Anda di halaman 1dari 16

# Chapter 4 4-1

## Fundamental Counting Principle

Spring Semester 2019 A student is to roll a die and flip a coin.
How many possible outcomes will there be?
1H 2H 3H 4H 5H 6H
1T 2T 3T 4T 5T 6T 6*2 = 12 outcomes
Sets, Operations on sets, Venn Diagram 12 outcomes
Rules of Counting: Factorial, Permutation, Combination
Probability, Laws of Probability, Conditional Probability For a college interview, Ali/Alia has to
Random Variable, Mathematical Expectation choose what to wear from the following: 4
Probability Distributions (Discrete and Continuous) slacks, 3 shirts, 2 shoes and 5 ties. How
many possible outfits does he/she have to
choose from? 4*3*2*5 = 120 outfits
1 5

## Permutations: ORDER MATTERS!

Fundamental Counting Principle
A Permutation is an arrangement of items in a
Fundamental Counting Principle can be used particular order.
determine the number of possible outcomes To find the number of Permutations of n items, we can
when there are two or more characteristics . use the Fundamental Counting Principle or factorial
notation.
Fundamental Counting Principle states that The number of ways to arrange the letters ABC:
____ ____ ____
if an event has m possible outcomes and 3 ____ ____
Number of choices for first blank?
another independent event has n possible
Number of choices for second blank? 3 2 ___
outcomes, then there are m* n possible
outcomes for the two events together. Number of choices for third blank? 3 2 1

3*2*1 = 6 3! = 3*2*1 = 6

4
ABC ACB BAC BCA CAB CBA 6

Chapter 4 4-2

Permutations Combinations
To find the number of Permutations of n items chosen r at a time,
you can use the formula
n! Practice: A basketball team consists of two centers, five forwards,
and four guards. In how many ways can the coach select a
n p r  ( n  r )! where 0  r  n.
starting line up of one center, two forwards, and two
5! 5! guards?
Practice: 5 p3  
( 5  3 )! 2!
 5 * 4 * 3  60
Center: Forwards: Guards:
A combination lock will open when the right 2! 5! 5 * 4 4! 4 * 3
2C1   2 5 C2    10 4 C2   6
choice of three numbers (from 1 to 30, inclusive) 1 !1 ! 2!3! 2 * 1 2!2! 2 * 1
is selected. How many different lock C1 * 5 C 2 * 4 C 2
2
combinations are possible assuming no number is
repeated? Thus, the number of ways to select the
30 ! 30!
30 p3 
( 30  3 )!

27!
 30 * 29 * 28  24360 starting line up is 2*10*6 = 120.
7 9

## Combinations: ORDER DOES NOT MATTER! Important Terms

A Combination is an arrangement of items in  Random Experiment – a process leading to an
which order does not matter. uncertain outcome
Since the order does not matter in combinations, there are  Basic Outcome – a possible outcome of a random
fewer combinations than permutations. experiment
The combinations are a "subset" of the permutations.
 Sample Space – the collection of all possible
n! outcomes of a random experiment
To find the number of C  where 0  r  n .
n r r!(n  r )! Event – any subset of basic outcomes from the
Combinations of nn 

## items chosen rr at a 5! 5! sample space

C3   
time, you can use the 5
3! (5  3)! 3!2!
formula
5 * 4 * 3 * 2 * 1 5 * 4 20
   10
3 * 2 *1* 2 *1 2 *1 2
8 10

Chapter 4 4-3

Important Terms
(continued) Examples
 Intersection of Events – If A
and B are two events in a
S Let the Sample Space be the collection of all
sample space S, then the possible outcomes of rolling one die:
A AB
intersection, A Ç B, is the set of B
all outcomes in S that belong to
both A and B
 Union of Events – If A S = {1, 2, 3, 4, 5, 6}
S
and B are two events in Let A be the event “Number rolled is even”
a sample space S, then
A B Let B be the event “Number rolled is at least 4”
the union, A U B, is the
set of all outcomes in S Then
that belong to either A = {2, 4, 6} and B = {4, 5, 6}
The entire shaded area represents A U B
A or B 11 13

Examples (continued)
Important Terms (continued) S = {1, 2, 3, 4, 5, 6} A = {2, 4, 6} B = {4, 5, 6}

##  A and B are Mutually Exclusive S Complements: A  {1, 3, 5} B  {1, 2, 3}

Events if they have no basic
outcomes in common Intersections: A  B  {4, 6} A  B  {5}
A B
 i.e., the set A Ç B is empty
Unions: A  B  {2, 4, 5, 6}
 Events E1, E2, … Ek are Collectively Exhaustive
A  A  {1, 2, 3, 4, 5, 6}  S
events if E1 U E2 U . . . U Ek = S
 i.e., the events completely cover the sample space  Mutually exclusive:
 A and B are not mutually exclusive
 The Complement of an event A is The outcomes 4 and 6 are common to both
S 

## the set of all basic outcomes in the A  Collectively exhaustive:

sample space that do not belong to A
 A and B are not collectively exhaustive
A. The complement is denoted A  A U B does not contain 1 or 3
12 14

Chapter 4 4-4

## Probability Probability Rules

 Probability – the chance that an  The Complement rule: P(A)  1 P(A) i.e., P(A)  P(A)  1
uncertain event will occur (always
between 0 and 1) 1 Certain
 Probability Postulates
 The probability of the union of two events is
1. If A is any event in the sample space S, then P(A or B)  P(A  B)  P(A)  P(B)  P(A  B)
0  P(A)  1
.5
2. Let A be an event in S, and let Oi denote the
The Multiplication rule (When events are independent):
basic outcomes. Then P(A)  P(O )  i

A  The probability of the intersection of two events is
(the notation means that the summation is over all
the basic outcomes in A) P(A and B)  P(A  B)  P(A) * P(B)
3. Probability of sample space is 1 P(S)  1 0 Impossible

15 17

Assessing Probability
Three approaches to assess probability of an uncertain
event
A Probability Table
1. classical probability
NA number of outcomes that satisfy the event Probabilities and joint probabilities for two events A
probabilit y of event A  
N total number of outcomes in the sample space and B are summarized in this table:
 Assumes all outcomes in the sample space are equally likely to occur
2. relative frequency probability B B
nA number of events in the population that satisfy event A
probabilit y of event A   A P(A  B) P(A  B ) P(A)
n total number of events in the population

## the limit of the proportion of times that an event A occurs in a large

A P(A  B) P(A  B ) P(A)
number of trials, n
3. subjective probability P(B) P( B ) P(S)  1.0
an individual opinion or belief about the probability of occurrence

16 18

Chapter 4 4-5

## Addition Rule Example Conditional Probability Example

Consider a standard deck of 52 cards, with four suits:
§¨ª  Of the cars on a used car lot, 70% have air
Let event A = card is an Ace. Let event B = card is from a red suit conditioning (AC) and 40% have a CD player
P(Red U Ace) = P(Red) + P(Ace) - P(Red Ç Ace) (CD). 20% of the cars have both.

## = 26/52 + 4/52 - 2/52 = 28/52

Don’t count  What is the probability that a car has a CD
the two red player, given that it has AC ?
Color aces twice!
Type Red Black Total
i.e., we want to find P(CD | AC)
Ace 2 2 4
Non-Ace 24 24 48
Total 26 26 52 19
21

## Conditional Probability Conditional Probability Example

(continued)
 Of the cars on a used car lot, 70% have air conditioning
 A conditional probability is the probability of one (AC) and 40% have a CD player (CD).
event, given that another event has occurred: 20% of the cars have both.

## P(A  B) The conditional

CD No CD Total
P(A | B)  probability of A given AC .2 .5 .7
P(B) that B has occurred
No AC .2 .1 .3
P(A  B) The conditional
Total .4 .6 1.0
P(B | A)  probability of B given
P(A) that A has occurred

P(CD  AC) .2
P(CD | AC)    .2857
P(AC) .7
20 22

Chapter 4 4-6

## Conditional Probability Example Statistical Independence

(continued)
 Given AC, we only consider the top row (70% of the cars). Of these,
20% have a CD player. 20% of 70% is 28.57%.
 Two events are statistically independent
if and only if:
CD No CD Total
AC .2 .5 .7
P(A  B)  P(A) P(B)
No AC .2 .1 .3  Events A and B are independent when the probability of one
event is not affected by the other event
Total .4 .6 1.0
 If A and B are independent, then
P(CD  AC) .2 P(A | B)  P(A)
P(CD | AC)    .2857 if P(B)>0
P(AC) .7
P(B | A)  P(B) if P(A)>0

23 25

## Statistical Independence Example (continued)

Multiplication Rule & Its Example  Of the cars on a used car lot, 70% have air conditioning
 Multiplication rule for two events A and B: (AC) and 40% have a CD player (CD). 20% of the cars
P(A  B)  P(A | B) P(B) have both.
 Are the events AC and CD statistically independent?
 also P(A  B)  P(B | A) P(A)
CD No CD Total
P(Red Ç Ace) = P(Red| Ace)P(Ace)
 2  4  2 AC .2 .5 .7
    
 4  52  52 No AC .2 .1 .3
number of cards that are red and ace 2
 
total number of cards 52 Total .4 .6 1.0
Color P(AC Ç CD) = 0.2
Type Red Black Total
P(AC) = 0.7
P(AC)P(CD) = (0.7)(0.4) = 0.28
Ace 2 2 4 P(CD) = 0.4

## Non-Ace 24 24 48 P(AC Ç CD) = 0.2 ¹ P(AC)P(CD) = 0.28

Total 26 26 52 So the two events are not statistically independent 26
24

Chapter 4 4-7

Introduction to
Marginal Probability Example Probability Distributions

## P(Ace)  Random Variable

2 2 4  Represents a possible numerical value from
 P(Ace  Red)  P(Ace  Black)   
52 52 52 a random experiment
Random
Color Variables
Type Red Black Total
Discrete Continuous
Ace 2 2 4
Random Variable Random Variable
Non-Ace 24 24 48
Total 26 26 52

27 31

## Using a Tree Diagram

(Not included for the Final Exam) Discrete Random Variables
.2
.7
 Can only take on a countable number of values
Given AC or P(AC Ç CD) = .2
no AC: Examples:
P(AC Ç CD) = .5
.5  Roll a die twice
.7 Let X be the number of times 4 comes up
All (then X could be 0, 1, or 2 times)
Cars
.2
.3 P(AC Ç CD) = .2  Toss a coin 5 times.
Let X be the number of heads
(then X = 0, 1, 2, 3, 4, or 5)
.1 P(AC Ç CD) = .1
.3 28
32

Chapter 4 4-8

## Discrete Probability Distribution Expected Value

Experiment: Toss 2 Coins. Let X = # heads.  Expected Value (or mean) of a discrete
Show P(x) , i.e., P(X = x) , for all values of x: distribution (Weighted Average)
4 possible outcomes
Probability Distribution  E(x)   xP(x)
T T x Value Probability x

0 1/4 = .25
T H 1 2/4 = .50
 Example: Toss 2 coins,
x P(x)
0 .25
2 1/4 = .25
x = # of heads, 1 .50
H T Probability
compute expected value of x: 2 .25
.50
E(x) = (0 x .25) + (1 x .50) + (2 x .25)
H H .25
= 1.0

0 1 2 x 33 35

## Probability Distribution Variance and Standard Deviation

Required Properties
 Variance of a discrete random variable X
s 2  E(X  ) 2   (x  ) 2 P(x)
 P(x)  0 for any value of x x
2
 
s  E(X ) - E(X)    x 2 P(x)    xP(x) 
2 2 2

x  x 
 The individual probabilities sum to 1;  Standard Deviation of a discrete random variable X

 P(x)  1
x
 2
  (x  ) 2 P(x)
x

## (The notation indicates summation over all possible x values)

 Example: Toss 2 coins, X = # heads,
compute standard deviation (recall E(x) = 1)
 (0  1)2 (.25)  (1  1)2 (.50)  (2  1)2 (.25)  .50  .707

34 = 0, 1, or 2 36

Chapter 4 4-9

## Probability  A manufacturing plant labels items as either

Distributions defective or acceptable
Discrete Continuous  A firm bidding for contracts will either get a contract
Probability Probability or not
Distributions Distributions
 A marketing research firm receives survey
responses of “yes I will buy” or “no I will not”
Binomial Uniform
 New job applicants either accept the offer or reject
Hypergeometric Gaussian or Normal it
Poisson Exponential

37 39

## Discrete Probability Distribution

Binomial Probability Distribution Binomial Distribution Formula
 A fixed number of observations, n
 e.g., 15 tosses of a coin; ten light bulbs taken from a warehouse n! X X
P(x)  P (1- P)n
 Two mutually exclusive and collectively exhaustive x ! (n  x )!
categories
 e.g., head or tail in each toss of a coin; defective or not defective
light bulb P(x) = probability of x successes in n trials,
 Generally called “success” and “failure” with probability of success P on each trial
Example: Flip a coin four
 Probability of success is P , probability of failure is 1 – P times, let x = # heads:
x = number of ‘successes’ in sample,
 Constant probability for each observation n=4
(x = 0, 1, 2, ..., n)
 e.g., Probability of getting a tail is the same each time we toss P = 0.5
n = sample size (number of trials
the coin or observations) 1 - P = (1 - 0.5) = 0.5
 Observations are independent P = probability of “success” x = 0, 1, 2, 3, 4
 The outcome of one observation does not affect the outcome of 1- P = probability of “failure”
the other
38 40

Chapter 4 4-10

## Example: Binomial Distribution: Mean & Variance

Calculating a Binomial Probability  Mean  E(x)  nP

 Variance
2
 nP(1- P)
What is the probability of one success in five  nP(1- P)
observations if the probability of success is 0.1?
 Standard Deviation
Examples
x = 1, n = 5, and P = 0.1  nP  (5)(0.1)  0.5
Mean P(x) n = 5 P = 0.1
.6
.4
 nP(1- P)  (5)(0.1)(1 0.1) .2
n!  0.6708 0 x
P(x  1)  P X (1 P)n X
x!(n  x)! 0 1 2 3 4 5

5!
 (0.1)1(1 0.1)51  nP  (5)(0.5)  2.5
1! (5  1)! P(x) n = 5 P = 0.5
.6
 (5)(0.1)(0.9) 4
 nP(1- P)  (5)(0.5)(1 0.5)
.4
.2
 .32805  1.118 0 x
0 1 2 3 4 5
41 43

## Using PHStat (https://wps.aw.com/phstat/)

Binomial Distribution (Not included for the Final Exam)
 The shape of the binomial distribution depends on the  Select PHStat / Probability & Prob. Distributions / Binomial…
values of P and n
Mean P(x) n = 5 P = 0.1
.6
 Here, n = 5 and P = 0.1 .4
.2
0 x
0 1 2 3 4 5

P(x) n = 5 P = 0.5
 Here, n = 5 and P = 0.5 .6
.4
.2
0 x
0 1 2 3 4 5
42 44

Chapter 4 4-11

## Using PHStat Discrete Probability Distribution

(Not included for the Final Exam) The Poisson Distribution
(continued)
 Enter desired values in dialog box  Apply the Poisson Distribution when:
Here: n = 10  You wish to count the number of times an event occurs
in a given continuous interval
p = .35
 The probability that an event occurs in one subinterval is
Output for x = 0 very small and is the same for all subintervals
to x = 10 will be  The number of events that occur in one subinterval is
generated by PHStat independent of the number of events that occur in the
other subintervals
Optional check boxes  There can be no more than one occurrence in each
subinterval
 The average number of events per unit is  (lambda)

45 47

## PHStat Output Poisson Distribution Characteristics

(Not included for the Final Exam) (Not included for the Final Exam)
e x where:
P(x)  x = number of successes per unit
x!  = expected number of successes per unit
e = base of the natural logarithm system (2.71828...)
P(x = 3 | n = 10, P = .35) = .2522
Mean

 E(x) 
 Variance and Standard Deviation
2
 E[( X   ) 2 ] 

## P(x > 5 | n = 10, P = .35) = .0949 

46
where  = expected number of successes per unit 48

Chapter 4 4-12

## Graph of Poisson Probabilities Portfolio Example

(Not included for the Final Exam) (Not included for the Final Exam)
0.70 Investment X: x = 50 x = 43.30
Graphically: Investment Y:
0.60 y = 95 y = 193.21
 = .50 0.50 xy = 8250
= 0.40

## X 0.50 P(x) 0.30

Suppose 40% of the portfolio (P) is in Investment X and
0 0.6065 60% is in Investment Y:
0.20
1 0.3033 E(P)  .4 (50 )  (.6) (95 )  77
2 0.0758 0.10

3 0.0126
 (.4) 2 (43.30) 2  (.6)2 (193.21) 2  2(.4)(.6)( 8250)
0.00
0 1 2 3 4 5 6 7 P
4 0.0016
x
5 0.0002  133 .04
6 0.0000
P(X = 2) = .0758
7 0.0000 The portfolio return and portfolio variability are between the values
for investments X and Y considered individually
49 62

## Poisson Distribution Shape Interpreting the Results for Investment Returns

(Not included for the Final Exam) (Not included for the Final Exam)

 The shape of the Poisson Distribution  The aggressive fund has a higher expected
depends on the parameter  : return, but much more risk

0.70 0.25
y x
but
0.60
0.20
0.50

0.40
0.15

## y = 193.21 > x = 43.30

P(x)
P(x)

0.30 0.10

0.20
0.05
0.10

0.00 0.00
 The Covariance of 8250 indicates that the two
0 1 2 3

x
4 5 6 7 1 2 3 4 5 6

x
7 8 9 10 11 12
investments are positively related and will vary
in the same direction
50 63

Chapter 4 4-13

## The Normal Distribution

Density Function
Continuous Probability Distributions (Not included in the final exam)

##  There are many types of continuous probability

 The formula for the normal probability density function is
distributions
2
1  (X  ) 
1  
 

f(X)  e 2
2p
Bell Shaped Constant Exponential Where e = the mathematical constant a roximated by 2.71828
Probability Probability Probability p = the mathematical constant a roximated by 3.14159
= the o ulation mean
Distribution Distribution Distribution = the o ulation standard deviation
X = any value of the continuous variable

66
64

## The Normal Distribution Many Normal Distributions

 Bell Shaped
 Symmetrical
 Mean, Median & Mode are Equal f(X)
 Most commonly, it occurs because
of random errors
 Location is determined by the X
mean,
 Spread is determined by the
standard deviation, Mean
 The random variable has an infinite By varying the parameters and , we obtain
theoretical range:
= Median
different normal distributions
 +  to   = Mode

65 67

Chapter 4 4-14

## Translation to the Standardized The Standardized Normal Distribution

Normal Distribution (Not included for the final exam)
 Any normal distribution (with any mean and
standard deviation combination) can be  Also known as the “Z” distribution
transformed into the standardized normal  Mean is 0
distribution (Z)
 Standard Deviation is 1
 Need to transform X units into Z units
f(Z)
 The standardized normal distribution (Z) has a
mean of 0 and a standard deviation of 1
1
 Translate from X to the standardized normal (the
“Z” distribution) by subtracting the mean of X and Z
0
dividing by its standard deviation: X Values above the mean have positive Z-values,
The Z distribution always has mean = 0 and standard
Z values below the mean have negative Z-values
deviation = 1 70
68

## The Standardized Normal

Probability Density Function Example
(Not included for the final exam)
 The formula for the standardized normal  If X is distributed normally with mean of 100
probability density function is and standard deviation of 50, the Z value for
X = 200 is
1 (1/2)Z 2
f(Z)  e X 200  100
2 Z   2.0
50
Where e = the mathematical constant approximated by 2.71828
= the mathematical constant approximated by 3.14159  This says that X = 200 is two standard
Z = any value of the standardized normal distribution deviations (2 increments of 50 units) above
the mean of 100.
69
71

Chapter 4 4-15

## Comparing X and Z units Finding Normal Probabilities

(Not included for the final exam)
(Not included for the final exam)

## Probability is measured by the area

under the curve
f(X) P (a £ X £ b)
100 200 X ( = 100, = 50) = P (a < X < b)
0 2.0 Z ( = 0, = 1) (Note that the
probability of any
Note that the shape of the distribution is the same, individual value is zero)
only the scale has changed. We can express the
problem in original units (X) or in standardized a b X
units (Z)
72 74

## Probabilities Probability as Area Under the Curve

(Not included for the final exam) (Not included for the final exam)
The total area under the curve is 1.0, and the curve is
For a discrete random variable, we can talk symmetric, so half is above the mean, half is below
about the possibility of a single occurrence, f(X) P(   X  )  0.5
two occurrences, etc. P(  X   )  0.5

## In contrast, for a continuous random

variable, we can only talk about the 0.5 0.5
probability of a range of values.
X
P(  X   )  1.0
73
75

Chapter 4 4-16

## General Procedure for

Finding Normal Probabilities The Empirical Rule
(continued)

## To find P(a < X < b) when X is  ± 2 covers about 95% of X’s

distributed normally:
 ± 3 covers about 99.7% of X’s
 Draw the normal curve for the problem in
terms of X
2 2 3 3
 Translate X-values to Z-values
x x

76 78

Empirical Rules

## What can we say about the distribution of values

around the mean? For any normal distribution:
f(X)