6/14/2016

2.5 MULTIPLICATION AND TOTAL PROBABILITY 2.5 MULTIPLICATION AND TOTAL PROBABILITY
RULES RULES
Total Probability Rule (multiple events)
Multiplication Rule
Assume E1, E2, …, Ek are k mutually exclusive sets. Then,
If in an experiment the events A and B can both occur,then
P  B   P  B  E1   P  B  E2    P  B  Ek 
P  A  B   P  B A P  A  P  A B  P  B 
 P  B E1  P  E1   P  B E2  P  E2    P  B Ek  P  Ek 

Example 14 Suppose that P  A B   0.4 and P  B   0.5.

Total Probability Rule (two events)
Determine the following:
For any events A and B, (a) P  A  B (b) P  A  B 
P  B   P  B  A   P  B  A   P  B A  P  A   P  B A  P  A  Solution: (a) P  A  B   P  A B  P  B   0.4  0.5  0.2

(b) P  A  B   P  A B  P  B   0.6  0.5  0.3

2.5 MULTIPLICATION AND TOTAL PROBABILITY

2.6 INDEPENDENCE
RULES

Example 15 The probability is 1% that an electrical connector that

is kept dry fails during the warranty period of a Independence (two events)
portable computer. If the connector is ever wet, the
probability of a failure during the warranty period is
Two events are independent if any one of the following is true:
5%. If 90% of the connectors are kept dry and 10% are
wet, what proportion of connectors fail during the
 
(a) P A B  P  A 
warranty period?
 
(b) P B A  P  B 
Solution: Let
F : the connectors fail (c) P  A  B   P  A  P  B 
D : the connector is dry
W : the connector is wet
P  F D   0.01, P  F W   0.05,
P  D   0.9, P W   0.1

 P  F   P  F D  P  D   P  F W  P W 

 0.01 0.9   0.05  0.1  0.014

2.6 INDEPENDENCE 2.6 INDEPENDENCE

Example 16 A small town has one fire engine and one ambulance
available for emergencies. The probability that the fire Independence (multiple events)
engine is available when needed is 0.98, and the
probability that the ambulance is available when
The events E1, E2, …, En are independent if and only if for any
called is 0.92. In the event of an injury resulting from subset of these events Ei1 , Ei2 , , Eik ,
a burning building, find the probability that both the
ambulance and the fire engine will available. 
P Ei1  Ei2      
 Eik  P Ei1  P Ei2   P Eik 
Solution: Let A and B represent the respective events that the
fire engine and the ambulance are available. Then,
P  A  B   P  A P  B   0.98  0.92   0.9016

1
 6/14/2016

2.6 INDEPENDENCE Solution:

Example 17 The following system operates only if there is a path of
functional device from left to the right. The probability
that each device functions is as shown. What is the
Let Box A: component 1, 2, 3, 4; Box B: component 5, and 6; and Box C:
component 7
P  system works   P  A works  P  B works  P  C works 

P  A works   P  2 and 4 work   P 1 and 3 work 

probability that the circuit operates? Assume
independence.

 P   2 and 4 work   1 and 3 work  


 0.9  0.9    0.98  0.97    0.9  0.9   0.98  0.97  
 0.9906

Figure 2.3 An electrical system.

2.7 BAYES’ THEOREM

P  B works   P  5 works   P  6 works   P  5  6 work 

 P  5 works   P  6 works   P  5 works  P  6 works  Definition

 0.95  0.9   0.95 0.9  P  A B 

P  B A P  A
for P  B   0
P  B
 0.995
Bayes’ Theorem
If E1, E2, …, Ek are k mutually exclusive events and B is any
 P  system work   0.9906  0.995  0.99   0.9758 event. Then,
P  B E1  P  E1 
P  E1 B  
P  B E1  P  E1   P  B E2  P  E2    P  B Ek  P  Ek 

for P  B   0

2.7 BAYES’ THEOREM 2.7 BAYES’ THEOREM

Solution:
Example 18
A new process of more accurately detecting anaerobic respiration in Let
O : Obligate anaerobes F : Facultative anaerobes
cells in being tested. The new process is important due to its high
A : Aerotolerant M : Microaerophiles
accuracy, its lack of extensive experimentation, and the fact that it N : Nanaerobes S : Test is signal
could be used to identify five different categories of organisms:
Obligate anaerobes, Facultative anaerobes, Arotolerant,
Microaerophiles, and Nanaerobes instead of using a single test for P  S O   0.978 P  O   0.31
each category. The process claims that it can identify obligate
P  S F   0.981 P  F   0.27
anaerobes with 97.8% accuracy, facultative anaerobes with 98.1%
accuracy, aerotolerant with 95.9% accuracy, microaerophiles with P  S A   0.959 P  A   0.08
96.5% accuracy, and nanaerobes with 99.2% accuracy. If any category is
P  S M   0.965 P  M   0.21
not present, the process does not signal. Samples are prepared for the
calibration of the process and 31% of them contain obligate anaerobes, P  S N   0.992 P  N   0.13
27% contain facultative anaerobes, 21% contain microaerophiles, 13%
contain nanaerobes, and 8% contain aerotolerant. A test sample is
selected randomly.
(a) What is the probability that the process will signal?
(b) If the test signals, what is the probability that microaerophiles are
present?

2
 6/14/2016

2.7 BAYES’ THEOREM 2.7 BAYES’ THEOREM

(a) P  S   P  O  P  S O   P  F  P  S F   P  A P  S A Example 19 Customers are used to evaluate preliminary product designs.

In the past, 95% of highly successful products received good
 PM  PS M   P N  P S N  reviews, 60% of moderately successful products received good
reviews, and 10% of poor products received good reviews. In
 0.31 0.978  0.27  0.981  0.08  0.959  addition, 40% of products have been highly successful, 35%
 0.21 0.965  0.13  0.992  have been moderately successful and 25% have been poor
products.
 0.97638 (a) What is probability that are product attains a good
review?
(b) If a new product attains a good review, what is the
PS M  PM  0.965  0.21
(b) PM S     0.2076 probability that it will be a highly successful product?
PS  0.97638 (c) If a product does not attain a good review, what is the
probability that it will be a highly successful product?

Solution: G ~ product attains a good review

H ~ products that were highly successful
M ~ products that were moderate successful
P ~ products that were poor successful

2.7 BAYES’ THEOREM 2.8 RANDOM VARIABLES

P  H   0.4, P  G H   0.95 P  M   0.35, P  G M   0.60

Definition
P  P   0.25, P  G P   0.10
A random variable is a function that assigns a real number to
each outcome in the sample space of a random experiment.
(a) P  G   P G H  P  H   P G M  P  M   P G P  P  P 

 0.95  0.4   0.6  0.35   0.10  0.25 

 0.6150 Definition
P  G  H  0.95  0.4  A discrete random variable is a random variable with a finite
(b) P  H G    0.6179
P G  0.6150 (or countably infinite) range.

P  G  H  0.05  0.4  A continuous random variable is a random variable with an

(c) P  H G     0.0519
P  G  1  0.6150 interval (either finite or infinite) of real numbers for its range.

for

2.8 RANDOM VARIABLES 2.8 RANDOM VARIABLES

In some cases, the random variable X is actually discrete but, Example 20

because the range of possible values is so large, it might be more
convenient to analyze X as a continuous random variable.
Examples of continuous random variables:
Electrical current, length, pressure, temperature, time, voltage,
weight
(Need to use measurement tools)
Examples of discrete random variables:
Number of scratches on a surface, proportion of defective parts
among 1000 tested, number of transmitted bits received in error.
(Countably)
Decide whether a discrete or continuous random variable is the best model for
each of the following variables:
(a) The time until a projectile returns to earth. (continuous)
(b) The number of times a transistor in a computer memory changes state in
one operation. (discrete)
(c) The volume of gasoline that is lost to evaporation during the filling of a
gas tank. (continuous)
(d) The outside diameter of a machined shaft. (continuous)
(e) The number of cracks exceeding one-half inch in 10 miles of an interstate
highway. (discrete)
(f ) The weight of an injection-molded plastic part. (continuous)
(g) The number of molecules in a sample of gas. (discrete)
(h) The concentration of output from a reactor. (continuous)