Continuous Distribution

MAT 3103: Computational Statistics and Probability

Chapter 6: Continuous Distribution

Continuous probability distribution:

A continuous probability distribution describes the probabilities of a continuous random
variable, which can take on any value within a given range. Since there are infinitely
many possible values, the probability of the variable taking on any one specific value is
zero.
In data science and machine learning, many models and algorithms rely on assumptions
about the probability distribution of data. Understanding continuous distributions helps in
identifying patterns and making predictions.

Normal distribution:
Everything in life is a trade-off. Some of us are born with high aptitudes for academic
learning, some are born with great physical skills, some are athletic, some are artistic and so
on. In terms of skills and talents, humans are wildly diversified. What we end up
accomplishing in life ultimately depends on our practice and effort, but we are all born with
different aptitudes and potentials.

Above is a normal curve which is quite simple. Let us consider the population of students in
AIUB. The horizontal axis represents how good they are at Math. Further to the right means
they’re really good, further to the left means they’re really bad. Now, notice that it gets really
thin at the far ends of the curve which means there are a few students who are really, really
good at Math, and a few students who are really, really bad. The majority of the students fall
into the mediocre middle. We can apply a “normal curve” in this way to tons of things in a
population in real life like height, weight, emotional maturity and so on.

1
 Continuous Distribution

Probability distribution of normal distribution:

Mathematically, the distribution of a normal variable X with mean μ and variance σ 2, denoted
by, X N ( μ, σ 2), is defined as:

( ) ; −∞ ≤ x ≤ ∞ .
2
−1 x−μ
f(x) = 1 e 2 σ

σ √2π

Characteristics of normal distribution:

a. The normal curve is bell-shaped as shown below-

b. Mean, median and mode of normal distribution coincide.

c. The normal curve is symmetric and mesokurtic.
x−μ
d. If X N( μ, σ 2), then Z = N( 0 , 1). This Z is called standard normal
σ
variable.
e. If 95% values of any variable fall in the limit x ± 2σ (i.e. x−¿ 2σ to x +2σ ), then this
variable is called normal variable, and follows normal distribution.
Example 6.1: The life length (in days) of electric bulb follows N (400, 5000). Find the
probability that the life length of a randomly selected bulb is (i) less than 450 days, (ii)
between 300 to 500 days, and (iii) more than 350 days. [N.B. Z – table is to be used to
calculate the probabilities]
Solution: Let, x be the life length (in days) of electric bulb.
Since, X N (400, 5000); we have, μ = 400, σ 2 = 5000 ∴ σ = √ 5000 =
70.71.

x−μ 450−400
i) P (X¿450) = P ( ¿ ) = P (Z ¿ 0.71) = 0.7611.
σ 70.71
300−400 x−μ 500−400
ii) P (300¿X¿500) = P ( <¿ ¿ ) = P (−¿1.41 ¿ Z ¿ 1.41)
70.71 σ 70.71
= P (Z ¿ 1.41) −¿ P (Z ←1.41) = 0.9207 – 0.0793 = 0.8414.
x−μ 350−400
iii) P (X¿350) = P ( ¿ ) = P (Z ¿ −¿0.71) = 1−¿ P (Z ≤ −¿0.71)
σ 70.71

2
 Continuous Distribution

= 1−¿ 0.2389 = 0.7611.

3
Continuous Distribution

4
 Continuous Distribution

Exponential distribution:
Exponential distribution is concerned with the amount of time until some specific event
occurs. There are fewer large values and more small values. The values of an exponential
random variable occur in this way. For example, the amount of money customers spend in a
trip to the supermarket follows an exponential distribution. There are more people who spend
small amounts of money and fewer people who spend large amounts of money.
Mathematically, the distribution of an exponential variable X is defined as:
1 −x
f(x) = λ ; x¿ 0, λ> ¿0.
λe
Here, X = service time / length of time / waiting time,
λ = average of service time / length of time / waiting time. Also, the variance is λ 2.
Here are more real-life applications in Bangladesh:
1️. Internet Downtime in Rural Areas
In many rural regions of Bangladesh, internet service interruptions occur unpredictably. The
time between two consecutive internet outages in a remote village using mobile broadband
or fiber optics follows an exponential distribution.
2️. Rainfall Duration in Monsoon Season
During the monsoon in Bangladesh, short spells of rain are more common than long
continuous downpours. If we measure how long a rain shower lasts before stopping, we
often find that most rains last for a short time, while long rainstorms are rarer.
3️. Queue at Mobile Recharge Shops
At a busy mobile recharge store in Motijheel or Gulistan, the time between two
consecutive customers arriving follows an exponential distribution. More often, customers
come within short intervals, but sometimes there is a longer wait.
4️. Call Center Wait Time (bKash, Nagad, GP, Banglalink)
If you call a customer care center (e.g., bKash, Nagad, Grameenphone, or Banglalink), the
waiting time before an agent picks up can be modeled using an exponential distribution.
During peak hours, short waiting times are more frequent, while long waits occur
occasionally.
5️. Power Outages in Rural Bangladesh
In some areas, particularly outside Dhaka and Chattogram, the time between two load-
shedding events follows an exponential pattern. Short gaps between outages are more
common than longer ones.
6️. Traffic Light Signal Changes

5
 Continuous Distribution

At major intersections in Dhaka (e.g., Shahbagh, Mohakhali, or Paltan), the time between
a red light turning green again follows an exponential distribution. Shorter intervals
between signal changes are more common than longer delays.
7️. Emergency Admissions at Hospitals
At hospitals like Dhaka Medical College or ICDDR, B, the arrival time of emergency
patients follows an exponential distribution. More patients come in within short time
intervals, and fewer long gaps occur.
8️. ATM Withdrawals in a Busy Area
At ATMs in areas like Bashundhara City or Jamuna Future Park, the time between two
people withdrawing money follows an exponential pattern. Shorter gaps are more common,
while sometimes, no one withdraws money for a long time.
9️. Water Supply Interruption in Dhaka WASA
In certain areas, the time between two interruptions in water supply follows an
exponential distribution. Shorter interruptions are more frequent, while longer gaps happen
occasionally.
10. Student Arrivals at Coaching Centers
In coaching centers like Udvash or Unmesh, the time between two students arriving for a
class follows an exponential pattern. More students arrive in quick succession, while longer
gaps are rare.
Formulas to calculate probabilities:
∝ ∝ −x
1 1 −x −x −x
P ( X ¿ x) = ∫ f (x ) dx = ∫e λ
dx = [ λ e λ ¿∝x = −¿(0−e λ ) = e λ .
x
λ x
λ
−x
P (X ¿ x) = 1−¿ e λ .
− x1 −x 2
P ( x 1 < ¿ X ¿ x 2) = e λ
−e λ .

Example 6.3: The average time needed to open a computer is 2 minutes. Find the probability
that a computer will be opened (i) after 3 minutes, (ii) before 2 minutes, (iii) within 2 to 3
minutes. If a man is in queue for half - an – hour, what is the probability that he will be able
to open the computer- (iv) after 35 minutes, (v) before 35 minutes, and (vi) within 32 to 35
minutes.
Solution: Let X be the time needed to open a computer. Given, λ = 2.
−x −3
(i) P (X ¿ 3) = e λ = e 2 = 0.2231
−x −2
(ii) P (X ¿ 2) = 1−¿ e λ = 1−¿ e 2 = 0.63212

6
 Continuous Distribution

−2 −3
(iii) P (2<¿ X ¿ 3) = e 2 −e 2 = 0.14478

(iv) As he is in queue for 30 minutes, he will open the computer after (35 −¿30) = 5
−x −5
minutes. P (X ¿ 5) = e λ = e 2 = 0.08208

(v) He will open the computer before (35−¿30) = 5 minutes.

−x −5
P (X ¿ 5) = 1−¿ e λ = 1−¿ e 2 = 1−¿ 0.08208 = 0.91792

(vi) He will open the computer within (32−¿30) = 2 minutes to (35−¿30) = 5 minutes.
−2 −5
P (2<¿ X ¿ 5) = e 2 −e 2 = 0.2858

Rayleigh distribution:
Mathematically, the distribution of a Rayleigh variable X is defined as:
x −x 2

f(x) = 2 σ ; x¿ 0, σ > ¿0.

2

σ e
2

Mean( average) x
Here, mode of the Rayleigh distribution, σ = = .
1.253 1.253
The Rayleigh distribution is used to model situations where values tend to cluster around a
lower range but can occasionally reach much higher values. It is often applied when the
magnitude of a variable depends on two or more independent components.

Real-Life Examples of Rayleigh Distribution in Bangladesh

1️. Wind Speed in Coastal Areas (Cox’s Bazar, Kuakata, Saint Martin's)
In coastal regions of Bangladesh, wind speed follows a Rayleigh distribution. Most of the
time, the wind blows at moderate speeds, but occasionally, strong gusts occur due to storms
or depressions in the Bay of Bengal.
👉 Example: During monsoon season, the average wind speed in Cox’s Bazar is around
12-15 km/h, but sudden strong gusts of 30-40 km/h can happen.

2️. Signal Strength of Mobile Networks (Grameenphone, Robi, Banglalink)

The strength of a mobile phone signal varies depending on environmental conditions,
obstacles, and distance from cell towers. The signal fading follows Rayleigh distribution.
👉 Example: In Dhaka, mobile signals are usually strong (e.g., -60 dBm), but in areas with
many buildings (e.g., Gulistan, Motijheel), some locations may have weak signals (-90 dBm
or lower).

7
 Continuous Distribution

3️. Sound Levels in a Dhaka Traffic Jam

Noise levels in busy intersections like Farmgate, Shahbagh, and Mohakhali typically
follow Rayleigh distribution. Most of the time, noise is moderate (70-90 dB), but
occasionally loud honks or sirens increase the intensity.
👉 Example:
 Normal traffic noise: 80 dB
 Occasional loud horns or sirens: 120 dB+

4️. Wave Heights in the Bay of Bengal

The height of sea waves follows a Rayleigh distribution. On most days, waves are small, but
during storms or cyclones, much larger waves occur.
👉 Example:
 Normal wave height near Cox’s Bazar: 0.5 – 1.5 meters
 During a storm: 5+ meters

5️. Lifespan of Electronic Devices (e.g., LED Bulbs, Fans, Mobile Phones)
The failure time of electronic components in Bangladesh follows a Rayleigh distribution.
Most products last close to their expected lifespan, but a few may fail much earlier or later
than expected.
👉 Example:
 Most LED bulbs last 2-3 years, but some fail after 6 months, while others work for
5+ years.

6️. Strength of Buildings During Earthquakes

During an earthquake, the shaking intensity varies depending on distance from the epicenter.
Structural damage distribution often follows a Rayleigh model.
👉 Example:
 In Sylhet (closer to earthquake zones), most buildings experience mild tremors, but
some suffer major cracks or collapse.

7️. Internet Speed in Rural Areas

In villages of Bangladesh, internet speed often follows a Rayleigh distribution. The
connection is usually slow, but sometimes, high-speed bursts occur.
👉 Example:

8
 Continuous Distribution

 Normal speed: 1-5 Mbps

 Occasional peaks: 15-20 Mbps

8️. Length of Fish in Rivers (Padma, Meghna, Jamuna)

In natural water bodies, most fish are of average size, but some grow significantly larger
than others, following a Rayleigh distribution.
👉 Example:
 Most Hilsa fish weigh 600-900g, but some grow to 2kg or more.

9️. Waiting Time for Public Transport in Dhaka

In Dhaka’s public transport system, waiting times for buses and rickshaws are usually
short, but occasionally, long waits occur due to traffic congestion.
👉 Example:
 Average wait for a bus: 5-10 minutes
 During traffic jams: 30+ minutes

🔟 Delivery Time for Online Orders (Daraz, Pathao, Foodpanda)

The time taken to deliver an order is mostly within a predictable range, but sometimes,
long delays happen.
👉 Example:
 Normal delivery time: 30-60 minutes
 During heavy rain or traffic: 2+ hours

Formulas to calculate probabilities:

2
∝ ∝ −x
x
2
−x
P (X ¿ x) = ∫ f (x ) dx = ∫ 2 e 2 σ dx = e 2 σ
2
2

x x σ
2
−x
P (X ¿ x) = 1−¿ e 2 σ 2

2 2
− x1 −x 2
P ( x 1< ¿ X ¿ x 2) = e 2 σ −e 2 σ
2 2

Example 6.4: The average wind speed of a day is 4.5 (knots). Find the probability that in a
randomly selected day, the wind speed (i) will exceed 4 knots, (ii) will be less than 3 knots,
and (iii) will be between 2 to 5 knots.

9
 Continuous Distribution

x 4.5
Solution: Let, X be the wind speed. Given, x = 4.5; then, σ = = = 3.59.
1.253 1.253
2
−4
(i) P (X ¿ 4) = 2(3.59)
2
= 0.5376
e
2
−3
(ii) P (X ¿ 3) = 1−¿ 2(3.59)
2
= 0.2947
e
2 2
−2 −5
(iii) P (2<¿ X ¿ 5) = 2(3.59)
2
2(3.59)
2
= 0.4772
e −e

Example 6.5: The mode of the density of faded out signal is 0.5. Find the probability that the
density will be (i) more than 0.8, (ii) less than 0.4, and (iii) between 0.4 to 0.6.
Solution: Let, X be the density of faded out signal. Given, σ = 0.5.
2
−0.8
(i) P (X ¿ 0.8) = 2(0.5)
2
= 0.278
e
2
−0.4
(ii) P (X ¿ 0.4) = 1−¿ 2(0.5)
2
= 0.2739
e
2 2
−0.4 −0.6
(iii) P (0.4 <¿ X ¿ 0.6 ) = 2(0.5)
2
2 (0.5)
2
= 0.2393
e −e

Exercises
6.1. Vehicle Speed on Dhaka-Chattogram Highway
The speeds of vehicles on the Dhaka-Chattogram highway are normally distributed with a
mean speed of 80 km/hour and a standard deviation of 12 km/hour. What is the probability
that a randomly selected vehicle is traveling at more than 95 km/hour?

6.2. Mobile Battery Life of a Student

The battery life of a smartphone (e.g., a Walton or Symphony phone) is normally
distributed with a mean of 48 hours and a variance of 196 hours. Rakib wants to know the
probability that his phone's battery will last between 45 and 65 hours before needing a
recharge.

6.3. BUET Admission Test

Admission to BUET is based on an entrance exam. Scores on this test follow a normal
distribution N(600, 1200). Naim wants to get admitted to BUET, and he knows that he must
score better than at least 75% of students. He scored 690 in the test. Will he be able to
secure admission?

10
 Continuous Distribution

6.4. HSC Math Exam Scores

Many HSC students in Bangladesh took a mathematics exam. The final scores have a mean
of 65 and a standard deviation of 15. If we approximate the distribution using a normal
distribution, what percentage of students scored less than 80?

6.5. Bank Queue at Sonali Bank

The average waiting time for a customer at Sonali Bank is 18 minutes. Find the probability
that a customer will be served:
i) before 30 minutes,
ii) between 15 to 25 minutes, and
iii) after 28 minutes.

6.6. Internet Speed in Dhaka

The internet speed in Dhaka city is normally distributed with a mode of 12 Mbps. Find the
probability that a randomly selected user will experience a speed:
i) between 8 to 15 Mbps,
ii) more than 10 Mbps.

6.7. Wind Speed in Cox’s Bazar

The average wind speed in Cox’s Bazar is 0.75 knots. Find the probability that on a
randomly chosen day, the wind speed will be:
i) less than 0.6 knots,
ii) exceed 1.0 knots,
iii) between 0.5 to 0.8 knots.

6.8. Summer Temperature in Rajshahi

The maximum temperature in Rajshahi during summer follows a normal distribution
with a mean of 35°C and a standard deviation of 4°C. Find the probability that the
temperature on a randomly selected day will be between 32°C and 38°C.

6.9. Signal Transmission Time in Teletalk Network

The time required to send a signal from a server to a user in Teletalk’s network follows a
normal distribution with a mean of 6 minutes. Find the probability that a signal will be sent:
11
 Continuous Distribution

i) before 320 seconds,

ii) after 250 seconds.

6.10. Car Assembly Time in Pragati Industries

The time taken to assemble a car in Pragati Industries Ltd. follows a normal distribution
N(25, 9). What is the probability that a car can be assembled in:
i) less than 24.5 hours,
ii) between 25 and 28 hours?

6.11. Salaries of Software Engineers in Dhaka

The annual salaries of software engineers in Dhaka are approximately normally distributed
with a mean of TK 8,00,000 and a standard deviation of TK 3,00,000.
i) What percentage of engineers earn less than TK 6,00,000?
ii) What percentage earn between TK 7,50,000 and TK 10,50,000?

6.12. Waiting Time for Buses in Mirpur

The average waiting time for a bus in Mirpur (Dhaka) is 20 minutes. If a commuter waits
for 40 minutes, find the probability that:
i) he will board the bus between 45 to 60 minutes,
ii) he will wait more than 50 minutes,
iii) he will get the bus before 75 minutes.

12