Chapter 5 Discrete Probability Distributions 1 Larson/Farber 4th ed
Dec 29, 2015
Chapter 5
Discrete Probability Distributions
1Larson/Farber 4th ed
Chapter Outline
• 5.1 Probability Distributions• 5.2 Binomial Distributions• 5.3 More Discrete Probability Distributions
Larson/Farber 4th ed 2
Section 5.1
Probability Distributions
3Larson/Farber 4th ed
Section 5.1 Objectives
• Distinguish between discrete random variables and continuous random variables
• Construct a discrete probability distribution and its graph
• Determine if a distribution is a probability distribution
• Find the mean, variance, and standard deviation of a discrete probability distribution
• Find the expected value of a discrete probability distribution
Larson/Farber 4th ed 4
Random Variables
Random Variable• Represents a numerical value associated with each
outcome of a probability distribution.• Denoted by x• Examples
x = Number of sales calls a salesperson makes in one day.
x = Hours spent on sales calls in one day.
5Larson/Farber 4th ed
Random Variables
Discrete Random Variable• Has a finite or countable number of possible
outcomes that can be listed.• Example
x = Number of sales calls a salesperson makes in one day.
x
1 530 2 4
6Larson/Farber 4th ed
Random Variables
Continuous Random Variable• Has an uncountable number of possible outcomes,
represented by an interval on the number line.• Example
x = Hours spent on sales calls in one day.
7Larson/Farber 4th ed
x
1 2430 2 …
Example: Random Variables
Decide whether the random variable x is discrete or continuous.
Solution:Discrete random variable (The number of stocks whose share price increases can be counted.)
x
1 3030 2 …
8Larson/Farber 4th ed
1. x = The number of stocks in the Dow Jones Industrial Average that have share price increaseson a given day.
Example: Random Variables
Decide whether the random variable x is discrete or continuous.
Solution:Continuous random variable (The amount of water can be any volume between 0 ounces and 32 ounces)
x
1 3230 2 …
9Larson/Farber 4th ed
2. x = The volume of water in a 32-ouncecontainer.
Discrete Probability Distributions
Discrete probability distribution• Lists each possible value the random variable can
assume, together with its probability. • Must satisfy the following conditions:
10Larson/Farber 4th ed
In Words In Symbols1. The probability of each value of
the discrete random variable is between 0 and 1, inclusive.
2. The sum of all the probabilities is 1.
0 P (x) 1
ΣP (x) = 1
Constructing a Discrete Probability Distribution
1. Make a frequency distribution for the possible outcomes.
2. Find the sum of the frequencies.
3. Find the probability of each possible outcome by dividing its frequency by the sum of the frequencies.
4. Check that each probability is between 0 and 1 and that the sum is 1.
11Larson/Farber 4th ed
Let x be a discrete random variable with possible outcomes x1, x2, … , xn.
Exercise 1: Constructing a Discrete Probability Distribution
An industrial psychologist administered a personality inventory test for passive-aggressive traits to 150 employees. Individuals were given a score from 1 to 5, where 1 was extremely passive and 5 extremely
Score, x Frequency, f
1 24
2 33
3 42
4 30
5 21
aggressive. A score of 3 indicated neither trait. Construct a probability distribution for the random variable x. Then graph the distribution using a histogram.
12Larson/Farber 4th ed
Solution: Constructing a Discrete Probability Distribution
• Divide the frequency of each score by the total number of individuals in the study to find the probability for each value of the random variable.
24(1) 0.16
150P
33(2) 0.22
150P 42
(3) 0.28150
P
30(4) 0.20
150P
21(5) 0.14
150P
x 1 2 3 4 5
P(x) 0.16 0.22 0.28 0.20 0.14
• Discrete probability distribution:
13Larson/Farber 4th ed
Solution: Constructing a Discrete Probability Distribution
This is a valid discrete probability distribution since
1. Each probability is between 0 and 1, inclusive,0 ≤ P(x) ≤ 1.
2. The sum of the probabilities equals 1, ΣP(x) = 0.16 + 0.22 + 0.28 + 0.20 + 0.14 = 1.
x 1 2 3 4 5
P(x) 0.16 0.22 0.28 0.20 0.14
14Larson/Farber 4th ed
Solution: Constructing a Discrete Probability Distribution
• Histogram
1 2 3 4 50
0.05
0.1
0.15
0.2
0.25
0.3
Passive-Aggressive Traits
Score, x
Pro
babi
lity
, P(x
)
Because the width of each bar is one, the area of each bar is equal to the probability of a particular outcome.
15Larson/Farber 4th ed
Mean
Mean of a discrete probability distribution• μ = ΣxP(x)• Each value of x is multiplied by its corresponding
probability and the products are added
16Larson/Farber 4th ed
x P(x) xP(x)
1 0.16 1(0.16) = 0.16
2 0.22 2(0.22) = 0.44
3 0.28 3(0.28) = 0.84
4 0.20 4(0.20) = 0.80
5 0.14 5(0.14) = 0.70
Exercise 2: Finding the Mean
The probability distribution for the personality inventory test for passive-aggressive traits is given. Find the mean.
μ = ΣxP(x) = 2.94
Solution:
17Larson/Farber 4th ed
Variance and Standard DeviationDefining Formulas
Variance of a discrete probability distribution
σ2 = Σ(x – μ)2P(x)
Standard deviation of a discrete probability distribution
2 2( ) ( )x P x
18Larson/Farber 4th ed
Exercise 3: Finding the Variance and Standard Deviation – Defining Formula
The probability distribution for the personality inventory test for passive-aggressive traits is given. Find the variance and standard deviation. ( μ = 2.94)
x P(x)
1 0.16
2 0.22
3 0.28
4 0.20
5 0.14
19Larson/Farber 4th ed
𝜎 2=∑ ¿¿
Solution: Finding the Variance and Standard Deviation – Defining Formula
• Recall μ = 2.94
2 1.616 1.3 Standard Deviation:
20Larson/Farber 4th ed
Score, x f P(x) (x -µ)2 (x -µ)2 * P(x)1 24
0.16 3.76 0.6022 33
0.22 0.88 0.1943 42
0.28 0.00 0.0014 30
0.20 1.12 0.2255 21
0.14 4.24 0.594
TOTAL 150 1.00 10.02 1.616
Exercise 4: Variance and Standard Deviation using Computational Formula
The probability distribution for the personality inventory test for passive-aggressive traits is given. Find the variance and standard deviation. ( μ = 2.94)
x P(x)
1 0.16
2 0.22
3 0.28
4 0.20
5 0.14
21Larson/Farber 4th ed
𝜎 2=∑ [𝑥2 ∙𝑃 (𝑥 ) ]−𝜇2
Finding the Variance and Standard Deviation – Computational Formula
Score, x f P(x) x * P(x) x2 * P(x)
1 24 0.16 0.16 0.162 33 0.22 0.44 0.883 42 0.28 0.84 2.524 30 0.20 0.80 3.205 21 0.14 0.70 3.50
TOTAL 150 1.00 2.94 10.26
2 1.616 1.3 Standard Deviation:
Variance:
22Larson/Farber 4th ed
= 10.26 – = 1.616
Exercise 5: Finding the Variance and Standard Deviation via TI-84
23Larson/Farber 4th ed
L1 L2Score, x f P(x)
1 24 0.162 33 0.223 42 0.284 30 0.205 21 0.14
1-Var Stats L1, L2
Expected Value
Expected value of a discrete random variable • Equal to the mean of the random variable.• E(x) = μ = Σ xP(x)• E(x) represents the “average” value of all the
outcomes• E(x) represents the value that we would expect to get
if the trials could continue forever!• Mathematical expectation plays an important role in
an area called decision theory
24Larson/Farber 4th ed
Example: Finding an Expected Value
At a raffle, 1500 tickets are sold at $2 each for four prizes of $500, $250, $150, and $75. You buy one ticket. What is the expected value of your gain?
25Larson/Farber 4th ed
Solution: Finding an Expected Value
• To find the gain for each prize, subtractthe price of the ticket from the prize: Your gain for the $500 prize is $500 – $2 = $498 Your gain for the $250 prize is $250 – $2 = $248 Your gain for the $150 prize is $150 – $2 = $148 Your gain for the $75 prize is $75 – $2 = $73
• If you do not win a prize, your gain is $0 – $2 = –$2
26Larson/Farber 4th ed
Solution: Finding an Expected Value
• Probability distribution for the possible gains (outcomes)
Gain, x $498 $248 $148 $73 –$2
P(x) 1
1500
1
1500
1
1500
1
1500
1496
1500
( ) ( )
1 1 1 1 1496$498 $248 $148 $73 ( $2)1500 1500 1500 1500 1500$1.35
E x xP x
You can expect to lose an average of $1.35 for each ticket you buy.
27Larson/Farber 4th ed
Exercise 6: Finding an Expected Value
• If you bet $1 in Kentucky’s Pick 4 Lottery, you either lose $1, or gain $4999.
• The winning prize is $5000, but your $1 bet is not returned, so the net gain is $4999.
• The game is played by selecting a four-digit number between 0000 and 9999.
If you bet $1 on 1234, what is your expected gain (or loss)?
Larson/Farber 4th ed 28
Solution: Finding an Expected Value
Larson/Farber 4th ed 29
To find the gain for each prize, subtract the price of the ticket from the value of the prize.
Description Payout Cost Gain (x)Fraction Decimal
Expected
Value
P(x) P(x) x*P(x)
Winner $5,000$1 $4,999 1/10000 0.0001 $0.50
Losing Ticket $0 $1 ($1)9999/10000 0.9999 ($1.00)
TOTAL 1 ($0.50)
Interpretation: In the long run, you can expect to lose an average of $ 0.50 for each $1 bet.
Section 5.1 Summary
• Distinguished between discrete random variables and continuous random variables
• Constructed a discrete probability distribution and its graph
• Determined if a distribution is a probability distribution
• Found the mean, variance, and standard deviation of a discrete probability distribution
• Found the expected value of a discrete probability distribution
Larson/Farber 4th ed 30
Section 5.2
Binomial Distributions
Larson/Farber 4th ed 31
Section 5.2 Objectives
• Determine if a probability experiment is a binomial experiment
• Find binomial probabilities using the binomial probability formula
• Find binomial probabilities using technology and a binomial table
• Find the mean, variance, and standard deviation of a binomial probability distribution
Larson/Farber 4th ed 32
Binomial Experiments
1. The experiment is repeated for a fixed number of trials, where each trial is independent of other trials
2. There are only two possible outcomes of interest for each trial. The outcomes can be classified as a success (S) or as a failure (F)
3. The probability of a success P(S) is the same for each trial
4. The random variable x counts the number of successful trials
Larson/Farber 4th ed 33
Notation for Binomial Experiments
Symbol Description
n The number of times a trial is repeated
p = P(S) The probability of success in a single trial
q = P(F) The probability of failure in a single trial q = (1 – p)
r The random variable represents a count of the number of successes in n trials: r = 0, 1, 2, 3, … , n.
Larson/Farber 4th ed 34
Example: Binomial Experiments
Decide whether the experiment is a binomial experiment. If it is, specify the values of n, p, and q, and list the possible values of the random variable r.
Larson/Farber 4th ed 35
1. A certain surgical procedure has an 85% chance of success. A doctor performs the procedure on eight patients. The random variable represents the number of successful surgeries.
Solution: Binomial Experiments
Binomial Experiment
1. Each surgery represents a trial. There are eight surgeries, and each one is independent of the others.
2. There are only two possible outcomes of interest for each surgery: a success (S) or a failure (F).
3. The probability of a success, P(S), is 0.85 for each surgery.
4. The random variable r counts the number of successful surgeries.
Larson/Farber 4th ed 36
Solution: Binomial Experiments
Binomial Experiment• n = 8 (number of trials)• p = 0.85 (probability of success)• q = 1 – p = 1 – 0.85 = 0.15 (probability of failure)• r = 0, 1, 2, 3, 4, 5, 6, 7, 8 (number of successful
surgeries)
Larson/Farber 4th ed 37
Example: Binomial Experiments
Decide whether the experiment is a binomial experiment.
If it is, specify the values of n, p, and q, and list the possible values of the random variable r.
Larson/Farber 4th ed 38
1. Flip a coin 6 times and count the number of times the coin lands on heads.
6
0.5
0,1,2,3,4,5,6
Example: Binomial Experiments
Decide whether the experiment is a binomial experiment. If it is, specify the values of n, p, and q, and list the possible values of the random variable r.
Larson/Farber 4th ed 39
2. A jar contains five red marbles, nine blue marbles, and six green marbles. You randomly select three marbles from the jar, without replacement. The random variable represents the number of red marbles.
Solution: Binomial Experiments
Not a Binomial Experiment
• The probability of selecting a red marble on the first trial is 5/20.
• Because the marble is not replaced, the probability of success (red) for subsequent trials is no longer 5/20.
• The trials are not independent and the probability of a success is not the same for each trial.
Larson/Farber 4th ed 40
Example: Finding Binomial Probabilities
Microfracture knee surgery has a 75% chance of success on patients with degenerative knees. The surgery is performed on three patients. Find the probability of the surgery being successful on exactly two patients.
Create a tree diagram and use it to compute this probability.
Larson/Farber 4th ed 41
Finding Binomial Probabilities via Binary Tree
Draw a tree diagram and use the Multiplication Rule
Larson/Farber 4th ed 42
9(2 ) 3 0.422
64P successful surgeries
Binomial Probability Formula
43Larson/Farber 4th ed
Binomial Probability Formula• The probability of exactly r successes in n trials is
• n = number of trials• p = probability of success• q = 1 – p probability of failure• r = number of successes in n trials
𝑃 (𝑟 )=𝑛𝐶𝑟 𝑝𝑟𝑞𝑛− 𝑟=
𝑛 !(𝑛−𝑟 )! 𝑟 !
𝑝𝑟𝑞𝑛−𝑟
Exercise 1: Finding Binomial Probabilities via Binomial Formula
Repeat the previous exercise using the binomial formula. .
Larson/Farber 4th ed 44
2 3 2
3 2
2 1
3 1(2 )
4 4
3! 3 1
(3 2)!2! 4 4
9 1 273 0.422
16 4 64
P successful surgeries C
𝑛=3 ,𝑝=34
,𝑟=2
Exercise 2: Finding Binomial Probabilities
Use TI-84 binompdf function
Larson/Farber 4th ed 45
TI-83/84 DISTR / 0: binompdf(n, p, r )
P(two successes ) = binompdf(3,0.75,2) =0.422
𝑛=3 ,𝑝=34
,𝑟=2
Exercise 3: Binomial Probability Distribution
• List the possible values of r with the corresponding probability of each.
• Example: Binomial probability distribution for Microfracture knee surgery: n = 3, p = Use binomial probability formula to find
probabilities.
Larson/Farber 4th ed 46
r 0 1 2 3
P(r)
3
4
Exercise 3: Binomial Probability Distribution
Binomial Probability Distribution• Solution: Binomial probability distribution for
Microfracture knee surgery: n = 3, p = 0.75
Larson/Farber 4th ed 47
r 0 1 2 3
P(r) 0.016 0.141 0.422 0.422
Exercise 3: Binomial Probability Distribution via TI-84
• Microfracture knee surgery: n = 3, p = 0.75
Larson/Farber 4th ed 48
L1 L2 =binompdf(3,0.75, L1) r P(r)
0 0.0161 0.1412 0.4223 0.422
TOTAL 1.000
Example: Construct a Binomial Distribution
In a survey, workers in the U.S. were asked to name their expected sources of retirement income. Seven workers who participated in the survey are randomly selected and asked whether they expect to rely on Social
Larson/Farber 4th ed 49
Security for retirement income. Create a binomial probability distribution for the number of workers who respond yes.
Solution: Constructing a Binomial Distribution
• 25% of working Americans expect to rely on Social Security for retirement income.
• n = 7, p = 0.25, q = 0.75, r = 0, 1, 2, 3, 4, 5, 6, 7
Larson/Farber 4th ed 50
P(r = 0) = 7C0(0.25)0(0.75)7 = 1(0.25)0(0.75)7 ≈ 0.1335
P(r = 1) = 7C1(0.25)1(0.75)6 = 7(0.25)1(0.75)6 ≈ 0.3115
P(r = 2) = 7C2(0.25)2(0.75)5 = 21(0.25)2(0.75)5 ≈ 0.3115
P(r = 3) = 7C3(0.25)3(0.75)4 = 35(0.25)3(0.75)4 ≈ 0.1730
P(r = 4) = 7C4(0.25)4(0.75)3 = 35(0.25)4(0.75)3 ≈ 0.0577
P(r = 5) = 7C5(0.25)5(0.75)2 = 21(0.25)5(0.75)2 ≈ 0.0115
P(r = 6) = 7C6(0.25)6(0.75)1 = 7(0.25)6(0.75)1 ≈ 0.0013
P(r = 7) = 7C7(0.25)7(0.75)0 = 1(0.25)7(0.75)0 ≈ 0.0001
Solution: Constructing a Binomial Distribution
Larson/Farber 4th ed 51
r P(r)
0 0.1335
1 0.3115
2 0.3115
3 0.1730
4 0.0577
5 0.0115
6 0.0013
7 0.0001
All of the probabilities are between 0 and 1 and the sum of the probabilities is 1.00001 ≈ 1.
Exercise 4: Finding Binomial Probabilities
A survey indicates that 41% of women in the U.S. consider reading their favorite leisure-time activity. You randomly select four U.S. women and ask them if reading is their favorite leisure-time activity. Find the probability that at least two of them respond yes.
Larson/Farber 4th ed 52
Solution: • n = 4, p = 0.41, q = 0.59• At least two means two or more.• Find the sum of P(2), P(3), and P(4).
Solution: Finding Binomial Probabilities
Larson/Farber 4th ed 53
P(r = 2) = 4C2(0.41)2(0.59)2 = 6(0.41)2(0.59)2 ≈ 0.351094
P(r = 3) = 4C3(0.41)3(0.59)1 = 4(0.41)3(0.59)1 ≈ 0.162654
P(r = 4) = 4C4(0.41)4(0.59)0 = 1(0.41)4(0.59)0 ≈ 0.028258
P(r ≥ 2) = P(2) + P(3) + P(4) ≈ 0.351094 + 0.162654 + 0.028258 ≈ 0.542
Section 5.3 Objectives
• Use the binomial table to find P(r )• Make histograms for binomial distributions• Compute µ and • Compute the minimum number of trials n needed to
achieve a given probability of success P(r).
Larson/Farber 4th ed 54
Exercise 1: Finding Binomial Probabilities Using a Table
About thirty percent of working adults spend less than 15 minutes each way commuting to their jobs. You randomly select six working adults. What is the probability that exactly three of them spend less than 15 minutes each way commuting to work? Use a table to find the probability. (Source: U.S. Census Bureau)
Larson/Farber 4th ed 55
Solution:• Binomial with n = 6, p = 0.30, r = 3
Solution: Finding Binomial Probabilities Using a Table
• A portion of Table 2 is shown
Larson/Farber 4th ed 56
The probability that exactly three of the six workers spend less than 15 minutes each way commuting to work is 0.185.
Exercise 2: Graphing a Binomial Distribution
Fifty-nine percent of households in the U.S. subscribe to cable TV. You randomly select six households and ask each if they subscribe to cable TV. Construct a probability distribution for the random variable x. Then graph the distribution. (Source: Kagan Research, LLC)
Larson/Farber 4th ed 57
Solution: • n = 6, p = 0.59, q = 0.41• Find the probability for each value of r
Graphing a Binomial Distribution
Solution: Graphing a Binomial Distribution
Larson/Farber 4th ed 59
x 0 1 2 3 4 5 6
P(x) 0.005 0.041 0.148 0.283 0.306 0.176 0.042
0 1 2 3 4 5 60
0.05
0.1
0.15
0.2
0.25
0.3
0.35
Subscribing to Cable TV
Households
Pro
babi
lity
Histogram:
Mean, Variance, and Standard Deviation
• Mean: μ = np
• Variance: σ2 = npq
• Standard Deviation:
Larson/Farber 4th ed 60
npq
Exercise 3: Finding the Mean, Variance, and Standard Deviation
In Pittsburgh, Pennsylvania, about 56% of the days in a year are cloudy. Find the mean, variance, and standard deviation for the number of cloudy days during the month of June. Interpret the results and determine any unusual values. (Source: National Climatic Data Center)
Larson/Farber 4th ed 61
Solution: n = 30, p = 0.56, q = 0.44
Mean: μ = np = 30∙0.56 = 16.8Variance: σ2 = npq = 30∙0.56∙0.44 ≈ 7.4Standard Deviation: 30 0.56 0.44 2.7npq
Solution: Finding the Mean, Variance, and Standard Deviation
Larson/Farber 4th ed 62
μ = 16.8 σ2 ≈ 7.4 σ ≈ 2.7
• On average, there are 16.8 cloudy days during the month of June.
• The standard deviation is about 2.7 days. • Values that are more than 2.5 standard deviations
from the mean are considered unusual: 16.8 – 2.5(2.7) =10.05, A June with 10 cloudy
days would be unusual. 16.8 + 2.5 (2.7) =23.55 A June with 24 cloudy
days would also be unusual.
Binomial Probabilities: Equivalent Formulas
Larson/Farber 4th ed 63
Exercise 4: Compute Binomial Probabilities
If 22% of U.S. households have a Nintendo game, compute the probability that
a. exactly 5 of 12 randomly chosen families will have Nintendo games.
b. at most, 5 randomly chosen families will have Nintendo games.
Larson/Farber 4th ed 64
Solution: Compute Binomial Probabilities
Larson/Farber 4th ed 65
L1 L2 =binompdf(12,0.22,L1)
r P(r)
0 0.0507
1 0.1717
2 0.2663
3 0.2503
4 0.1589
5 0.0717
TOTAL 0.9696
Solution: Compute Binomial Probabilities
Larson/Farber 4th ed 66
r P(r)
5binompdf(12, 0.22, 5) = 0.0717
a) P(exactly 5 of 12 randomly chosen families will have Nintendo games)
P(5) = binompdf(12,0.22,5) = 0.0717
Solution: Compute Binomial Probabilities
Larson/Farber 4th ed 67
b) P(at most five randomly chosen families will have Nintendo games)
P(
r P(r)
0 binompdf(12, 0.22, 0) = 0.0507
1 binompdf(12, 0.22, 1) = 0.1717
2 binompdf(12, 0.22, 2) = 0.2663
3 binompdf(12, 0.22, 3) = 0.2503
4 binompdf(12, 0.22, 4) = 0.1589
5binompdf(12, 0.22, 5) = 0.0717
sum = 0.9696
Exercise 5: Use Binomial Cumulative Density Function
If 22% of U.S. households have a Nintendo game, compute the probability that at most, 5 of 12 randomly chosen families will have Nintendo games.
Larson/Farber 4th ed 68
Solution:
P( binomcdf( 12,0.22,5) = 0.9696
Quota Problems
• We can use the binomial distribution table “backwards” to solve for a minimum number of trials.
• Given: r and p• Find: value of n that satisfies requirement for
expected value, or reliability specification• Use calculator technology or tables together with
guess/check strategy• Show minimum of three guesses and three checks
Example: Satisfy Quota for Expected Value of Distribution
Suppose a satellite requires 3 solar cells for its power, the probability that any one of these cells will fail is 0.15, and the cells operate and fail independently.
We want to find the least number of cells each satellite should have so that the expected number of working cells (the mean) is no smaller that 3. That is, n is the total number of cells, and r is the number of working cells, p is probability that a cell will work.
Larson/Farber 4th ed 70
Example: Satisfy Quota for Expected Value of Distribution
We want to find the least number of cells each satellite should have so that the expected number of working cells (the mean) is no smaller that 3. That is, n is the total number of cells, and r is the number of working cells, p is probability that a cell will work, and Since
Let S = “cell works” p = 0.85, q = 0.15
Larson/Farber 4th ed 71
cell 1 cell 2 cell 3 … cell n
Example: Satisfy Quota for Expected Value of Distribution
Larson/Farber 4th ed 72
cell 1 cell 2 cell 3 … cell n
Example: Satisfy Quota for Expected Value of Distribution
Larson/Farber 4th ed 73
p= 0.85 q = 0.15 n= 4
r P(r)0 0.0011 0.0112 0.0983 0.3684 0.522
TOTAL 1.000 0 1 2 3 4 TOTAL0.000
0.100
0.200
0.300
0.400
0.500
0.600
Probability Distribution: n = 4, p = 0.85
r
P(r
)
==>
Example: Satisfy Quota for Expected Value of Distribution
Larson/Farber 4th ed 74
==>
Interpretive Statement: If we put up lots of satellites with four cells, we can expect that an average of 3.4 cells will work in each satellite. Note that each additional solar satellite will produce four new cells (e.g. trials) of the binomial experiment.
Exercise 6: Satisfy Reliability Quota
Suppose a satellite requires 3 solar cells for its power, the probability that any one of these cells will fail is 0.15, and the cells operate and fail independently.
We want to find the smallest number of cells the satellite should have to be 99% sure that there will be adequate power (i.e. at least three cells work).
How many cells do we need to meet the specification P(?
Larson/Farber 4th ed 75
P(fail) = 0.15
P(fail) = 0.15
P(fail) = 0.15
. . . P(fail) = 0.15
Exercise 6: Satisfy Reliability Quota
Larson/Farber 4th ed 76
n P(r >=3 ) = 1 - P( r <=2) Expected Successes x Y1 = 1 - binomcdf(x,0.85,2) µ = np
3 0.6141 2.55
4 0.8905 3.40
5 0.9734 4.25
6 0.9941 5.10
7 0.9988 5.95
Exercise 6: Satisfy Reliability Quota
Conclusion: We need at least 6 cells to be 99%sure that all satellites will be operational.
Larson/Farber 4th ed 77
Interpretive Statement: In order to meet the 99% reliability specification, we will need to install at least 6 cells in each satellite to ensure that the satellite will be fully operational.
Exercise 6: Interpretive Statement
Larson/Farber 4th ed 78
• If ___ cells are installed in a satellite, then there is a 99% probability that the satellite will be operational.
OR • 99% of all satellites with ____ cells in them will be
operational.
Exercise 6: Interpretive Statement(s)
Larson/Farber 4th ed 79
• If 6 cells are installed in a satellite, then there is a 99% probability that the satellite will be operational.
OR • 99% of all satellites with 6 cells in them will be fully
operational.
Section 5.3 Summary
• Determined if a probability experiment is a binomial experiment
• Found binomial probabilities using the binomial probability formula
• Graphed a binomial distribution• Found the mean, variance, and standard deviation of
a binomial probability distribution• Solved quota problems
Larson/Farber 4th ed 80
Section 5.4
More Discrete Probability Distributions
Larson/Farber 4th ed 81
Section 5.4 Objectives
• Find probabilities using the geometric distribution• Find probabilities using the Poisson distribution• Use a Poisson Approximation to the Binomial
Distribution
Larson/Farber 4th ed 82
Exercise 1: Geometric Distribution
Susan is taking Western Civilization on a pass/fail basis. Historically, the passing rate for this course has been 77% each term. Let n = 1, 2, 3, . . . represent the number of times a student takes this course until a passing grade is received. Assume the attempts are independent.
Construct a tree diagram for n = 1, 2, and 3 attempts. List the outcomes and their associated probabilities.
Larson/Farber 4th ed 83
Exercise 1: Geometric Distribution
Susan is taking Western Civilization on a pass/fail basis. Historically, the passing rate for this course has been 77% each term. Use your tree diagram to compute:
a) What is the probability that Susan passes on the first try?
b) What is the probability that Susan passes on the second try?
c) What is the probability that Susan passes on the third try?
d) What is the probability that Susan passes on the nth try?
Larson/Farber 4th ed 84
Exercise 1: Geometric Distribution
Larson/Farber 4th ed 85
n Factors P(n)
1 0.77 0.770
2 0.23 0.77 0.177
3 0.23 0.23 0.77 0.041
Geometric Distribution
A discrete probability distribution. It satisfies the following conditions:
A trial is repeated until a success occurs
The repeated trials are independent of each other
The probability of success p is constant for each trial
• The probability that the first success will occur on trial n is P(n) = p(q)n – 1, where q = 1 – p.
Larson/Farber 4th ed 86
Geometric Distribution
Larson/Farber 4th ed 87
Geometric Distribution – TI-84 Calculator
The probability of success on exactly the nth try is given by
Larson/Farber 4th ed 88
1 2 3 . . . n
Geometric Distribution – TI-84 Calculator
The probability that a success will occur on or before the nth try is given by
Larson/Farber 4th ed 89
1 2 3 . . .
Geometric Distribution – TI-84 Calculator
The probability that a success will occur after try is given by =
Larson/Farber 4th ed 90
1 2
Exercise 2 Solution: Geometric Distribution
Susan is taking Western Civilization on a pass/fail basis. Historically, the passing rate for this course has been 77% each term. Complete the following table:
Larson/Farber 4th ed 91
Probability Description Probability Expression
TI-84 Command
success on exactly the 3rd trysuccess on or before the 3rd trysuccess after the 3rd try
Exercise 2 Solution: Geometric Distribution
Susan is taking Western Civilization on a pass/fail basis. Historically, the passing rate for this course has been 77% each term. Complete the following table:
Larson/Farber 4th ed 92
Probability Description
Probability Expression TI-84 Command
success on exactly the 3rd try
= 0.041
success on or before the 3rd try
= 0.988
success after the 3rd try
= = 0.012
Exercise 3: Geometric Distribution
From experience, you know that the probability that you will make a sale on any given telephone call is 0.23. Find the probability that your first sale on any given day will occur on your fourth or fifth sales call.
Larson/Farber 4th ed 93
Solution:• P(sale on fourth or fifth call) = P(4) + P(5)• Geometric with p = 0.23, q = 0.77, n = 4, 5
Solution: Geometric Distribution
• P(4) = 0.23(0.77)4–1 ≈ 0.105003• P(5) = 0.23(0.77)5–1 ≈ 0.080852
Larson/Farber 4th ed 94
P(sale on fourth or fifth call) = P(4) + P(5)
≈ 0.105003 + 0.080852
≈ 0.186
Poisson Distribution
A discrete probability distribution. It satisfies the following conditions:
The experiment consists of counting the number of times an event occurs in a given interval
The interval can be an interval of time, area, or volume
The probability of the event occurring is the same for each interval
The number of occurrences in one interval is independent of the number of occurrences in other intervals
Larson/Farber 4th ed 95
The Poisson Distribution
• This distribution is used to model the number of “rare” events that occur in a time interval, volume, area, length, etc…
• Examples: Number of auto accidents during a month Number of diseased trees in an acre Number of customers arriving at a bank
Poisson Distribution
• The probability of exactly r occurrences in an interval is
Larson/Farber 4th ed 97
where e 2.71828 and λ is the mean number of occurrences in the interval
The Poisson Distribution
Exercise 4: Poisson Distribution
The mean number of accidents per month at a certain intersection is 3. What is the probability that in any given month four accidents will occur at this intersection?
Larson/Farber 4th ed 99
= , r =4
Exercise 5: Poisson Distribution
On average, boat fishermen on Pyramid Lake catch 0.667 fish per hour. Suppose you decide to fish the lake on a boat for 7 hours.
a) What is S ?
b) What is the expected number of fish caught over the 7-hour period?
c) Construct a table for r = 0, 1, 2, . . ., 8 fish
Larson/Farber 4th ed 100
r 0 1 2 3 4 5 6 7 8
P(r)
Exercise 5 Solution: Poisson Distribution
On average boat fishermen on Pyramid Lake catch 0.667 fish per hour. Suppose you decide to fish the lake on a boat for 7 hours.
a) What is S? S = fish is caught
b) What is the expected number of fish caught over the 7-hour period?• = • // Expected number of fish caught in a 7 hour
period
Larson/Farber 4th ed 101
Exercise 5 Solution: Poisson Distribution
On average boat fishermen on Pyramid Lake catch 0.667 fish per hour. Suppose you decide to fish the lake on a boat for 7 hours.
c) Construct a table for r = 0,1,2,3 … 8 fish
Larson/Farber 4th ed 102
λ 4.7
L1 r 0 1 2 3 4 5 6 7 8
L2
P(r) = poissonpdf(4.7, L1) 0.009 0.043 0.100 0.157 0.185 0.174 0.136 0.091 0.054
Exercise 5 Solution: Poisson Distribution
Larson/Farber 4th ed 103
Probability Description
Probability Expression TI-84 Command
At least 4 fish?
More than 7 fish?
Between 2 and 5 fish inclusive
Finding Poisson ProbabilitiesUsing the Table
• We can use Page A-16 instead of the formula:
1) Find λ at the top of the table
2) Find r along the left margin of the table
Using the Poisson Table Page A17
Recall, λ = 4
r = 0
r = 4
r = 7
Poisson Approximation to the Binomial
Exercise 6: Poisson Approximation to the Binomial
In Kentucky’s Pick 4 game, you pay $1 to select a sequence of four digits, such as 2283. If you play this game once every day, find the probability of winning exactly once in 365 days.
Solution: Consider a binomial experiment:1. 2. Because there is one winning set of numbers among the 10,000 that are possible
Example: Poisson Approximation to the Binomial
1. [n = 365]2. [ np = 0.0365]
Conclusion: We may use the Poisson distribution as an approximation to the binomial distribution. Winning is a “rare” event.
= On average, we can expect to win 0.0365 times in a 365-day interval.
Example: Poisson Approximation to the Binomial
Interpretive Statement: The probability of winning exactly once in a 365-day interval is about 0.035.
Section 5.4 Summary
• Found probabilities using the geometric distribution• Found probabilities using the Poisson distribution• Used a Poisson Approximation to the Binomial
Distribution
Larson/Farber 4th ed 110