0% found this document useful (0 votes)
62 views10 pages

Module 4 Continuous Probability Distributions

The document discusses the normal distribution, which is the most commonly used continuous probability distribution in statistics. It provides a good model for many continuous populations. A normal random variable X has a probability density function that is defined by its mean μ and variance σ^2. The normal distribution is denoted by N(μ, σ). An example is provided to derive the cumulative distribution function (CDF) and calculate the probability that a measurement exceeds a given value, for a normal distribution with known mean and variance.

Uploaded by

hyuka kai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
62 views10 pages

Module 4 Continuous Probability Distributions

The document discusses the normal distribution, which is the most commonly used continuous probability distribution in statistics. It provides a good model for many continuous populations. A normal random variable X has a probability density function that is defined by its mean μ and variance σ^2. The normal distribution is denoted by N(μ, σ). An example is provided to derive the cumulative distribution function (CDF) and calculate the probability that a measurement exceeds a given value, for a normal distribution with known mean and variance.

Uploaded by

hyuka kai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution

Normal Distribution

CE 29 Continuous The normal distribution (also


Probability and Statistics called the Gaussian

Probability density, f(x)


for Engineering Probability distribution) is by far the
most commonly used
Course Instructor:
Distributions distribution in statistics. This
distribution provides a good
JUSTIN JESSE L. SERANILLA
Assistant Professor
Institute of Civil Engineering
Normal Distribution | Normal Approximation to Binomial
and Poisson Distribution | Lognormal Distribution |
model for many, although not
University of the Philippines Diliman
Exponential Distribution | Erlang and Gamma all, continuous populations.
Course Material by: Distributions | Continuous Uniform Distribution
REYGIE Q. MACASIEB

UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 2

1 2

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution

Normal Distribution Assume that the current measurements in a strip of wire follow a normal
distribution with a mean of 10 milliamperes and a variance of 4 (milliamperes)2.
Probability density, f(x)

A random variable X with probability Derive the CDF and determine the probability that a measurement exceeds 13
density function milliamperes?

1
𝑓 𝑥 = 𝑒
𝜎 2𝜋

is a normal random variable with


parameters 𝜇, where −∞ < 𝜇 < ∞, and 1
𝜎 > 0. Also, 𝑃 𝑋 > 13 = 𝑒
𝜎 2𝜋
𝐸 𝑋 = 𝜇 and 𝑉 𝑋 = 𝜎

and the notation 𝑁(𝜇, 𝜎 ) is used to


denote the distribution
UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 3 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 4

3 4
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution

Normal Distribution Standard Normal Random Variable


The proportion of a normal population that A normal random variable with
is within a given number of standard 𝜇 = 0 𝑎𝑛𝑑 𝜎2 = 1
deviations of the mean is the same for any is called a standard normal random
normal population. variable and is denoted as Z.

For this reason, when dealing with normal The probability distribution function of a
populations, we often convert from the standard normal random variable is:
units in which the population items were 1
originally measured to standard units. 𝑓 𝑧 = 𝑒 𝑓𝑜𝑟 − ∞ < 𝑧 < ∞
2𝜋
For any normal random variable,
𝑃(𝜇 – 𝜎 < 𝑋 < 𝜇 + 𝜎) = 0.6827 Standard units tell how many standard The cumulative distribution function is :
𝑃(𝜇 – 2𝜎 < 𝑋 < 𝜇 + 2𝜎) = 0.9545 deviations an observation is from the
𝑃(𝜇 – 3𝜎 < 𝑋 < 𝜇 + 3𝜎) = 0.9973 population mean. 1
Φ 𝑧 = 𝑃 𝑍 ≤ 𝑧 = 𝑒 𝑑𝑧 −3 −2 −1 0 1 2 3
2𝜋
UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 5 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 6

5 6

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution

Standardizing a Normal Random Variable


Example 4.1a
Suppose that the current measurements in a strip of wire are assumed to follow
a normal distribution with 𝜇 = 10 and 𝜎 = 2 𝑚𝐴, what is the probability that the
Suppose X is a normal random variable with mean 𝜇 and variance 𝜎 ,
current measurement is between 9 and 11 mA?
the random variable
(𝑋 − 𝜇)
𝑍= Answer
𝜎

is a random variable with 𝐸(𝑍) = 0 and 𝑉(𝑍) = 1

The probability is obtained by using the Cumulative Standard Normal


Distribution Table.

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 7 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 8

7 8
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution

Example 4.1b Example 4.2


Suppose that the current measurements in a strip of wire are assumed to follow Statistical analysis of vehicular accidents show
a normal distribution with 𝜇 = 10 and 𝜎 = 2 𝑚𝐴. Determine the value x for that the annual vehicle miles (i.e. miles per
which there is 0.98 probability that a current measurement is below x. vehicle per year) driven between traffic accidents
(of all severities) can be represented by a normal
random variable with a mean of 15,000 miles per
Answer
year and coefficient of variation (𝑐𝑜𝑣 = ) of
25%. For a typical driver who drives 10,000 miles
per year,
a. What is the probability of him/her having an accident in a year?
b. If the driver has driven 8000 miles in a given year without encountering any
accident, what is the probability of his her having an accident for the
remainder of the year?

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 9 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 10

9 10

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Approximation to Binomial and Poisson Distribution

Central Limit Theorem Assume that the number of asbestos particles in a square
meter of dust on a surface follows a Poisson distribution
Let 𝑋1, … , 𝑋𝑛 be a random sample from a population with mean  and variance 2. with a mean of 1000. If a square meter of dust is analyzed,
The sample mean is given by 𝑋 =
⋯ what is the probability that 950 or fewer particles are
found?
Let 𝑆 = 𝑋 + 𝑋 + ⋯ + 𝑋 be the sum of the sample observations. Then if n is
sufficiently large, X – number of asbestos in a square meter
𝜆 = 1000
𝜎
𝑋 ~𝑁 𝜇, and 𝑆 ~𝑁(𝑛𝜇, 𝑛𝜎 ) 𝑒 1000
𝑛 𝑃 𝑋 ≤ 950 =
𝑥!

…too hard manually

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 11 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 12

11 12
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Approximation to Binomial and Poisson Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Approximation to Binomial and Poisson Distribution

Normal Approximations Normal Approximations to Binomial Distribution


If 𝑋 is a random variable with parameters 𝑛 and 𝑝,
The binomial and Poisson distributions become
more bell-shaped and symmetric as their mean 𝑋 − 𝑛𝑝
value increase. 𝑍=
𝑛𝑝(1 − 𝑝)
is approximately a standard normal random variable.
For manual calculations, the normal To approximate a binomial probability with a normal
approximation is practical – exact probabilities of
the binomial and Poisson, with large means, distribution, a continuity correction is applied as
require technology (Minitab, Excel). follows:
𝑥 + 0.5 − 𝑛𝑝
𝑃 𝑋 ≤ 𝑥 = 𝑃 𝑋 ≤ 𝑥 + 0.5 ≈ 𝑃 𝑍 ≤
The normal distribution is a good approximation 𝑛𝑝 1 − 𝑝
for: and
• Binomial if np > 5 and np(1-p) > 5. 𝑥 − 0.5 − 𝑛𝑝
• Poisson if λ > 5. 𝑃 𝑋 ≥ 𝑥 = 𝑃 𝑋 ≥ 𝑥 − 0.5 ≈ 𝑃 𝑍 ≥
𝑛𝑝 1 − 𝑝
UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 13 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 14

13 14

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Approximation to Binomial and Poisson Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Approximation to Binomial and Poisson Distribution

Normal Approximations to Poisson Distribution Example 4.3


If 𝑋 is a Poisson random variable with 𝐸 𝑋 = 𝜆 and In a digital communication channel, assume that the
𝑉 𝑋 = 𝜆, number of bits received in error can be modeled by a
𝑋−𝜆 binomial random variable. The probability that a bit is
𝑍=
𝜆 received in error is 10 . If 16 million bits are
is approximately a standard normal random variable. transmitted, what is the probability that 150 or fewer
The approximation is good for 𝜆 ≥ 5 errors occur?
To approximate a Poisson probability with a normal Answer
distribution, a continuity correction is applied as
follows:
𝑥 + 0.5 − 𝜆
𝑃 𝑋 ≤ 𝑥 = 𝑃 𝑋 ≤ 𝑥 + 0.5 ≈ 𝑃 𝑍 ≤ Image source: https://vrcacademy.com/tutorials/normal-approximation-poisson-distribution/

𝜆
and
𝑥 − 0.5 − 𝜆
𝑃 𝑋 ≥ 𝑥 = 𝑃 𝑋 ≥ 𝑥 − 0.5 ≈ 𝑃 𝑍 ≥
𝜆
UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 15 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 16

15 16
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Normal Approximation to Binomial and Poisson Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Lognormal Distribution

Example 4.4 Lognormal Distribution


A high-volume printer produces minor print-quality errors on a
test pattern of 1000 pages of text according to a Poisson For data that are highly skewed or
distribution with a mean of 0.4 per page.
a. What is the mean number of pages with errors (one or
that contain outliers, the normal
more)? distribution is generally not
b. Approximate the probability that more than 350 pages appropriate.
contain errors (one or more).

Answer The lognormal distribution, which is


related to the normal distribution, is
often a good choice for these data
sets.

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 17 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 18

17 18

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Lognormal Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Lognormal Distribution

Lognormal Distribution Example 4.5


The lifetime of a semiconductor laser has a lognormal
Let 𝑊 denote a normal random variable with mean 𝜃 and variance 𝜔2, then distribution with 𝜃 = 10 and 𝜔 = 1.5 hours.
𝑋 = 𝑒 is a lognormal random variable with probability density function: a. What is the probability that the lifetime exceeds
10,000 hours?
1 b. What lifetime is exceeded by 99% of lasers?
𝑓 𝑥 = 𝑒 0<𝑥<∞
𝑥𝜔 2𝜋
Answer
The mean and variance of X are

𝐸 𝑋 =𝑒
𝑉 𝑋 =𝑒 (𝑒 − 1)

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 19 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 20

19 20
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Lognormal Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Lognormal Distribution

Example 4.6
The drainage from a community during a storm has
𝜇 = 1.2 million gallons per day (mgd) and 𝜎 = 0.4
mgd. If the storm drain system is designed with a
maximum drainage capacity of 1.5 mgd, and it can be
defined by a lognormal distribution,
a. What is the probability of flooding during a storm
that is assumed in the design of the drainage
system?
b. What is the probability that the drainage flow
during a storm is between 1.0 mgd and 1.6 mgd?
c. What is the 90th percentile drainage load from the
community during a storm?

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 21 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 22

21 22

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Exponential Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Exponential Distribution

Recall in discrete probability distribution…


Exponential Distribution
X trials (Bernoulli trials) X trials (Bernoulli trials) X trials (Bernoulli trials)

The random variable 𝑋 that equals the distance between successive events of a
Geometric Distribution Geometric Distribution Geometric Distribution Poisson process with mean number of events 𝜆 > 0 per unit interval is an
Probability of X trials until Probability of X trials until Probability of X trials until exponential random variable with parameter 𝜆. The probability density function of
recurrence recurrence recurrence X is:
_
𝑓 𝑥 = 𝜆𝑒 𝜆𝑥 𝑓𝑜𝑟 0 ≤ 𝑥 < ∞
Similarly…
X=space/time (Poisson Process) X=space/time (Poisson Process) X=space/time (Poisson Process) If a random variable 𝑋 has an exponential distribution with parameter 𝜆.
1 1
Exponential Distribution Exponential Distribution Exponential Distribution 𝜇=𝐸 𝑋 = 𝜎 =𝑉 𝑋 =
𝜆 𝜆
Probability of space/time (X) Probability of space/time (X) Probability of space/time (X)
until recurrence until recurrence between until recurrence Note:
• Poisson distribution : Mean and variance are same.
• Exponential distribution : Mean and standard deviation are same.
UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 23 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 24

23 24
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Exponential Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Exponential Distribution

Example 4.7
In a large corporate computer network, user log-ons
to the system can be modeled as a Poisson process
with a mean of 25 log-ons per hour.
a. What is the probability that there are no log-ons in
the next 6 minutes (0.1 hour)?
b. What is the probability that the time until the next
log-on is between 2 and 3 minutes (0.033 & 0.05
hours)?
c. What is the interval of time such that the probability
that no log-on occurs during the interval is 0.90?
d. What is the mean and standard deviation of the time
until the next log-in?

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 25 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 26

25 26

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Erlang and Gamma Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Erlang and Gamma Distribution

Recall in discrete probability distribution…


X trials (Bernoulli trials) X trials (Bernoulli trials) X trials (Bernoulli trials)
The failures of CPUs of large computer systems are often
modeled as a Poisson process. Assume that units that fail are
repaired immediately and the mean number of failures per hour
Geometric Distribution Geometric Distribution Geometric Distribution is 0.0001. Let 𝑋 denote the time until 4 failures occur. What is
Probability of X trials until Probability of X trials until Probability of X trials until
the probability that 𝑋 exceed 40,000 hours?
recurrence recurrence recurrence
Negative Binomial Distribution
Let the random variable 𝑁 denote the number of failures in 40,000 hours.
Probability of X trials until r occurrences The time until 4 failures occur exceeds 40,000 hours if and only if the number of failures
Similarly…
X=space/time (Poisson Process) X=space/time (Poisson Process)
in 40,000 hours is ≤ 3.
X=space/time (Poisson Process)

𝑃 𝑋 > 40,000 = 𝑃(𝑁 ≤ 3)


Exponential Distribution Exponential Distribution Exponential Distribution 𝜆 = 40,000 0.0001 = 4 failures in 40,000 hours
Probability of space/time (X) Probability of space/time (X) Probability of space/time (X)
between recurrence between recurrence between recurrence 𝑒 4
𝑃 𝑁≤3 = = 0.433
Erlang (and Gamma) Distribution 𝑘!
Probability of space/time (X) until r occurrences
UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 27 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 28

27 28
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Erlang and Gamma Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Erlang and Gamma Distribution

Erlang Distribution Gamma Distribution

The random variable X with probability density function:


Generalizing from the prior exercise:
 r x r 1e   x
𝑒 𝜆𝑥 f  x  , for x  0 (4-18)
𝑃 𝑋>𝑥 =
𝑘!
= 1 − 𝐹(𝑥)  r 

is a gamma random variable with parameters λ > 0 and r > 0. If r is an integer,


Now differentiating F(x): then X has an Erlang distribution.

If X is a gamma random variable with parameters λ and r,


𝜆 𝑥 𝑒
𝑓 𝑥 = for 𝑥 > 0 and 𝑟 = 1,2, …
𝑟−1 !
𝜇 = 𝐸 𝑋 = and 𝜎2 = 𝑉 𝑋 =
UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 29 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 30

29 30

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Erlang and Gamma Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Erlang and Gamma Distribution

Gamma Function Example 4.8


In a data communication system, several
The gamma function is the generalization of the factorial function messages that arrive at a node are bundled into a
for r > 0, not just non-negative integers. packet before they are transmitted over the
network. Assume the messages arrive at the
node according to a Poisson process with 𝜆 = 25
Γ 𝑟 = 𝑥 𝑒 𝑑𝑥 , for 𝑟 > 0
messages per minute. Five messages are used to
form a packet.
Properties of the gamma function a. What is the mean time until a packet is formed, that is, until five messages
Γ 𝑟 = 𝑟 − 1 Γ(𝑟 − 1) recursive property have arrived at the node?
Γ 𝑟 = 𝑟−1 ! factorial property b. What is the standard deviation of the time until a packet is formed?
Γ 1 = 0! = 1 c. What is the probability that a packet is formed in less than 12 seconds?
Γ = 𝜋 / = 1.77 useful if manual d. What is the probability that a packet is formed in less than 6 seconds?

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 31 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 32

31 32
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Erlang and Gamma Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Continuous Uniform Distribution

Continuous Uniform Distribution

This is the simplest continuous distribution and analogous to its discrete


counterpart.

A continuous random variable 𝑋 with probability density function

1
𝑓 𝑥 = 𝑓𝑜𝑟 𝑎 ≤ 𝑥 ≤ 𝑏
𝑏−𝑎

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 33 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 34

33 34

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.
CONTINUOUS PROBABILITY DISTRIBUTIONS  Continuous Uniform Distribution CONTINUOUS PROBABILITY DISTRIBUTIONS  Continuous Uniform Distribution

Mean and Variance of Continuous Uniform Distribution Example 4.9


The random variable X has a continuous uniform distribution on [4.9, 5.1]. The
𝑎+𝑏 𝑏−𝑎 probability density function of X is 𝑓(𝑥) = 5 , 4.9 ≤ 𝑥 ≤ 5.1 . What is the
𝜇=𝐸 𝑋 = 𝜎 =𝑉 𝑋 =
2 12 probability that a measurement of current is between 4.95 & 5.0 mA? What is
the mean and the variance?
CDF of Continuous Uniform Distribution
Answer
x
1 xa
F  x   du 
a 
b  a ba
The Cumulative distribution function is
0 xa
F  x    x  a   b  a  a  x  b
1 b x

UNIVERSITY OF THE PHILIPPINES DILIMAN UNIVERSITY OF THE PHILIPPINES DILIMAN


INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 35 INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 36

35 36
2021

CONTINUOUS PROBABILITY DISTRIBUTIONS  Continuous Uniform Distribution

BEFORE YOU PROCEED… QUESTIONS?


Example 4.10
The thickness of a flange on an aircraft component is uniformly [email protected]
distributed between 0.95 and 1.05 mm.
a. Determine the cumulative distribution function of flange thickness.
b. Determine the proportion of flanges that exceeds 1.02 mm.
Post in course page forum
c. What thickness is exceeded by 90% of the flanges?
d. Determine the mean and variance of flange thickness

Answer

This Institutional Work is


EXCLUSIVELY OWNED by References
UP and ICE Montgomery D.C. and Runger G.C, Applied Statistics and Probability for Engineers 6th ed. John Wiley and Sons, 2014
Do not distribute without Devore, J.L. Probability and Statistics for Engineering and the Sciences 9th ed. Brookes/COLE USA, 2015.
the permission of the Ang, A.H-S., and Tang, W.H. Probability Concepts in Engineering: Emphasis on Applications to Civil and Environmental
author/s or the institution. Engineering. 2nd ed. New York, NY: John Wiley & Sons, 2006
UNIVERSITY OF THE PHILIPPINES DILIMAN
INSTITUTE OF CIVIL ENGINEERING CE 29: Probability and Statistics for Engineering 37 Photographs are taken from Google, Bing and/or licensed under creativecommons.org

37 38

This material has been reproduced and communicated to you by or on behalf of University of the Philippines pursuant to PART IV: The Law on Copyright of Republic Act (RA) 8293 or the “Intellectual
Property Code of the Philippines”.
The University does not authorize you to reproduce or communicate this material. The Material may contain works that are subject to copyright protection under RA 8293. Any reproduction and/or
communication of the material by you may be subject to copyright infringement and the copyright owners have the right to take legal action against such infringement.

You might also like