Practical-12

Application of Exponential Distribution

Q. (a) The records for the arrival of aircraft at an airport indicate that the arrival of aircraft is
exponentially distributed with an average of five minutes between flight arrivals. What is the
probability that the time interval between flights will be (i) Less than 5 minutes (ii) More than
7 minutes?

(b) The life time in hours of a certain of electric component follows exponential distribution
with distribution function.
.
𝐹(𝑋) = 1 − 𝑒 ; x≥0.
(i) What is the probability that the component will survive up to 300 hours? (ii) What is the
probability that it will fail during 350 to 400 hours? (iii) Find its expectation and variance of
the life time of the component?

Aim: (a) To find the probability that the time interval between flights will be
(i) Less than 5 minutes
(ii) More than 7 minutes.
(b) (i) To find that the probability that the component will survive up to 300 hours.
(ii) To find that the probability that the electric component will fail during 350 to 400 hours.
(iii) Find expectation and variance of the life time of the electric component.

Procedure:
Let X follows exponential distribution with parameter 𝜃 then its probability density function
is
𝑓(𝑥; 𝜃) = 𝜃𝑒 ; x ≥0 and
its cumulative distribution function is
𝐹(𝑥) = 1 − 𝑒 ; x≥0.
𝐸(𝑋) = 𝑀𝑒𝑎𝑛 = and Variance=

Calculations:
(a) Let X denote the arrival time between flights in minutes.
Give that, 𝐸(𝑋) = 𝑀𝑒𝑎𝑛 = =5⟹𝜃= .

Thus, the probability density function of X is given by

𝑓 𝑥; = 𝜃𝑒 = 𝑒 ; x≥0.

(i) Probability that the time interval between flights will be Less than 5 minutes is

𝑃(𝑋 ≤ 5) = ∫ 𝑒 𝑑𝑥 = ∫ 𝑒 𝑑𝑥 = = −[𝑒 − 1] = 1 − 𝑒

𝑃(𝑋 ≤ 5) = 1 − 0.3679 = 0.6321.

(ii) Probability that the time interval between flights will be More than 7 minutes is

⁄
𝑃(𝑋 ≤ 7) = ∫ 𝑒 𝑑𝑥 = ∫ 𝑒 𝑑𝑥 = =𝑒 = 0.2466

(b) Let X follows life time (in hours) of the electric component.
.
Given that 𝐹(𝑋) = 1 − 𝑒 = 1−𝑒
.
Here 𝜃 = 0.008 = then its p.d.f. is 𝑓(𝑥) = 0.008𝑒 and
⁄
C.D.F. is 𝐹(𝑋) = 1 − 𝑒 ; x≥0.

(i) The probability that the component will survive up to 300 hours is P[X<300].

.
i.e., P[X < 300] = 1 − 𝑒 =1−𝑒 = 1 − 0.0907 = 0.9093.

(ii) The probability that the electric component will fail during 350 to 400 hours is
P[350<X<400].

.
i.e., P[350 < X < 400] = ∫ 𝑓(𝑥) 𝑑𝑥 = ∫ 𝑓(𝑥) 𝑑𝑥 = ∫ 0.008𝑒 𝑑𝑥

.
.
P[350 < X < 400] = 0.008 ∫ 𝑒 𝑑𝑥 = (0.008) = 0.0200.
.

(iii) 𝐸(𝑋) = 𝑀𝑒𝑎𝑛 = = = 125 and Variance= = = 0.0001.

. ( )

Conclusion:
(a) The estimated parameter is 𝜃 = .

(i) Probability that the time interval between flights will be Less than 5 minutes is 0.6321.

(ii) Probability that the time interval between flights will be More than 7 minutes is 0.2466.
(b) Here parameter is 𝜃 = 0.008 = .

(i) The probability that the component will survive up to 300 hours is 0.9093.

(ii) The probability that the electric component will fail during 350 to 400 hours is 0.0200.

(iii) Expectation of the life time of the component is 125

and Variance of the life time of the component is 0.0001.

 Practical-13

Lack of Memory Property of Exponential Distribution

Q. (a) Suppose that times between fatal auto accidents on a stretch of busy highway have an
exponential distribution with a mean of 20 days. Suppose that an accident occurred on July 1.
What is the probability that another fatal accident occurred in the same month? If the month
of July were accident-free in this stretch of highway except for the accident on July 1, what is
the probability that there will be another fatal accident in the following month (August)?
(b) Let X be the time (in hours) required to repair a computer system. We assume that X has
an exponential distribution with parameter 𝜃 = . Find P(X>10│X>8).

(c ) The distance between major cracks in a highway follows an exponential distribution with
a mean of 5 miles. Given that there are no cracks in the first 5 miles inspected, what is the
probability that there are no major cracks in the next 15 miles?

Aim: (a) To find the probability that there will be another fatal accident in the following
month (August).
(b) To find P(X>10│X>8).
(c ) To find the probability that there are no major cracks in the next 15 miles.

Procedure:
Let X follows exponential distribution with parameter 𝜃 then its p.d.f. is given by
𝑓(𝑥; 𝜃) = 𝜃𝑒 ; x ≥0 and
its cumulative distribution function is 𝐹(𝑥) = 1 − 𝑒 ; x≥0.
Let X has exponential distribution, then for every constant a≥0, one has
P[Y≤x│X≥a]=P[X≤x] for all x, where Y=X – a.  This condition explains exponential
distribution has ‘lacks of memory’.

Calculations:
(a) Let X be the time in days from July 1 to the next fatal accident on this stretch of highway.
Then X is exponentially distributed with a mean of 20 days.

i.e., Given that 𝐸(𝑋) = 𝑀𝑒𝑎𝑛 = = 20 ⇒ 𝜃 = . Then its C.D.F. is F(X) = 1 − 𝑒 .

The probability that another fatal accident will occur in the month of July is P[X≤31], which
is
.
P[X ≤ 31] = 1 − 𝑒 =1−𝑒 = 0.7878.
The month of July has 31 days and the month of August has 31 days. If the month of July is
accident-free except for the accident on July 1. i.e., Total days are 62. Then the probability
that an accident occurs in August is:

i.e., 𝑃[𝑌 ≤ 𝑥|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥] ⇒ 𝑃[𝑋 − 𝑎 ≤ 𝑥|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥]

⇒ 𝑃[𝑋 ≤ 𝑥 + 𝑎|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥] ⇒ 𝑃[𝑋 > 𝑥 + 𝑎|𝑋 > 𝑎] = 𝑃[𝑋 > 𝑥].

P[X≤62│X>31] = 1-P[X>62│X>31]

= 1-P[X>31]

= P[X≤31]

.
=1−𝑒 =1−𝑒 = 0.7878.

In this P[X≤62│X>31] = P[X≤31] is satisfied. The exponential distribution exhibits memory

less property.
If the occurrence of fatal accidents is a random event and furthermore, if the time
between two successive accidents is exponentially distributed, then there is no “memory” in
the waiting of the next fatal accident. Having a full month of no accidents has no bearing on
when the next fatal accident occurs.

(b) Given that X has exponential distribution with parameter 𝜃 = .

Then its C.D.F. is F(X) = 1 − 𝑒 .

By conditional probability of memory less property of exponential distribution is:

i.e., 𝑃[𝑌 ≤ 𝑥|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥] ⇒ 𝑃[𝑋 − 𝑎 ≤ 𝑥|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥]

⇒ 𝑃[𝑋 ≤ 𝑥 + 𝑎|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥] ⇒ 𝑃[𝑋 > 𝑥 + 𝑎|𝑋 > 𝑎] = 𝑃[𝑋 > 𝑥].
P[X>10│X>8] = P[X>8+2│X>8]= P[X>2] [∵P[X>8+2│X>8]= P[X>2] ]
= 1 – P[X≤2]
= 1 – F(2)

= 1 – (1 − 𝑒 )
P[X>10│X>8] = 1 − (1 − 𝑒 ) = 𝑒 = 0.6065.

(c ) Let X denote the distance between major cracks. Given that, Mean (μ)=5. Then, X is an
exponential random variable with 𝜇 = = 5 ⇒ 𝜃 = = 0.2 cracks/mile.
.
Then its C.D.F. is F(X) = 1 − 𝑒 .
Given that there are no cracks in the first 5 miles inspected, then the probability that there are
no major cracks in the next 15 miles  this shows lacks of memory less property of
exponential distribution.

By memory less property, we have

i.e., 𝑃[𝑌 ≤ 𝑥|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥] ⇒ 𝑃[𝑋 − 𝑎 ≤ 𝑥|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥]
⇒ 𝑃[𝑋 ≤ 𝑥 + 𝑎|𝑋 ≥ 𝑎] = 𝑃[𝑋 ≤ 𝑥] ⇒ 𝑃[𝑋 > 𝑥 + 𝑎|𝑋 > 𝑎] = 𝑃[𝑋 > 𝑥].
. .
P[X>15+5│X>5]=P[X>15]=∫ 0.2𝑒 𝑑𝑥 = [−𝑒 ] =𝑒 = 0.0498.
Conclusion:
The exponential distribution satisfies lacks of memory less property by the above three
problems:

(a) The probability that there will be another fatal accident in the following month (August)
is 0.7878.
(b) The computer system repair of the P(X>10│X>8) probability is 0.6065.
(c ) The probability that there are no major cracks in the next 15 miles is 0.0498.
 Practical-14

Application of Weibull Distribution

Q. (a) The service life in hours of semiconductor is a random variable having a Weibull
distribution with α=0.025 and β=0.50.
(i) How long can such a semiconductor be expected to last?
(ii) What is the probability that such a semiconductor will still be in operating condition after
4,000 hours.
(b) The lifetime of a certain kind of an emergency backup battery (in hours) is a random
variable X having the Weibull distribution with α=0.10 and β=0.50. Find
(i) The mean lifetime of these batteries;
(ii) The probability that such a battery will last more than 300 hours.

Aim: (a) (i) To find the probability of life time of a semiconductor be expected to last.
(ii) To find the probability that such a semiconductor will still be in operating condition after
4,000 hours.
(b) (i) To find the mean lifetime of an emergency backup batteries (in hours).
(ii) To find the probability of an emergency backup battery will last more than 300 hours.

Procedure:
Let X follows Weibull distribution of the parameters (α,β) with probability density function is

𝑓(𝑥; 𝛼, 𝛽) = 𝛼𝛽𝑥 𝑒 ; 𝛼 > 0, 𝛽 > 0, 𝑥 > 0

0; 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑒

𝑀𝑒𝑎𝑛(𝜇) = ⁄

Calculations:
(a) Given that α=0.025 and β=0.50.

(i) The life service of a semiconductor be expected to last is

1
Γ 1+ 1
𝛽 ⁄
𝑀𝑒𝑎𝑛(𝜇) = ⁄
=𝛼 Γ 1+
𝛼 𝛽
⁄ .
⇒ 𝜇 = (0.025) Γ 1+ = (0.025) Γ(1 + 2) = (1600)Γ(3)
.

⇒ 𝜇 = (1600)(2!) = 3200 hours.

(ii) Probability of a semiconductor will still be in operating condition after 4,000 hours is
𝐹(𝑥) = ∫ 𝛼𝛽𝑥 𝑒 𝑑𝑥

. ( . ) .
𝑃[𝑋 > 4000] = (0.025)(0.5)𝑥 𝑒 𝑑𝑥

. ( . ) .
𝑃[𝑋 > 4000] = (0.0125)𝑥 𝑒 𝑑𝑥

√
1 1
𝑃[𝑋 > 4000] = × 𝑒 𝑑𝑥
80 √𝑥
√
put 𝑢 = ⇒ 𝑑𝑢 = 𝑑𝑥
√

√
𝑃[𝑋 > 4000] = − ∫ 𝑒 𝑑𝑢 = − ( )
= [−𝑒 ] = −𝑒

√ √ × √
𝑃[𝑋 > 4000] = − 𝑒 −𝑒 =𝑒 =𝑒 = 0.2057.

(b) Given that α=0.10 and β=0.50.

(i) Mean lifetime of these batteries is
𝜇 = 𝐸(𝑋) = ∫ 𝑥𝑓(𝑥)𝑑𝑥 = ∫ 𝑥𝛼𝛽𝑥 𝑒 𝑑𝑥 = ∫ 𝛼𝛽𝑥 𝑒 𝑑𝑥

put 𝑢 = 𝛼𝑥 ⇒ 𝑑𝑢 = 𝛼𝛽𝑥 𝑑𝑥 and 𝑥 = ⇒𝑥=𝑢 𝛼

⁄ .
𝜇=𝛼 ∫ 𝑢 𝑒 𝑑𝑢 = 𝛼 Γ 1+ = (0.1) Γ 1+ = (100)(2!) = 200 hours.
.

∴μ=Mean lifetime of batteries is 200 hours.

(ii) The probability of an emergency backup battery will last more than 300 hours.

. ( . ) .
𝐹(𝑥) = ∫ 𝛼𝛽𝑥 𝑒 𝑑𝑥 = ∫ (0.1)(0.5)𝑥 𝑒 𝑑𝑥
√
. ( . ) .
𝐹(𝑥) = ∫ (0.05)𝑥 𝑒 𝑑𝑥 = ∫ 𝑑𝑥
√

√
put 𝑢 = − ⇒ 𝑑𝑢 = 𝑑𝑥
√

⇒ −∫ 𝑒 𝑑𝑢 = 𝑒

. √
. ( . ) √
∴∫ 𝑥 𝑒 (0.5)(0.1)𝑑𝑥 = [−𝑒 ] = −𝑒 =𝑒 0.1769 ≅ 0.177.

Conclusion:
The following are the calculated results:
(a) (i) The probability of life time of a semiconductor be expected to last is 3,200 hours.
(ii) Probability of a semiconductor will still be in operating condition after 4,000 hours is
0.2057.
(b) (i) The mean lifetime of an emergency backup batteries is 200 hours.
(ii) The probability of an emergency backup battery will last more than 300 hours is 0.1769.
 Practical-15

Application of Logistic Distribution

Q. Fit a logistic distribution for a given data and obtain Logistic frequencies.

Class Interval 11-13 13-15 15-17 17-19 19-21 21-23 23-25

Frequencies 8 24 42 65 36 16 9
Aim: To fit a logistic distribution for a given data and obtain Logistic frequencies.

Procedure:

The probability density function of logistic distribution with parameters α and β is given by

𝑓(𝑥; 𝛼, 𝛽) = ; −∞ < 𝑥 < ∞; 𝛼, 𝛽 > 0, and C.D.F. is given by

𝐹 (𝑥) = .

Then we have to estimate the parameters of α, β of the logistic distribution by using the given
data. The estimates are obtained as:

∑ ∑
𝛼= Mean of the given frequency distribution= ∑
; zi=Mid value; But 𝑧̅ = .

𝛽 = Standard deviation of the given data= (∑ 𝑓 𝑧 − 𝑁𝛼 )

By substituting 𝛼 and 𝛽 in the p.d.f. we get fitted logistic distribution for the given data. To
obtain the expected frequencies first we have to compute F(xi).

∴ 𝐹(𝑥 ) = , where xi is the upper limit of the class interval then expected

frequencies are obtained as 𝑒 = 𝑁∆𝐹(𝑥 ); where ∆𝐹(𝑥 ) = 𝐹(𝑥 ) − 𝐹(𝑥 ).

Calculations:

For the given data:

Class Interval Frequencies (fi) 𝒛𝒊 𝒇𝒊 𝒛 𝒊 𝒇𝒊 𝒛𝟐𝒊

11 – 13 8 12 96 1152
13 – 15 24 14 336 4704
15 – 17 42 16 672 10752
17 – 19 65 18 1170 21060
19 – 21 36 20 720 14400
21 – 23 16 22 352 7744
23 – 25 9 24 216 5184
∑ 𝑓 =200 ∑ 𝑧 =126 ∑ 𝑓 𝑧 =3562 ∑ 𝑓 𝑧 = 64996

∑ 𝑓𝑧 3562
∴𝛼= = = 17.81
∑ 𝑓 200

∑ 𝑧 126
∴ 𝑧̅ = = = 18
𝑛 7

∴𝛽= (∑ 𝑓 𝑧 − 𝑁𝛼 ) = [64996 − (200)(17.81) ] = 2.79

∴ 𝐹(𝑥 ) =

1
𝑥 = 11 ⇒ 𝐹(𝑥 ) = = 0.0801
11 − 17.81
1 + 𝑒𝑥𝑝 −
2.79

1
𝑥 = 13 ⇒ 𝐹(𝑥 ) = = 0.1514
13 − 17.81
1 + 𝑒𝑥𝑝 −
2.79

1
𝑥 = 15 ⇒ 𝐹(𝑥 ) = = 0.2675
15 − 17.81
1 + 𝑒𝑥𝑝 −
2.79

1
𝑥 = 17 ⇒ 𝐹(𝑥 ) = = 0.4279
17 − 17.81
1 + 𝑒𝑥𝑝 −
2.79
 1
𝑥 = 19 ⇒ 𝐹(𝑥 ) = = 0.6050
19 − 17.81
1 + 𝑒𝑥𝑝 −
2.79

1
𝑥 = 21 ⇒ 𝐹(𝑥 ) = = 0.7583
21 − 17.81
1 + 𝑒𝑥𝑝 −
2.79

1
𝑥 = 23 ⇒ 𝐹(𝑥 ) = = 0.8653
23 − 17.81
1 + 𝑒𝑥𝑝 −
2.79

1
𝑥 = 25 ⇒ 𝐹(𝑥 ) = = 0.9294
25 − 17.81
1 + 𝑒𝑥𝑝 −
2.79

Class Intervals fi Upper Limit 𝑭(𝒙𝒊 ) ∆𝑭(𝒙𝒊 ) 𝒆𝒊 = 𝑵∆𝑭(𝒙𝒊 )

– ∞ – 11 – 11 0.0801 16.02
0.0801
11 – 13 8 13 0.0713 14.26
0.1514
13 – 15 24 15 0.1161 23.22
0.2675
15 – 17 42 17 0.1604 32.08
0.4279
17 – 19 65 19 0.1771 35.42
0.6050
19 – 21 36 21 0.1533 30.66
0.7583
21 – 23 16 23 0.1070 21.40
0.8653
23 – 25 9 25 0.0640 12.80
0.9294
25 – ∞ – ∞ 1 0.0706 14.12
∑ 𝑓 =200 ∑ 𝑒 = 199.98 ≅ 200

Conclusion:
Logistic distribution is fitted to the given data. Calculated expected frequencies. They
are 16.02, 14.26, 23.22, 32.08, 35.42, 30.66, 21.40, 12.80 and 14.12 respectively.
 Practical-16

Application of Cauchy Distribution

Q. (a) The distribution function of Cauchy distribution is 𝐹(𝑥) = 𝑇𝑎𝑛 + .

Let X follows C(2,4). Find the probability that

(i) X is less than 4,
(ii) X is greater than 5,
(iii) X is between 1 and 4.5.
(b) Assume some risky experiment leads to discrepancies (errors) which are distributed
according to the Cauchy distribution 𝑓(𝑥) = . Find the probability that the error is
( )

√
smaller than − .

Aim: (a) Let X ~ C(2,4) then to find the probability that (i) X is less than 4,
(ii) X is greater than 5, (iii) X is between 1 and 4.5.
√
(b) To find the probability that the error is smaller than− .

Procedure:
The distribution function of Cauchy distribution is

𝐹(𝑥) = + 𝑇𝑎𝑛 and the probability density function is

𝑓(𝑥) = ( )
; – ∞<x<∞.

Calculations:
(a) Given that μ=2, and λ=4.
The distribution function of Cauchy distribution is

𝐹(𝑥) = + 𝑇𝑎𝑛 ⇒ 𝐹(𝑥) = 0.5 + 𝑇𝑎𝑛

[Note: Put your calculator in radians then calculate Tan-1(0.5)=0.4636, because Cauchy
distribution measures circular wheel circumference.]
(i) The probability that X is less than 4 is
P[X≤4] = F(4)
.
= 0.5 + 𝑇𝑎𝑛 = 0.5 + 𝑇𝑎𝑛 (0.5) = 0.5 + = 0.6476
. .

(ii) The probability that X is greater than 5,

P[X>5] = 1 – P(X<5)=1 – F(5)
.
= 1 − 0.5 + 𝑇𝑎𝑛 = 0.5 − 𝑇𝑎𝑛 (0.75) = 0.5 − = 0.2952
. .
(iii) The probability that X is between 1 and 4.5 is
P[1≤X≤4.5] = P(X≤4.5) – P[X≤1]=F(4.5) – F(1)
.
= 0.5 + 𝑇𝑎𝑛 − 0.5 + 𝑇𝑎𝑛

= 𝑇𝑎𝑛 (0.625) − 𝑇𝑎𝑛 (−0.25)

= (0.5586) − (−0.245) = 0.2558

. .

√
(b) The probability that the error is smaller than− is
√
√ √ √
√ ( )
𝑃 𝑋<− =∫ 𝑓(𝑥)𝑑𝑥 = ∫ ( )
𝑑𝑥 = ∫ ( )
𝑑𝑥 =

√3 1 𝜋
𝑃 𝑋<− = −0.7137 + = −0.2272 + 0.5 = 0.2728
2 𝜋 2
Conclusion:
(a) (i) The probability that X is less than 4 is 0.6476.
(ii) The probability that X is greater than 5 is 0.2952.
(iii) The probability that X is between 1 and 4.5 is 0.2558.
√
(b) The probability that the error is smaller than− is 0.2728.