IE4102 Lecture1

IE 4102 Statistics for Engineers
Lecture 1: Probability Basics
Assist. Prof. Duygun Fatih Demirel
Spring 2024
Copyright © 2014 John Wiley & Sons, Inc. All rights reserved.
What Engineers Do?
An engineer is someone who solves problems of

interest to society with the efficient application of
scientific principles by:
• Refining existing products
• Designing new products or processes
The Usage of Statistics in
Engineering
The Creative Process
Figure 1-1 The engineering method
Statistics Supports The Creative Process
The field of statistics deals with the collection,

presentation, analysis, and use of data to:
• Make decisions
• Solve problems
• Design products and processes
It is the science of data.
Variability
• Statistical techniques are useful to describe
and understand variability.
• By variability, we mean successive observations
of a system or phenomenon do not produce
exactly the same result.
• Statistics gives us a framework for describing this
variability and for learning about potential
sources of variability.
6
An Engineering Example of Variability
Eight prototype units are produced and their pull-off forces are measured (in
pounds): 12.6, 12.9, 13.4, 12.3, 13.6, 13.5, 12.6, 13.1.
All of the prototypes does not have the same pull-off force. We can see the
variability in the above measurements as they exhibit variability.
The dot diagram is a very useful plot for displaying a small body of data -
say up to about 20 observations.
This plot allows us to see easily two features of the data; the location, or
the middle, and the scatter or variability.
Figure 1-2 Dot diagram of the pull-off force data.
Basic Methods of Collecting Data
Three basic methods of collecting data:

– A retrospective study using historical data
• Data collected in the past for other purposes.
– An observational study
• Data, presently collected, by a passive
observer.
– A designed experiment
• Data collected in response to process input
changes.
Hypothesis Tests
Hypothesis Test
• A statement about a process behavior value.
• Compared to a claim about another process value.
• Data is gathered to support or refuse the claim.
One-sample hypothesis test:

• Example: Ford avg mpg = 30
vs
Ford avg mpg < 30
Two-sample hypothesis test:

• Example: Ford avg mpg – Chevy avg mpg = 0
vs
Ford avg mpg – Chevy avg mpg > 0
Sec 1-2.4 Designed Experiments 9
Factorial Experiment & Example
An experiment design which uses every possible combination
of the factor levels to form a basic experiment with “k”
different settings for the process. This type of experiment is
called a factorial experiment.
Example:
Consider a petroleum distillation column:
• Output is acetone concentration

• Inputs (factors) are:
1. Reboil temperature
2. Condensate temperature
3. Reflux rate
• Output changes as the inputs are changed by experimenter.

Sec 1.2.4 Designed Experiments 10
Factorial Experiment Example
• Each factor is set at 2 reasonable levels (-1 and +1)
• Resultant data is used 8 (23) runs are made, at every
combination of factors, to observe acetone output.
• To create a mathematical model of the process representing
cause and effect.
Table 1-1 The Designed Experiment (Factorial Design) for the Distillation Column
Sec 1-2.4 Designed Experiments 11
Mechanistic and Empirical Models
A mechanistic model is built from our underlying knowledge of
the basic physical mechanism that relates several variables.
Example: Ohm’s Law
Current = Voltage/Resistance
I = E/R
I = E/R + 
where  is a term added to the model to account for the fact that
the observed values of current flow do not perfectly conform to
the mechanistic model.
• The form of the function is known.
Sec 1-3 Mechanistic & Empirical Models 12
Mechanistic and Empirical Models
An empirical model is built from our engineering

and scientific knowledge of the phenomenon, but
is not directly developed from our theoretical or
first-principles understanding of the underlying
mechanism.
The form of the function is not known a priori.
An Example of an Empirical Model
• In a semiconductor manufacturing plant, the

finished semiconductor is wire-bonded to a frame.
In an observational study, the variables recorded
were:
• Pull strength to break the bond (y)
• Wire length (x1)
• Die height (x2)
• The data recorded are shown on the next slide.
Table 1-2 Wire Bond Pull Strength Data
Pull ෣
strength = 𝛽0 + 𝛽1 wire length + 𝛽2 die height + 𝜀
where the “hat,” or circumflex, over pull strength

indicates that this is an estimated or predicted quality.
In general, this type of empirical model is called a

regression model.
The estimated regression relationship is given by:
Pull ෣
strength = 2.26 + 2.74 wire length + 0.0125 die height
Visualizing the Data
Figure 1-6 Three-dimensional plot of the pull strength (y),

wire length (x1) and die height (x2) data.
Visualizing the Resultant Model Using Regression Analysis
Figure 1-7 Plot of the predicted values (a plane) of pull

strength from the empirical regression model.
Models Can Also Reflect Uncertainty
• Probability models help quantify the risks involved in

statistical inference, that is, risks involved in decisions
made every day.
• Probability provides the framework for the study and
application of statistics.
•Probability concepts will be introduced in the next
lecture.
Sec 1-4 Probability & Probability Models 19
Random Experiment
• An experiment is a procedure that is
– carried out under controlled conditions, and
– executed to discover an unknown result.
• An experiment that results in different
outcomes even when repeated in the
same manner every time is a random
experiment.
20
Sample Spaces
• The set of all possible outcomes of a

random experiment is called the
sample space, S.
• S is discrete if it consists of a finite or
countable infinite set of outcomes.
• S is continuous if it contains an
interval of real numbers.
21
Example 2-1: Defining Sample
Spaces
• Randomly select a camera and record the recycle time of
a flash. S = R+ = {x | x > 0}, the positive real numbers.
• Suppose it is known that all recycle times are between 1.5
and 5 seconds. Then
S = {x | 1.5 < x < 5} is continuous.
• It is known that the recycle time has only three values(low,
medium or high). Then S = {low, medium,
high} is discrete.
• Does the camera conform to minimum recycle time
specifications?
S = {yes, no} is discrete.
22
Events are Sets of Outcomes
• An event (E) is a subset of the sample space of
a random experiment.
• Event combinations
– The Union of two events consists of all outcomes
that are contained in one event or the other,
denoted as E1 U E2.
– The Intersection of two events consists of all
outcomes that are contained in one event and the
other, denoted as E1 ∩ E2.
– The Complement of an event is the set of outcomes
in the sample space that are not contained in the
event, denoted as E.
Sec 2-1.3 Events 23
Mutually Exclusive Events
• Events A and B are mutually exclusive because they
share no common outcomes.
• The occurrence of one event precludes the occurrence
of the other.
• Symbolically, A ∩B = Ø
Sec 2-1.3 Events 24
Probability
• Probability is the likelihood or chance that
a particular outcome or event from a
random experiment will occur.
• In this chapter, we consider only discrete
(finite or countably infinite) sample spaces.
• Probability is a number in the [0,1] interval.
• A probability of:
– 1 means certainty
– 0 means impossibility
Sec 2-2 Interpretations & Axioms of Probability 25
Probability Based on Equally-Likely
Outcomes
• Whenever a sample space consists of N

possible outcomes that are equally likely, the
probability of each outcome is 1/N.
• Example: In a batch of 100 diodes, 1 is laser
diode. A diode is randomly selected from the
batch. Random means each diode has an
equal chance of being selected. The probability
of choosing the laser diode is 1/100 or 0.01,
because each outcome in the sample space is
equally likely.
Sec 2-2 Interpretations & Axioms of Probabilities 26
Probability of an Event
• For a discrete sample space, the probability
of an event E, denoted by P(E), equals the
sum of the probabilities of the outcomes in E.
• The discrete sample space may be:

– A finite set of outcomes
– A countably infinite set of outcomes.
Axioms of Probability
• Probability is a number that is assigned to each member of a collection
of events from a random experiment that satisfies the following
properties:
If S is the sample space and E is any event in the random experiment,
1. P(S) = 1
2. 0 ≤ P(E) ≤ 1
3. For any two events E1 and E2 with E1∩E2 = Ø,
P(E1UE2) = P(E1) + P(E2)
• The axioms imply that:

– P(Ø) = 0 and P(E′ ) = 1 – P(E)
– If E1 is contained in E2, then P(E1) ≤ P(E2).
Probability of a Union
• For any two events A and B, the
probability of union is given by:
P( A  B) = P( A) + P(B) − P( A  B)
• If events A and B are mutually

exclusive, then P( A  B) = ,
and therefore:
P( A  B) = P( A) + P(B)
Sec 2-3 Addition Rules 29
Conditional Probability
• P(B | A) is the probability of event B
occurring, given that event A has already
occurred.
• A communications channel has an error
rate of 1 per 1000 bits transmitted. Errors
are rare, but do tend to occur in bursts. If a
bit is in error, the probability that the next
bit is also in error is greater than 1/1000.
Sec 2-4 Conditional Probability 30
Conditional Probability Rule
• The conditional probability of an event B
given an event A, denoted as P(B | A), is:
P(B | A) = P(A∩B) / P(A) for P(A) > 0.
• From a relative frequency perspective of n
equally likely outcomes:
– P(A) = (number of outcomes in A) / n
– P(A∩B) = (number of outcomes in A∩B) / n
– P(B | A) = number of outcomes in A ∩ B / number
of outcomes in A
31
Example 2-11
There are 4 probabilities conditioned on flaws in the
below table. Parts Classified
Surface Flaws
Defective Total
Yes (F ) No (F' )
Yes (D ) 10 18 28
No (D' ) 30 342 372
Total 40 360 400
P(F ) = 40 400 and P(D) = 28 400

P(D | F ) = P(D F ) P(F ) = 400 10 40
400 = 10
40
P ( D ' | F ) = P ( D ' F ) P ( F ) = 400

30 40
400 = 30
40
P ( D | F ') = P ( D F ') P ( F ') = 400

18 360
400 = 360
18
P ( D ' | F ') = P ( D ' F ') P ( F ') = 342

400
360
400 = 342
360
32
Multiplication Rule
• The conditional probability can be
rewritten to generalize a multiplication
rule.
P(A∩B) = P(B|A)·P(A) = P(A|B)·P(B)
• The last expression is obtained by

exchanging the roles of A and B.
33
Example 2-13: Machining
Stages
The probability that a part made in the 1st stage of a
machining operation meets specifications is 0.90.
The probability that it meets specifications in the
2nd stage, given that met specifications in the first
stage is 0.95.
What is the probability that both stages meet
specifications?
• Let A and B denote the events that the part has

met1st and 2nd stage specifications, respectively.
• P(A∩B) = P(B | A)·P(A) = 0.95·0.90 = 0.855
Sec 2-5 Multiplication & Total Probability Rules 34
Two Mutually Exclusive
Subsets
• A and A are mutually
exclusive.
• A∩B and A ∩B are
mutually exclusive
• B = (A∩B) U(A ∩B)
Total Probability Rule

For any two events A and B
P ( B) = P ( B  A) + P ( B  A)
= P ( B | A)  P ( A) + P ( B | A)  P ( A)
35
Example 2-14: Semiconductor Contamination
Information about product failure based on chip manufacturing
process contamination is given below. Find the probability of
failure.
Probability Level of Probability
of Failure Contamination of Level
0.1 High 0.2
0.005 Not High 0.8
Let F denote the event that the product fails.

Let H denote the event that the chip is exposed to high
contamination during manufacture. Then
− P(F | H) = 0.100 and P(H) = 0.2, so P(F H) = 0.02

− P(F | H ) = 0.005 and P(H ) = 0.8, so P(F H ) = 0.004
− P(F) = P(F ∩H) + P(F ∩H ) (Using Total Probability rule)
= 0.020 + 0.004 = 0.024
36
Event Independence
• Two events are independent if any one
of the following equivalent statements is
true:
1. P(A | B) = P(A)
2. P(B | A) = P(B)
3. P(A∩B) = P(A)·P(B)
• This means that occurrence of one
event has no impact on the probability
of occurrence of the other event.
37
Example 2-16:
Table 1 provides an example of 400 parts classified by surface flaws
and as (functionally) defective. Suppose that the situation is different
and follows Table 2. Let F denote the event that the part has surface
flaws. Let D denote the event that the part is defective.
The data shows whether the events are independent.
TABLE 1 Parts Classified TABLE 2 Parts Classified (data chg'd)

Surface Flaws Surface Flaws
Defective Yes (F ) No (F' ) Total Defective Yes (F ) No (F' ) Total
Yes (D ) 10 18 28 Yes (D ) 2 18 20
No (D' ) 30 342 372 No (D' ) 38 342 380
Total 40 360 400 Total 40 360 400
P (D |F ) = 10/40 = 0.25 P (D |F ) = 2/40 = 0.05

P (D ) = 28/400 = 0.10 P (D ) = 20/400 =
0.05
not same same
Events D & F are dependent Events D & F are independent
38
Bayes Theorem with Total
Probability
If E1, E2, … Ek are k mutually exclusive and
exhaustive events and B is any event,
P ( B | E1 ) P ( E1 )
P ( E1 | B) =
P ( B | E1 ) P ( E1 ) + P ( B | E2 ) P ( E2 ) + ... + P ( B | Ek ) P ( Ek )
where P(B) > 0
Note : Numerator expression is always one of

the terms in the sum of the denominator.
Sec 2-7 Bayes Theorem 39
Example 2-19
A printer manufacturer obtained the following three types of printer
failure probabilities. Hardware P(H) = 0.3, software P(S) = 0.6, and other
P(O) = 0.1. Also, P(F | H) = 0.9, P(F | S) = 0.2, and P(F | O) = 0.5.
If a failure occurs, determine if it’s most likely due to hardware,
software, or other.
P(F ) = P(F | H )P(H ) + P(F | S )P(S ) + P(F | O)P(O)
= 0.9(0.1) + 0.2(0.6) + 0.5(0.3) = 0.36
P(F | H )  P(H ) 0.9  0.1
P(H | F ) = = = 0.250
P(F ) 0.36
P(F | S )  P(S ) 0.2  0.6
P(S | F ) = = = 0.333
P(F ) 0.36
P(F | O)  P(O) 0.5  0.3
P(O | F ) = = = 0.417
P(F ) 0.36
Note that the conditionals given failure add to 1. Because P(O | F) is
largest, the most likely cause of the problem is in the other category.
40
Random Variable and its
Notation
• A variable that associates a number with the
outcome of a random experiment is called a
random variable.
• A random variable is a function that assigns a real
number to each outcome in the sample space of a
random experiment.
• A random variable is denoted by an uppercase
letter such as X. After the experiment is conducted,
the measured value of the random variable is
denoted by a lowercase letter such as
x = 70 milliamperes. X and x are shown in italics,
e.g., P(X = x).
Sec 2-8 Random Variables 41
Discrete & Continuous Random
Variables
• A discrete random variable is a random
variable with a finite or countably infinite
range. Its values are obtained by counting.
• A continuous random variable is a random
variable with an interval (either finite or
infinite) of real numbers for its range. Its
values are obtained by measuring.
Examples of Discrete & Continuous Random
Variables
• Discrete random variables:

– Number of scratches on a surface.
– Proportion of defective parts among 100 tested.
– Number of transmitted bits received in error.
– Number of common stock shares traded per day.
• Continuous random variables:
– Electrical current and voltage.
– Physical measurements, e.g., length, weight, time,
temperature, pressure.
Discrete Random Variables
Physical systems can be modeled by the same or
similar random experiments and random variables.
The distribution of the random variable involved in
each of these common systems can be analyzed. The
results can be used in different applications and
examples.
We often omit a discussion of the underlying sample

space of the random experiment and directly describe
the distribution of a particular random variable.
Sec 3-1 Discrete Random Variables 44
Probability Distributions
A random variable is a function that assigns a
real number to each outcome in the sample
space of a random experiment.
The probability distribution of a random variable

X gives the probability for each value of X.
Sec 3-2 Probability Distributions & Probability Mass 45

Functions
Example 3-4: Digital Channel
• There is a chance that a bit
transmitted through a digital
transmission channel is
received in error.
• Let X equal the number of bits
received in error in the next 4 Figure 3-1 Probability
bits transmitted. distribution for bits in
• The associated probability error.
distribution of X is shown in the P(X =0) = 0.6561
table. P(X =1) = 0.2916
P(X =2) = 0.0486
• The probability distribution of X P(X =3) = 0.0036
is given by the possible values P(X =4) = 0.0001
along with their probabilities. 1.0000
46
Probability Mass Function
For a discrete random variable X with possible values
x1, x2, …, xn, a probability mass function is a function
such that:
(1) f ( xi )  0
n
(2)  f ( xi ) = 1
i =1
(3) f ( xi ) = P( X = xi )
Sec 3-2 Probability Distributions & Probability Mass 47

Functions
Cumulative Distribution Functions
Example 3-6: Consider the probability distribution for the digital channel
example.
x P (X =x )
0 0.6561
1 0.2916
2 0.0486
3 0.0036
4 0.0001
1.0000
Find the probability of three or fewer bits in error.

• The event (X ≤ 3) is the total of the events: (X = 0), (X = 1), (X = 2),
and (X = 3).
• From the table:
P(X ≤ 3) = P(X = 0) + P(X = 1) + P(X = 2) + P(X = 3) = 0.9999
Sec 3-3 Cumulative Distribution Functions 48
Cumulative Distribution Function and Properties
The cumulative distribution function, is the probability that a random

variable X with a given probability distribution will be found at a value
less than or equal to x.
Symbolically,
F ( x) = P( X  x) =  f ( xi )
xi  x
For a discrete random variable X, F(x) satisfies the following properties:
(1) F ( x) = P( X  x) =  f ( xi )
xi  x
(2) 0  F ( x)  1
(3) If x  y, then F (x)  F ( y)

Variance Formula Derivations
V ( X ) = (x − )2 f ( x) is the definitional formula
x
= ( x2 − 2 x +  2 ) f ( x)
x
=  x2 f (x) − 2 xf (x) +  2  f (x)

x x
=  x2 f (x) − 2 2 +  2
x
=  x2 f (x) −  2 is the computational formula

x
The computational formula is easier to calculate manually.
Sec 3-4 Mean & Variance of a Discrete Random Variable 50
In Example 3-4, there is a chance that a bit transmitted through a digital
transmission channel is received in error. X is the number of bits received in
error of the next 4 transmitted. The probabilities are
P(X = 0) = 0.6561, P(X = 2) = 0.0486, P(X = 4) = 0.0001,
P(X = 1) = 0.2916, P(X = 3) = 0.0036
Use table to calculate the mean & variance.
x f (x ) x · f (x ) (x - 0.4)2 (x - 0.4)2 · f (x ) x 2 · f (x )
0 0.6561 0.0000 0.160 0.1050 0.0000
1 0.2916 0.2916 0.360 0.1050 0.2916
2 0.0486 0.0972 2.560 0.1244 0.1944
3 0.0036 0.0108 6.760 0.0243 0.0324
4 0.0001 0.0004 12.960 0.0013 0.0016
Total = 0.4000 0.3600 0.5200
= Mean = Variance (σ 2) = E (x 2)
=μ σ 2 = E (x 2) - μ 2 = 0.3600
Computational formula
Expected Value of a Function of a Discrete Random Variable
If X is a discrete random variable with probability mass function f (x),
E h( X ) = h(x) f (x)

x
If h ( x) = ( X −  ) , then its expectation is the variance of X.

2
In Example 3-9, X is the number of bits in error in the

next four bits transmitted. What is the expected value of
the square of the number of bits in error?
X 0 1 2 3 4
f (X ) 0.6561 0.2916 0.0486 0.0036 0.0001
Here h ( x) = X 2
Answer:
E ( X 2 ) = X 2  f ( X ) = 02  0.6561+12  0.2916 + 22  0.0486 + 32  0.036 + 42  0.0001

= 0.5200
Binomial Distribution
The random variable X that equals the number
of trials that result in a success is a binomial
random variable with parameters 0 < p < 1 and
n = 1, 2, ....
The probability mass function is:
 n x
f ( x) =   p (1− p) for x = 0,1,...n
n− x
(3-7)
 x
For constants a and b, the binomial expansion is
( ) ( k ) b
n
+ = k n−k
n n
a b a
Sec 3-6 Binomial Distribution k =0 54
Example 3-17: Binomial Coefficient
Exercises in binomial coefficient calculation:
10! 10  9  8  7!
( 3 ) = 3!7! = 3 2 1 7! = 120
10
15! 15 14 1312 11.10!

( 15
10 ) = 10!5! = 10!.5 4  3 2 1 = 3,003
100! 100  99  98  97.96!
( 100
4 ) = 4!96! = 4  3 2 1.96! 3,921,225
Sec 3-6 Binomial Distribution 55
Exercise 3-18:
Each sample of water has a 10% chance of containing a particular
organic pollutant. Assume that the samples are independent with
regard to the presence of the pollutant. Find the probability that, in the
next 18 samples, exactly 2 contain the pollutant.
Answer:
Let X denote the number of samples that contain the pollutant in the
next 18 samples analyzed. Then X is a binomial random variable with
p = 0.1 and n = 18
18
P ( X = 2) =   ( 0.1) ( 0.9) = 153( 0.1) ( 0.9) = 0.2835
2 16 2 16
 2
0.2835 = BINOMDIST(2,18,0.1,FALSE)
Exercise 3-18:
Determine the probability that at least 4
samples contain the pollutant.
Answer:
P ( X  4) = 1− P ( X  4)
18
3
= 1−   ( 0.1) (0.9)
x 18− x
x=0  x 
= 1− 0.150 + 0.300 + 0.284 + 0.168

= 0.098
0.0982 =1- BINOMDIST(3,18,0.1,TRUE)

57
Exercise 3-18:
Now determine the6 probability that 3 ≤ X <

18
7. P (3  X  7) =   (0.1) (0.9)
x 18− x
x=3  x 
Answer: = 0.168 + 0.070 + 0.022 + 0.005
= 0.265
0.2660 = BINOMDIST(7,18,0.1,TRUE) - BINOMDIST(2,18,0.1,TRUE)
Appendix A, Table II (pg. 705) is a cumulative binomial table

for selected values of p and n.
58
Binomial Mean and Variance
If X is a binomial random variable
with
parameters p and n,
 = E ( X ) = np
and
 = V ( X ) = np (1− p )
2
Example 3-19:
For the number of transmitted bit received in error
in Example 3-16, n = 4 and p = 0.1. Find the mean
and variance of the binomial random variable.
Answer:
μ = E(X) = np = 4*0.1 = 0.4
σ2 = V(X) = np(1-p) = 4*0.1*0.9 = 0.36
σ = SD(X) = 0.6
Geometric Distribution
• Binomial distribution has:
– Fixed number of trials.
– Random number of successes.
• Geometric distribution has reversed roles:

– Random number of trials.
– Fixed number of successes, in this case 1.
• The probability density function of Geometric

distribution is
f ( x) = p(1− p)x−1
x = 1, 2, …, the number of failures until the 1st success.
0 < p < 1, the probability of success.
Sec 3-7 Geometric & Negative Binomial Distributions 61
Example 3.21:
The probability that a wafer contains a large particle of
contamination is 0.01. Assume that the wafers are
independent. What is the probability that exactly 125
wafers need to be analyzed before a particle is
detected?
Answer:
Let X denote the number of samples analyzed until a
large particle is detected. Then X is a geometric random
variable with parameter p = 0.01.
P(X=125) = (0.99)124(0.01) = 0.00288.
62
Geometric Mean & Variance
If X is a geometric random variable with
parameter p,
 = E( X ) =
1
p
and
 2
=V ( X ) =
(1− p)
p2
Sec 3-7 Geometric & Negative Binomial Distributions 63
Exercise 3-22: Mean and Standard Deviation
The probability that a bit transmitted through a digital transmission

channel is received in error is 0.1. Assume that the transmissions are
independent events, and let the random variable X denote the number
of bits transmitted until the first error. Find the mean and standard
deviation.
Answer:
Mean = μ = E(X) = 1 / p = 1 / 0.1 = 10
Variance = σ2 = V(X) = (1-p) / p2 = 0.9 / 0.01 = 90
Standard deviation = 90 = 9.49
64
Poisson Distribution
The random variable X that equals the
number of events in a Poisson process is a
Poisson random variable with parameter λ > 0,
and the probability density function is:
e 
− x
f ( x) = for x = 0,1,2,3,... (3-16)
x!
65
Example 3-31: Calculations for Wire Flaws-1
For the case of the thin copper wire, suppose that
the number of flaws follows a Poisson distribution
With a mean of 2.3 flaws per mm. Find the
probability of exactly 2 flaws in 1 mm of wire.
Answer:
Let X denote the number of flaws in 1 mm of wire
e−2.3 2.32
P ( X = 2) = = 0.265
2!
In Excel
0.26518 = POISSON(2,2.3,FALSE)
66
Example 3-31: Calculations for Wire Flaws-2
Determine the probability of 10 flaws in 5 mm of
wire.
Answer :
Let X denote the number of flaws in 5 mm of wire.
E ( X ) =  = 5mm  2.3 flaws/mm=11.5 flaws

11.510
P ( X = 10) = e −11.5
= 0.113
10!
In Excel
0.1129 = POISSON(10,11.5,FALSE)
67
Poisson Mean & Variance
If X is a Poisson random variable with parameter λ, then
μ = E(X) = λ and σ2 =V(X) = λ
The mean and variance of the Poisson model are the same.
For example, if particle counts follow a Poisson distribution with a mean

of 25 particles per square centimeter, the variance is also 25 and the
standard deviation of the counts is 5 per square centimeter.
If the variance of a data is much greater than the mean, then the
Poisson distribution would not be a good model for the distribution of
the random variable.
68
Continuous Random Variables
• A continuous random variable is one which
takes values in an uncountable set.
• They are used to measure physical characteristics
such as height, weight, time, volume, position,
etc...
Examples
1. Let Y be the height of a person (a real number).
2. Let X be the volume of juice in a can.
3. Let Y be the waiting time until the next person
arrives at the server.
69
Probability Density Function
For a continuous random variable X, a probability density function is
a function such that
(1) f ( x)  0 means that the function is always non-negative.


(2)  f ( x) dx = 1
−
b
(3) P ( a  X  b) =  f ( x) dx = area under f ( x ) dx from a to b
a
(4) f ( x) = 0 means there is no area exactly at x.
70
Example 4-1: Electric Current
Let the continuous random variable X denote the current
measured in a thin copper wire in milliamperes(mA).
Assume that the range of X is 4.9 ≤ x ≤ 5.1 and f(x) = 5.
What is the probability that a current is less than 5mA?
Answer:
5 5
P ( X  5) =  f ( x)dx =  5 dx = 0.5
4.9 4.9
5.1
P ( 4.95  X  5.1) =  f ( x)dx = 0.75
4.95 Figure 4-4 P(X < 5)
illustrated.
71
Cumulative Distribution
Functions
The cumulative distribution function of a continuous
random variable X is,
x
F ( x) = P ( X  x) =  f (u ) du for −  x  
−
The cumulative distribution function is defined for all real

numbers.
Example 4-3: Electric Current
For the copper wire current measurement in
Exercise 4-1, the cumulative distribution
function consists of three expressions.
0 x < 4.9
F (x ) = 5x - 24.5 4.9 ≤ x ≤ 5.1
1 5.1 ≤ x
Figure 4-6 Cumulative distribution function
The plot of F(x) is shown in Figure 4-6.
Probability Density Function from the Cumulative
Distribution Function
• The probability density function (PDF) is

the derivative of the cumulative
distribution function (CDF).
• The cumulative distribution function
(CDF) is the integral of the probability
density function (PDF).
dF ( x)
Given F ( x) , f ( x) = as long as the derivative exists.
dx
Exercise 4-5: Reaction Time
• The time until a chemical reaction is complete (in
milliseconds, ms) is approximated by this
cumulative distribution function:
F ( x) = 0
 for x  0
1− e−0.01x for 0  x
• What is the Probability density function?
f ( x) =
dF ( x) d  0
dx
=  −0.01x = 0 −0.01x for x  0
dx 1− e 0.01e for 0  x 
• What proportion of reactions is complete within
200 ms?
P ( X  200) = F ( 200) = 1− e−2 = 0.8647
Mean & Variance
Suppose X is a continuous random variable with probability
density function f(x). The mean or expected value of X,
denoted as µ or E(X), is

 = E( X ) =  xf ( x) dx
−
The variance of X, denoted as V(X) or is 2 ,

 
 2 = V ( X ) =  ( x −  ) f ( x) dx =  x2 f ( x) dx −  2
2
− −
The standard deviation of X is  = 2.
76
Normal Distribution
A random variable X with probability density function
−( x− )
2
f ( x) =
1
e 2 2 -  x  
2
is a normal random variable with parameters µ,

where −     , and   0. Also,
E ( X ) =  and V ( X ) =  2
and the notation N ( , ) is used to denote the distribution.
2
Sec 4-6 Normal Distribution 77
Empirical Rule
For any normal random variable,
P(μ – σ < X < μ + σ) = 0.6827
P(μ – 2σ < X < μ + 2σ) = 0.9545
P(μ – 3σ < X < μ + 3σ) = 0.9973
Figure 4-12 Probabilities associated with a normal distribution

78
Standard Normal Random
Variable
A normal random variable with
μ = 0 and σ2 = 1
is called a standard normal random variable
and is denoted as Z. The cumulative
distribution function of a standard normal
random variable is denoted as:
Φ(z) = P(Z ≤ z)
Values are found in Appendix Table III and
by using Excel and Minitab.
Example 4-11
Assume Z is a standard normal random variable.
Find P(Z ≤ 1.50). Answer: 0.93319
Figure 4-13 Standard normal Probability density function
Find P(Z ≤ 1.53). Answer: 0.93699

Find P(Z ≤ 0.02). Answer: 0.50398
NOTE : The column headings refer to the hundredths digit of the value of z in P(Z ≤ z).
For example, P(Z ≤ 1.53) is found by reading down the z column to the row 1.5 and then selecting
the probability from the column labeled 0.03 to be 0.93699.
80
Standardizing a Normal Random
Variable
Suppose X is a normal random variable with mean  and variance  2 ,
the random variable
Z=
( X − )

is a normal random variable with E(Z ) = 0 and V (Z ) =1.
The probability is obtained by using Appendix Table III with z =

( x − )
.

Example 4-14:
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 current measurement is between 9 and 11 mA?
Answer:
9 −10 x −10 11 −10 
P (9  X  11) = P   
 2 2 2 
= P ( −0.5  z  0.5)
= P ( z  0.5) − P ( z  −0.5)
= 0.69146 − 0.30854 = 0.38292
Using Excel
0.38292 = NORMDIST(11,10,2,TRUE) - NORMDIST(9,10,2,TRUE)
82
Example 4-14
Determine the value for which the probability that a current
measurement is below 0.98.
Answer:
 X − 10 x − 10 
P ( X  x) = P   
 2 2 
 x − 10 
= P Z   = 0.98
 2 
z = 2.05 is the closest value.
z = 2 ( 2.05) + 10 = 14.1 mA.
Using Excel
14.107 = NORMINV(0.98,10,2)
83
84
85

IE4102 Lecture1

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

IE4102 Lecture1

Uploaded by

Copyright:

Available Formats

IE 4102 Statistics for Engineers

Lecture 1: Probability Basics

Assist. Prof. Duygun Fatih Demirel

An engineer is someone who solves problems of

Figure 1-1 The engineering method

The field of statistics deals with the collection,

Figure 1-2 Dot diagram of the pull-off force data.

Three basic methods of collecting data:

One-sample hypothesis test:

Two-sample hypothesis test:

Sec 1-2.4 Designed Experiments 9

Consider a petroleum distillation column:

• Output is acetone concentration

• Output changes as the inputs are changed by experimenter.

Sec 1-3 Mechanistic & Empirical Models 12

An empirical model is built from our engineering

Sec 1-3 Mechanistic & Empirical Models 13

• In a semiconductor manufacturing plant, the

• The data recorded are shown on the next slide.

Sec 1-3 Mechanistic & Empirical Models 14

Sec 1-3 Mechanistic & Empirical Models 15

where the “hat,” or circumflex, over pull strength

In general, this type of empirical model is called a

The estimated regression relationship is given by:

Sec 1-3 Mechanistic & Empirical Models 16

Figure 1-6 Three-dimensional plot of the pull strength (y),

Sec 1-3 Mechanistic & Empirical Models 17

Figure 1-7 Plot of the predicted values (a plane) of pull

Sec 1-3 Mechanistic & Empirical Models 18

• Probability models help quantify the risks involved in

Sec 1-4 Probability & Probability Models 19

• The set of all possible outcomes of a

Sec 2-1.3 Events 24

• Whenever a sample space consists of N

Sec 2-2 Interpretations & Axioms of Probabilities 26

• The discrete sample space may be:

Sec 2-2 Interpretations & Axioms of Probability 27

If S is the sample space and E is any event in the random experiment,

• The axioms imply that:

Sec 2-2 Interpretations & Axioms of Probability 28

• If events A and B are mutually

Sec 2-4 Conditional Probability 30

P(F ) = 40 400 and P(D) = 28 400

P ( D ' | F ) = P ( D ' F ) P ( F ) = 400

P ( D | F ') = P ( D F ') P ( F ') = 400

P ( D ' | F ') = P ( D ' F ') P ( F ') = 342

P(A∩B) = P(B|A)·P(A) = P(A|B)·P(B)

• The last expression is obtained by

• Let A and B denote the events that the part has

Sec 2-5 Multiplication & Total Probability Rules 34

Total Probability Rule

Let F denote the event that the product fails.

− P(F | H) = 0.100 and P(H) = 0.2, so P(F H) = 0.02

The data shows whether the events are independent.

TABLE 1 Parts Classified TABLE 2 Parts Classified (data chg'd)

P (D |F ) = 10/40 = 0.25 P (D |F ) = 2/40 = 0.05

where P(B) > 0

Note : Numerator expression is always one of

Sec 2-8 Random Variables 42

• Discrete random variables:

Sec 2-8 Random Variables 43

We often omit a discussion of the underlying sample

Sec 3-1 Discrete Random Variables 44

The probability distribution of a random variable

σ2 = V(X) = np(1-p) = 40.10.9 = 0.36