(𝑥̅ = )
2
2 2.0 2.5 3.0 3.5
3 2.5 3.0 3.5 4.0
4 3.0 3.5 4.0 4.5
5 3.5 4.0 4.5 5.0

𝑣 2 3 4 5
(𝑎 − 𝑥̅ )2 + (𝑏 − 𝑥̅ )2
=
2
2 0.00 0.25 1.00 2.25
3 0.25 0.00 0.25 1.00
4 1.00 0.25 0.00 0.25
5 2.25 1.00 0.25 0.00

ii) To Find the mean

∑ 𝑣̅ 10
μ𝑣̅ = 𝑛
= 16 = 0.625

ii) To Find the S.D

4(0 − 6.25)2 + 8(0.25 − 6.25)2 + 4(1 − 0.625)2 8.25

𝜎=√ =√
16 16
𝜎 = √0.5156
𝜎 = 0.7181

Example-4:
Find the Mean and Standard Deviation of sampling distribution of Variances (S.D.V) for the population
𝑃 = {2,3,4,5}. by drawing samples of size two
(a) with replacement
(b) without replacement
Solution:
Without replacement
1) The sampling distribution Variance (𝑥̅ )
The total no of samples with replacement is given
𝑁 𝑛 = 42 = 16
The total no of samples without replacement is given
𝑁𝐶𝑛 = 4𝐶2 = 6 = {(2,3), (2,4), (2,5), (3,4), (3,5), (4,5)}

Mean of each sample

𝑎+𝑏
𝑥̅ = = {2.5,3,3.5,3.5,4,4.5}
2
 (𝑎 − 𝑥̅ )2 + (𝑏 − 𝑥̅ )2
𝑣̅ = = {0.25,1,2.25,0.25,1,0.25}
2

ii) To Find the mean

∑v
̅ 5
μv̅ = 6
= 6 = 0.8333

iii) To Find the S.D

3(0.25 − 0.8333)2 + (2.25 − 0.8333)2 + 2(1 − 0.8333)2

𝜎=√
6

3.0833
𝜎=√
6
𝜎 = √0.5138

𝜎 = 0.7169

SAMPLING DISTRIBUTIONS MEANS (σ known)

Example-5:
Determine the mean and S.D of the sampling distribution of means of 300 random samples of size 36
are drawn from a population of 1500 which is normally distributed with mean 22.4 and S.D of 0.048 if
sampling is done
i) with replacement
ii) without replacement
Solution:
Let N = 1500
Mean = 𝜇= 22.4
s.d = 𝜎 = 0.048
also n= 36
i) with replacement
wkt
a) Mean = μ𝑥̅ = 𝜇 = 22.4
𝜎 0.048
b) S. D = σ𝑥̅ = = = 0.008
√𝑛 √36
ii) without replacement
a) Mean = μ𝑥̅ = 𝜇 = 22.4
𝜎 𝑁−𝑛 0.048 1500−36
b) S. D = σ𝑥̅ = √ = √ = 0.008
√𝑛 𝑁−1 √36 1500−1

Example-6:
The sampling distribution of means of 300 random samples of size 36 is drawn from a population of
1500 which is normally distributed with mean 22.4 and S.D of 0.048. determine the expected number of
random samples having their means
a) Between 22.39 and 22.41
b) Greater than 22.42
c) Less than 22.37
d) Less than 22.38 or more than 22.41.

Solution:
x−μ
Let N = 1500, μ= 22.4, σ = 0.048 n= 36, Z =
σ
i) To find P(22.39 ≤ X ≤ 22.41)
a−μ X−μ b−μ
Wkt P(a ≤ X ≤ b) = P (σ/ n ≤ σ/ n ≤ σ/ n)
√ √ √
22.39 − 22.4 22.41 − 22.4
P(22.39 ≤ X ≤ 22.41) = P ( ≤Z≤ )
0.048/√36 0.048/√36
𝑃(22.39 ≤ X ≤ 22.41) = P(−1.25 ≤ Z ≤ 1.25)

P(22.39 ≤ X ≤ 22.41) = 2Area between {Z = 0 to Z = 1.25}

= 2{0.3944}
= 0.7888
Therefore Expected no samples
N = Probablity × Number of samples
N = 0.7888 × 300
𝑁 = 237

ii)To find P(X ≥ 22.42)

22.42 − 22.4
P(X ≥ 22.42) = P (Z ≥ )
0.048/√36

P(X ≥ 22.42) = P(Z ≥ 2.50)

P(X ≥ 22.42) = 0.5 − Area between {Z = 0 to Z = 2.50}

P(X ≥ 22.42) = 0.5 − 0.4938
P(X ≥ 22.42) = 0.0062

Therefore Expected no samples

N = Probablity × Number of samples
N = 0.0062 × 300
N=2

iii) To find P(X ≤ 22.37)

22.37 − 22.4
P(X ≤ 22.37) = P (Z ≤ )
0.048/√36
P(X ≤ 22.37) = P(Z ≤ −3.75)
P(X ≤ 22.37) = 0.5 − Area between {Z = 0 to Z = −3.75}
P(X ≤ 22.37) = 0.5 − 0.4999
P(X ≤ 22.37) = 0.0001
Therefore Expected no samples
N = Probablity × Number of samples
N = 0.0001 × 300
N=0

iv) To find P(X ≤ 22.38 and X ≥ 22.41)

22.38 − 22.4 22.41 − 22.4
P(X ≤ 22.38 and X ≥ 22.41) = P [Z ≤ ] + P [Z ≥ ]
0.048/√36 0.048/√36
P(X ≤ 22.38 and X ≥ 22.41) = P[Z ≤ −2.53] + P[Z ≥ 1.26]

P(X ≤ 22.38 and X ≥ 22.41) = P[Z ≤ −2.53] + P[Z ≥ 1.26]

P(X ≤ 22.38 and X ≥ 22.41) = 0.0057 + 0.1038
P(X ≤ 22.38 and X ≥ 22.41) = 0.1095

Therefore Expected no samples

N = Probablity × Number of samples
N = 0.1095 × 300
N = 32.85
N = 33

Example-7:
Determine the probability that the sample mean area covered by a sample of 40 of 1 litre paint boxes
will be between 510 to 520 square feet given that a 1 litre of such paint box covers on the average 513.3
square feet with s.d of 31.5 s.ft
Solution:
x−μ
Let μ = 513.3, σ = 31.5 n = 40 Z = σ/ n
√
To find P(510 ≤ X ≤ 520)
510 − 513.3 520 − 513.3
P(510 ≤ X ≤ 520) = P ( ≤Z≤ )
31.5/√40 31.5/√40
P(510 ≤ X ≤ 520) = P(−0.6626 ≤ Z ≤ 1.3452)
P(510 ≤ X ≤ 520) = Area (Z = 0 to Z = −0.6626) + Area (Z = 0 to Z = 1.3452)
P(510 ≤ X ≤ 520) = 0.2462 + 0.4107
P(510 ≤ X ≤ 520) = 0.6569

Example-8:
Calculate the probability that a random sample of 16 computers will have an average life of less than 775
hours assuming that length of the life of computers is approximately normally distributed with mean 800
hours and std 40 hours.
Solution:
x−μ
Let μ = 800, σ = 40, n = 16, Z = σ/ n
√
To find P(X ≤ 775)
775 − 800
P(X ≤ 775) = P [Z ≤ ]
40/√16
P(X ≤ 775) = P(Z ≤ −2.5)

P(X ≤ 775) = 0.5 − Area(Z = 0 to Z = −2.5)

P(X ≤ 775) = 0.5 − 0.4938
P(X ≤ 775) =0.0062

Example-9:
Determine the probability that 𝑋̅ will be between75 and 78 if a random sample of size 100 is taken from
an infinite population having the mean μ = 76 and the variance σ2 = 256
Solution:
x−μ
Let μ = 76, σ = √256 = 16, Z = σ/ n
√
To find P(75 ≤ X ≤ 78)
75 − 76 75 − 78
P(75 ≤ X ≤ 78) = P ( ≤Z≤ )
16/√100 16/√100

P(75 ≤ X ≤ 78) = P(−0. 625 ≤ Z ≤ 1.25)

P(75 ≤ X ≤ 78) = Area Between[(Z = 0 to Z = −0. 625) + (Z = 0 to Z = 1.25)]

P(75 ≤ X ≤ 78) = 0.2340 + 0.3944

P(75 ≤ X ≤ 78) = 0.6284

Example-HW
Find 𝑃(𝑋̅ > 66.75) if a random sample of size 36 is taken from an infinite population having the mean
μ = 63 and the variance σ2 = 9
Example-HW
Calculate the mean and S.D of the sampling distribution of means of 80 random samples of size 25 by
sampling i) with replacement ii) without replacement
from a normal population of 3000 with mean 68 and S.D of 3
Example-HW
Determine the expected number samples whose mean lies
a) between 66.8 and 68.3
b) less than 66.4 from above examples
SAMPLING DISTRIBUTION OF DIFFERENCES AND SUM ( MORE THAN 1 MEAN)
μS −S = μS − μS
1 2 1 2
μS +S = μS + μS
1 2 1 2

σS1 −S2 = √σ2 S1 + σ2 S2

σS1 +S2 = √σ2 S1 + σ2 S2

Example-10:
Let U1 = {2,7,9}, U2 = {3,8}.

i) Find
a) μU , b) μU , c) μU +U , d) μU −U , e) σU1 , f) σU2 , g) σU1+U2 h) σU1−U2
1 2 1 2 1 2
ii)Verify
a) μU = μU + μU , b) μU1−U2 = μU − μU , c) σU1+U2 = √σ2 U1 + σ2 U2 d) σU1−U2= √σ2 U1 + σ2 U2
1 +U2 1 2 1 2

Sol: let Let

U1 = {2,7,9}, U2 = {3,8}.
U1 + U2 = {2 + 3,7 + 3,9 + 3,2 + 8,7 + 8,9 + 8} = {5,10,12,10,15,17}
U1 − U2 = {2 − 3,7 − 3,9 − 3,2 − 8,7 − 8,9 − 8} = {−1,4,6, −6, −1,1}
a) To find μU
1
∑ x 2 + 7 + 9 18
μU = = = =6
1 n 3 3
b) To find μU
2
∑ x 3 + 8 11
μU = = = = 5.5
2 n 2 2
b) To find μU +U
1 2
∑ x 5 + 10 + 12 + 10 + 15 + 17 69
μU +U = = = = 11.5
1 2 n 6 6
d) To find μU −U
1 2
∑ x −1 + 4 + 6 − 6 − 1 + 1 3
μU −U = = = = 0.5
1 2 n 6 6
e) To find σU1
(2 − 6)2 + (7 − 6)2 + (9 − 6)2 26
σU1 = √ = √ = 2.9439
3 3
f) To find σU2
(3 − 5.5)2 + (3 − 5.5)2 12.5
σU2 = √ =√ = 2.5000
2 2
g) To find σU1+U2

(5 − 11.5)2 + (10 − 11.5)2 + (12 − 11.5)2 +(10 − 11.5)2 + (15 − 11.5)2 + (17 − 11.5)2
σU1+U2 = √
6

89.5
=√ = 3.8622
6
h) To find σU1−U2
(−1 − 0.5)2 + (4 − 0.5)2 + (6 − 0.5)2 + (−6 − 0.5)2 + (−1 − 0.5)2 + (1 − 0.5)2
σU1−U2 = √
6
σU1−U2 = 3.8622

Verification
a) μU +U = μU + μU
1 2 1 2
11.5 = 6 + 5.5 = 11.5
b) μU1−U2 = μU − μU
1 2
0.5 = 6 − 5.5 = 0.5
c) σU1+U2 = √σ2 U1 + σ2 U2

26 12.5
3.8622 = √ + = 3.8622
3 2

d) σU1 −U2= √σ2 U1 + σ2 U2

26 12.5
3.8622 = √ + = 3.8622
3 2
Example-11:
The mean voltage of a battery is 15 and s.d is 0.2 Find the probability that four such batteries connected
in series will have a combined voltage of 60.8 or more volts.
Solution:
To find P(X ≥ 60.8)
Let mean of single battery 15 and std 0.2
Let μ=μA + μB + μC + μD = 15 × 4 = 60
σ = √σ2 A + σ2 B + σ2 C + σ2 D
σ = √4(0.2)2 = 0.4
x−μ
Z= σ
60.8 − 60
P(X ≥ 60.8) = P (Z ≥ )
0.4
P(X ≥ 60.8) = P(Z ≥ 2.00)

P(X ≥ 60.8) = 0.5 − Area bet(Z = 0 to Z = 2.00)

P(X ≥ 60.8) = 0.5 − 0.4773
P(X ≥ 60.8) = 0.0227

Example-12:
Suppose the diameter of motor shafts in a lot have mean of 0.249 inches and s.d if 0.003 inches. The
inner diameter of bearings in another lot have a mean of 0.255 inches and s.d of 0.002 inches
a) Find the mean and s.d of clearances between shafts and bearings selected from these lots.
b) If a shaft and bearing are selected at random find the probability that the shaft will not fit inside the
bearings. Assume that both dimensions are normally distributed
Solution:
Let μB = Mean diameter of bearing = 0.225 σB = std of bearing = 0.002
μS = Mean diameter of Shaft = 0.249 σS = std of Shaft = 0.003
a) To Find the mean and s.d
μd = μB−S = μB − μB = 0.225 − 0.249 = 0.006
σB−S = √σ2 𝐁 + σ2 S = √(0.002)2 + (0.003)2
σB−S = 0.0036

b) To the probability that the shaft will not fit inside the bearings.
To find P(X < 0)
0 − 0.006
P(X < 0) = P (X < )
0.0036
P(X < 0) = P(Z < −1.664)

P(X < 0) = 0.5 − Area between {Z = 0 to Z = −1.664}

P(X < 0) = 0.5 − 0.4515
P(X < 0) = 0.0485

SAMPLING DIST MEANS (σ UNKNOWN) (SMALL SAMPLES) ( n < 30)

Example-13:
A process of making certain ball bearings is under control if the dia of the bearings have mean of
0.500cm. if a random sample of 10 of these bearings has a mean dia of 0.5060 cm and sd of 0.0040cm. is
the process under control?
Solution:
Let μ = 0.500, 𝑥̅ = 0.5060 cm, n = 10, s = 0.0040cm ,

i) To find t by calculation
𝑥̅ − μ 0.5060 − 0.500
t= =
s/√n 0.0040/√10
t = 4.7434

ii) To find t by table

Let df = n − 1 = ϑ = 10 − 1 = 9
α = 0.005
t(ϑ, α) = t(9,0.005)
t(ϑ, α) = 3.350

comparing (i) and (ii) we observe that

4.7434 > 3.350
t(calculated) > t(ϑ, α)
the process is not under control

Example-14:
A company claims that the mean life time of tube lights is 500hours. is the claim of the company tenable
if random sample of 25 tube lights produced by the company has mean 518h and s.d 40 h. Company is
satisfied if t falls between −𝑡0.01 and 𝑡0.01
Solution:
Let μ = 500h, 𝑥̅ = 518h n = 25, s = 40h,

i) To find t by calculation
𝑥̅ − μ 518 − 500
t= =
s/√n 40/√25
t = 2.25

ii) To find t by table

Let df = ϑ = n − 1 = 25 − 1 = 24 α = 0.01

t(ϑ, α) = t(24,0.01)
t(ϑ, α) = 2.492

comparing (i) and (ii) we observe that

t(calculated) < t(ϑ, α)
2.25 < 2.492
Accept the company claim
 SAMPLING DISTRIBUTION OF PROPORTION

a) with replacement

a) Mean = μ𝑃 = 𝑝
𝑝𝑞
b) S. D = σ𝑝 = √ 𝑛
ii) without replacement
a) Mean = μ𝑃 = 𝑝
𝑝𝑞 𝑁−𝑛
b) S. D = σ𝑥̅ = √ [ ]
𝑛 𝑁−1

Example-15: Find the probability that in 120 tosses of a fair coin i) between 40% and 60% will be heads

Solution:
1
Mean = μ𝑃 = 𝑝 = 2 = 0.5
1 1
√2 × 2
S. D = σ𝑝 = = 0.0456
120
To find P(0.4 ≤ X ≤ 0.6)
0.4 − 0.5 0.6 − 0.5
P(0.4 ≤ X ≤ 0.6) = P ( ≤Z≤ )
0.0456 0.0456
P(0.4 ≤ X ≤ 0.6) = P(−2.1930 ≤ Z ≤ 2.1930)

P(0.4 ≤ X ≤ 0.6) = 2P(Z ≤ 2.1930)

P(0.4 ≤ X ≤ 0.6) = 2Area bet(Z = 0 to Z = 2.1930)

P(0.4 ≤ X ≤ 0.6) = 2 × 0.4859

P(0.4 ≤ X ≤ 0.6) = 0.9718

Example-16:
The election returns showed that a certain candidate received 46% of the votes determine the probability
that a poll of
a) 200 b) 1000.people. probability of win
Solution:
a) n = 100
46
Mean = μP = p = 100 = 0.46 and q = 1 − p = 1 − 0.46 = 0.54

(0.46)(0.54)
S. D = σ𝑝 = √ = 0.0352
200
To find P(X ≥ 50%)
0.5 − 0.46
P(X ≥ 0.5) = P (Z ≥ )
0.0352
P(X ≥ 0.5) = P(Z ≥ 1.1364)

P(X ≥ 0.5) = 0.5 − Area Between{Z = 0 to Z = 1.1364}

P(X ≥ 0.5) = 0.5 − 0.3721

P(X ≥ 0.5) = 0.1279

b) n = 1000
46
Mean = μP = p = = 0.46 and q = 1 − p = 1 − 0.46 = 0.54
100

(0.46)(0.54)
S. D = σ𝑝 = √ = 0.0158
1000

To find P(X ≥ 50%)

0.5 − 0.46
P(X ≥ 0.5) = P (Z ≥ )
0.0158
P(X ≥ 0.5) = P(Z ≥ 2.5316)

P(X ≥ 0.5) = 0.5 − Area Between{Z = 0 to Z = 2.5316}

P(X ≥ 0.5) = 0.5 − 0.4943
P(X ≥ 0.5) = 0.0057