Chapter 5

Discrete Probability Distributions

Section 5-1 Exercises

5.1 a. The variable, x, is a discrete random variable because x can take on only specific
integer values.

b. The possible values for x are:

x = {0, 1, 2, 3, 4, 5, 6}

5.3
a. The random variable is x, the number of children under 22 living in a household.

b. The random variable is discrete since the values for x can take on only specific integer
values such as 0, 1, 2, 3, 4, …

5.5 The expected value of a discrete probability distribution is determined using:

E ( x) = ∑ xP( x)

The calculations are:

Thus, the expected number of days per week that the helicopter company can operate per
week is 3.7 days.

Copyright ©2024 Pearson Education, Inc.

75
5.7.
a. The expected value of x is calculated using equation 5-1, E(x) = ∑ xP(x).
E(x) = (100)(0.25) + (125)(0.30) + (150)(0.45) = 130.

b. The variance of x is calculated using the following equation, ∑[x-E(x)]2P(x). The

calculations are shown below

x P(x) xP(x) [x-E(x)] [x-E(x)]2P(x)

100 0.25 25 -30 225
125 0.3 37.5 -5 7.5
150 0.45 67.5 20 180
The variance of x is equal to 225 + 7.5 + 180 = 412.50.

c. The standard deviation is computed using equation 5-2. The standard deviation is the
positive square root of the variance calculated in (b) above.

σx = 412.50 = 20.31

5.9.
a. E(x) = ΣxP(x) = 5(0.10) + . . . + 20(0.50) = 15.75,

b. The probability distribution of y is

y P(y)
10 0.10
15 0.15
20 0.25
25 0.50.

E(y) = ΣyP(y) =10(0.10) + . . . + 25(0.50) = 20.75

c. The probability distribution of Z is

z P(z)
25 0.10
50 0.15
75 0.25
100 0.50.

E(z) = ΣzP(z) = 25(0.10) + . . . + 100(0.50) = 78.75,

d. Adding a constant (in this case 5) increases the expected value by an amount equal to
the constant added.

Copyright ©2024 Pearson Education, Inc.

76
 e. Multiplying by a constant (in this case 5) results in the expected value being multiplied
by that same constant.

5.11
a. E(X) = ΣxP(x) = 2(0.27) + . . . + 7(0.03) = 3.51.

b. σ2 = Σ(x – E(x))2 P(x)= (-1.51)2(0.27) + . . . + 3.492(0.03) = 1.6499,

σ = σ 2 = 1.6499 = 1.2845.

5.13
a. The expected value of a discrete probability distribution is determined using:
E ( x) = ∑ xP( x)
The calculations are shown as follows:

x P(x) xP(x)
1 0.15 0.15
2 0.25 0.5
3 0.3 0.9
4 0.18 0.72
5 0.12 0.6
Sum = 2.87

Thus, the expected number of days that will be required to repair HDTVs is 2.87 days.

b. The variance for a discrete random variable is computed using the following equation:
σ 2 = ∑ [ x − E ( x)] 2 P( x)
The calculations are shown as follows:

x P(x) xP(x) [x - E(x)] [x-E(x)]2 [x-E(x)]2P(x)

1 0.15 0.15 -1.87 3.4969 0.5245
2 0.25 0.5 -0.87 0.7569 0.1892
3 0.3 0.9 0.13 0.0169 0.0051
4 0.18 0.72 1.13 1.2769 0.2298
5 0.12 0.6 2.13 4.5369 0.5444
Sum = 2.87 1.4931
The variance is 1.4931 days squared. The standard deviation is the square root of the
variance as follows:
σ = ∑ [ x − E ( x)] 2
P( x)
σ = 1.4931 = 1.22

The standard deviation is 1.22 days.

Copyright ©2024 Pearson Education, Inc.

77
 c. Based on the probability distribution, the chances of exceeding 4 days for repair time
is 0.12. Thus, not all repair times can be expected to be done in 4 days or less. However,
using the Empirical rule from Chapter 3, if the distribution is approximately bell shaped,
about 68% of the occurrences will be within one standard deviation of the mean so the
manager can expect about two-thirds of the time to repairs within the range:
2.87 + 1.22
1.65 days to 4.09 days.

5.15
a. To determine the total expected cost, you would first find the expected proportion of
defects based on the discrete probability distribution that was assessed based on historical
data. The expected value of a discrete probability distribution is determined using:
E ( x) = ∑ xP( x)

a. The expected proportion of defects is:

E[x] = (.01) (.4) + (.02)(.3) + (.05) (.2) + (.10) (.1) =

.004 + .006 + .01 + .01 = .03

Expected cost = 2,000 x $29 + 2000 x 0.03 x $5 = $58,000 + $300 = $58,300

b. The expected proportion of defects is

E[x] = (.01) (.40) + (.02)(.1) + (.05) (.7) + (.10) (.1) =

.001 + .002 + .035 + .01 = .048

Expected Cost = 2000 x $28.50 + 2000 x .048 x $5 = $57,000 + $480 = $57,480

Purchase from new supplier because total cost is lower - $57,480 < $58,300
The $0.50 per unit cost savings on the purchase price offsets the cost associated with the
higher expected defect proportion from the new supplier.

5.17

a. Profit = Sales – Costs

Small firm profits: 0.75(300000) – 150000 = 75000,
0.75(400000) – 150000 = 150000 (can’t sell more than produced)
0.75(400000) – 150000 = 150000
E(X) = ΣxP(x) = 75000(0.2) + 150000(0.5) + 150000(0.3) = $135,000.

Mid-sized profits: 0.75(300000) – 250000 = -25000,

0.75(600000) – 250000 = 200000 (can’t sell more than produced)
0.75(600000) – 250000 = 200000

Copyright ©2024 Pearson Education, Inc.

78
 E(X) = ΣxP(x) = -25000(0.2) + 200000(0.5) + 200000(0.3) = $155,000

Large firm profits: 0.75(300000) – 350000 = -125000,

0.75(700000) – 350000 = 175000
0.75(900000) – 350000 = 325000
E(X) = ΣxP(x) = -125000(0.2) + 175000(0.5) + 325000(0.3) = $160,000.

b. σ2 = Σ(x – E(X))2 P(x)

Small firm: σ2 = (-60000)2(0. 2) + 150002(0. 5) + 150002(0.3) = 900000000,
σ= σ2 = 900000000 = $30,000

Mid-sized firm: σ2 = (-180000)2(0. 2) + 450002(0. 5) + 450002(0.3) = 8.1 x 109,

σ= σ2 = 8.1 x 10 9 = $90,000.

Large firm: σ2 = (-285000)2(0. 2) + 150002(0. 5) +1650002(0.3) = 2.45 x 1010,

σ= σ2 = 2.45 x 1010 = $156,604.60.

c. The large firm has the largest expected profit. This would be the choice unless the
corporate board was risk adverse. In which case, the mid-sized firm has almost as large
an expected profit and a standard deviation that is 43% (1 – 90000/156604.60) smaller
than that of the large firm’s.

5.19
a. The frequency distribution is

Sold Count Percent

1 2 1.33
2 7 4.67
3 18 12.00
4 30 20.00
5 44 29.33
6 24 16.00
7 15 10.00
8 6 4.00
9 4 2.67
N= 150

Copyright ©2024 Pearson Education, Inc.

79
 b. Let X = the number of magazines sold, then the probability distribution is

x 0 1 2 3 4 5 6 7 8 9 10
P(x) 0 0.013 0.047 0.120 0.200 0.293 0.160 0.100 0.040 .027 0

E(X) = ΣxP(x) = 0(0) + 1(0.013) + . . . + 10(0) = 4.955

E(Profit) = E(sales) – cost = 3.49E(X) – 10(1.95) = 3.49E(X) – 19.50 = 3.49(4.955) –
19.50 = -$2.21

c. Since the expected loss is $2.21 for the ten magazines to obtain a positive expected
profit, the salvage value per magazine would have to be = 2.21/10 = $0.221 or $0.23.

5.21
a. Step 1: Convert the frequency distribution into a probability distribution using the
relative frequency of occurrence method. The frequency distribution is

Months Count Percent

14 1 0.80
15 3 2.40
16 8 6.40
17 6 4.80
18 23 18.40
19 27 21.60
20 30 24.00
21 16 12.80
22 9 7.20
23 2 1.60
N= 125

x 14 15 16 17 18 19 20 21 22 23
P(x) 0.008 0.024 0.064 0.048 0.184 0.216 0.240 0.128 0.072 0.016

b. Step 2: Compute the expected value using Equation 5-1.

E(x) = ΣxP(x) =14(0.008) + 15(0.024) + . . . + 23(0.016) = 19.168.
Step 3: Compute the standard deviation using 5-2.
σ2 = Σ(x – E(x))2 P(x)= (-5.168)2(0.008) + (-4.168)2(0.024) + . . . + 3.832(0.016) =
3.1638, (2) σ = σ 2 = 3.1638 = 1.7787.

c. For the majority of the covers to last longer than 19 months, the median would have to
be at most 19. The probability of lasting more than 19 months is 0.456 so the quality
control department is incorrect.

Copyright ©2024 Pearson Education, Inc.

80
Section 5-2 Exercises

5.23
The following steps are used to solve this problem:
Step 1: Define the characteristics of the binomial distribution.
n = 10, p = .30, x = 3

Step 2: Determine the probability of x successes in n trials using the binomial formula.
n!
P( x= 3)= p x (1 − p ) n − x
x !(n − x)!
10!
P( x= 3)= 0.303 (1 − 0.30)10−3
3!(10 − 3)!
P ( x= 3)= (120)(0.027)(0.082)
P ( x= 3)= 0.2668
There is a 0.2668 chance of observing 3 successes in a sample of ten items selected
randomly from a population in which the probability of a success is 0.30.

5.25 Use binomial table for n = 20

a. P(x = 5) = P(x < 5) - P(x < 4) = 0.1256 – 0.0510 = .0746
b. P(x > 7) = 1 - 7858 = .2142
c. E[x] = np = 20(.20) = 4
d. σ = npq = 20(.20)(.80) = 1.7889

5.27 This problem can be solved using the following steps:

Step 1: Define the characteristics of the binomial distribution.
n = 10, p = .70, x = 5
Step 2: Go to the binomial table in Appendix B. Locate the appropriate section of the
table for a sample size of n = 10 and the column with q = 0.70 at the bottom (p
= .30 at the top).
Step 3: Define the event of interest and obtain the desired probabilities from the binomial
table.
The event of interest is:
P(x < 5) – P(x < 4) = 0.1503 – 0.0473 = 0.1030
There is a 0.1030 probability that exactly five successes will be observed in a
sample of 10 items if the probability of a success is 0.70.

5.29
a.
Step 1: Define the characteristics of the binomial distribution.
In this case the characteristics are n = 7, p = 0.65, and q = 1-p = 0.35.
Step 2: Define the probability of the event of interest in terms of the binomial
probabilities given in Appendix B.
P(x = 3) = P(x ≤ 3) - P(x < 2)

Copyright ©2024 Pearson Education, Inc.

81
 Step 3: Locate the appropriate section (e.g., sample size, n) and column (e.g., probability
of success, p) in Appendix B.
The sample size is n = 7, and the probability of a success is p = 0.65.
Step 4: Locate the desired probability (probabilities) in the Appendix B and calculate the
probability of the event of interest.
We are interested in the probability of exactly 3 successes. P(x = 3) = P(x ≤ 3) -
P(x ≤ 2) = 0.1998 - .0556 = 0.1442.
b.
Steps 1 and 2 are identical to (a) above.
Step 3: the event of interest is the probability of four or more successes.
P(x > 4) = 1 – P(x < 3) = 1 – 0.1998 = 0.80020
c.
Steps 1,2 and 3 are identical to (a) above.
Step 4: the event of interest is the probability of exactly 7 successes. P(x = 7) = P(x ≤ 7) -
P(x ≤ 6) = 1 – 0.9510 = 0.0490.
d. The expected value of the random variable can be found using the equation 5-5, E(x) =
np = (7)(0.65) = 4.55

5.31
a. n = 6, p = 0.08, P(x = 2) = P(x < 2) - P(x < 1) = 0.9915 – 0.9227 = 0.0688.
b. n = 9, p = 0.80, P(x < 4) = P(x ≤ 3) = 0.0031.
c. n = 11, p = 0.65, P(2 < x ≤ 5) = P(x ≤ 5) - P(x ≤ 2 ) = 0.1487 – 0.0020 = 0.1467.
d. n = 14, p = 0.95, P(x ≥ 13) = 1 - P(x ≤ 12) = 1 – 0.1530 = 0.8470.
e. n = 10, p = 0.50, P(x > 3) = 1 - P(x ≤ 3) = 1 - 0.0013 = 0.9987

5.33
a. E(x) = np = 8(0.40) = 3.2
b. σ = npq = 8(0.4)(1 − 0.4) = 1.92 = 1.386
c. P(x > 3.2) = P(x ≥ 4) = 1 – P(x < 3) = 0.4059.
d. P(µ - 2σ ≤ x ≤ µ + 2σ) = P[3.2 – 2(1.386) ≤ x ≤ 3.2 + 2(1.386)] = P(0.428 ≤ x ≤ 5.972)
= P(1 < x ≤ 5) = P(x < 5) – P(x = 0) = 0.9502 – 0.0168 = 0.9334

5.35
a. Step 1: Define the characteristics of the binomial distribution:
n = 10, p = 0.34, q = 1 – p = 1 – 0.34 = 0.66.
Step 2: Use equation 5-4 to find the expected value:
µX = E(X) = np = 10(0.34) = 3.4
b. Step 1: Define the characteristics of the binomial distribution:
n = 10, p = 0.66, q = 1 – p = 1 – 0.66 = 0.34.
Step 2: Determine the probability of x successes in n trials using the binomial formula,
Equation 5-4:
10 
P(X = 10) =   0.6610 (0.34)10−10 = 0.0157
10 

Copyright ©2024 Pearson Education, Inc.

82
 c. Step 1: Define the characteristics of the binomial distribution:
n = 10, p = 0.66, q = 1 – p = 1 – 0.66 = 0.34.
Step 2: Determine the probability of x successes in n trials using the binomial formula,
Equation 5-4:
10  10 
P(X ≥ 8) = P(X = 8) + P(X = 9) + P(X = 10) =   0.668 (0.34)10−8 +   0.669 (0.34)10−9
8  9 
10 
+   0.6610 (0.34)10−10 = 0.2838.
10 

5.37
a. The sampling process meets the characteristics of a binomial distribution with n = 20,
p = 0.04. We are interested in the event that x = 0 defective dowel holes are observed in
the sample. The binomial table can be used to find this probability by going to the
section of the table for n = 20 and the column headed p = 0.04.
The event of interest is:
P(x = 0)
The probability from the table is:
P(x = 0) = 0.4420
Thus, the probability that the sampling plan will properly lead the company to let the
process continue operating when the defect rate is at the acceptable level of 0.04 is
0.4420. Note, however, that
P(x > 1) = 1 – 0.4420 = 0.5580
There is over a 55% chance that the sample will provide a result that causes the managers
to stop the drilling process for re-calibration even though the process is working
correctly. That would be a costly mistake.
b. The sampling process meets the characteristics of a binomial distribution with n = 20,
p = 0.10. We are interested in the event that x > 1 defective dowel holes are observed in
the sample. The binomial table can be used to find this probability by going to the
section of the table for n = 20 and the column headed p = 0.10.
The event of interest is:
P(x > 1) = 1 – P(x = 0)
P(x > 1) = 1 – 0.1216 = 0.8784
Thus, there is over an 87% chance that the sample will correctly tell the managers to stop
the process when the defect rate is 0.10. This is a high probability, which is good.

c. Individual letters will differ but should conclude that the sampling plan does a good
job of detecting when the defect rate is higher than acceptable ( p = 0.10) but is not
effective at allowing the process to continue operating when the defect rate is at the
acceptable rate of 0.04. An increase in sample size would be required to improve this.

5.39 n=8, p=0.37

a. Expected number = 8(0.37) = 2.96
b. Variance = 8(0.37)(0.63) = 1.8648, standard deviation = 1.3656

Copyright ©2024 Pearson Education, Inc.

83
 c. P(x < 2) = (Using the Binomial formula) P(x = 0) + P(x = 1) + P(x = 2)= 0.0248 +
0.1166 + 0.2397 = 0.3811

5.41
a. If 5 or more confirmed guests do not show then no guests will be sent to another hotel.
Therefore, we find the probability of 5 or more successes, where a success is defined as a
confirmed reservation that does not show. In this case n = 25, p = 0.15 and x = number
of no shows. The P(x > 5) = 1 – P( x < 4) = 1 - 0.6821 = 0.3179.
b. The probability that exactly two confirmed guests will be sent to another hotel is the
probability of there being exactly 3 successes. That is there are 3 no shows from the 25
confirmed reservations leaving 22 guests for only 20 rooms. The probability is found to
be P(x = 3) = P(x < 3) - P(x < 2) = 0.4711 – 0.2537 = .2174.
c. The probability that three or more guests will be sent to another hotel means that there are
two or fewer no shows. If x = number of no shows is defined as a success then x = 0
implies that 5 guests must be sent to another hotel. If x = 1 then four guests must be sent
to another hotel. If x = 2 then three guests must be sent to another hotel. Thus, we find
P(x < 2) = 0.25374.

5.43
a. The characteristics of the binomial distribution are p = 0.58, q = 1-p = 0.42, and n = 30.
The event of interest is the probability that from a sample of 30, fewer than 17 workers
are confident that they have saved enough, P(x < 17) = P(x < 16). This probability can be
found in Excel 2016 with the function BINOM.DIST (16,30,0.58,true) = 0.3666.
b. The characteristics of the binomial distribution are p = 0.58, q = 1-p = 0.42, and n = 50.
The event of interest is the probability that in a random sample of 50 workers more than
40 workers have saved for retirement.

P(x > 40) = P(x > 41) = 1-P(x < 40). This probability can be found in Excel 2016 with the
function BINOM.DIST as follows: = 1-BINOM.DIST(40,50,0.58,true) = 1-0.9997 = 0.0003.

5.45

a. x w =
∑ wi xi =
30(0.50) + 10(0.10) + 50(0.35)
= 0.372 .
∑ wi 30 + 10 + 50
b. Step 1: Define the characteristics of the binomial distribution:
n = 20, p = 0.40, q = 1 – p = 1 – 0.60 = 0.60.
Step 2: Use equation 5-5 to find the expected value:
µX = E(x) = np = 20(0.60) = 12.
Given that the average obtained is 12, 4 seems to be extremely small. It would seem
that the estimate may be too high.

Copyright ©2024 Pearson Education, Inc.

84
5.47
a.
Tabulated statistics: Male-Female
Columns: Male-Female (M-F > 0) = “0” (M-F ≤ 0) = “1”
0 1 All
113 37 150
75.33 24.67 100.00
Cell Contents: Count
% of Row

b. E(x) = np = 150(0.281) = 42.15.

c.
Cumulative Distribution Function
Binomial with n = 150 and p = 0.281
P( x < 36) = 0.1521
P(x ≥ 37) = 1 – P(x ≤ 36) = 1 – 0.1521= 0.8479
d. Since there is a very large probability that the outcome we observed or something
larger would occur, it seems quite plausible that the Utah percentage agrees with that
obtained by the Bureau of Labor Statistics.

5.49
a.
There were 18 corporations that recovered their investment in analytics in 2 years or
less.
b.
Binomial with n = 35 and p = 0.63
P( x < 18 ) = 0.1087

Section 5-3 Exercises

5.51
a. You can find the desired probability using the following steps:
Step 1: Define the segment unit.
Because the mean was stated to be 3 arrivals per 15 minutes, the segment unit is
15 minutes or .25 hours.
Step 2: Determine the mean of the random variable.
The mean is λ = 3
Step 3: Determine the segment size, t and then calculate λt.
The issue in the problem asks for the probability of no customers arriving in 15
minutes which is one segment so t = 1. Thus, = λt (3)(1)
= 3
Step 4: Define the event of interest and use the Poisson table to find the desired
probability.
The event of interest is:
P(x = 0)
To use the Poisson table, go to the column headed λt = 3 . Then find the value of
x from the left hand column. The desired probability is:

Copyright ©2024 Pearson Education, Inc.

85
 P(x = 0) = 0.0498
b. To determine the desired probability, you can use the following steps.
Step 1: Define the segment unit.
Because the mean was stated to be 3 arrivals per 15 minutes, the segment unit is
15 minutes or .25 hours.
Step 2: Determine the mean of the random variable.
The mean is λ = 3
Step 3: Determine the segment size, t and then calculate λt.
The issue in the problem asks for the probability of fewer than 3 customers
arriving in 30 minutes which is two segments so t = 2.= λt (3)(2)
= 6
Step 4: Define the event of interest and use the Poisson table to find the desired
probability.
We are asked to calculate the probability that fewer than 4 customers will arrive.
Thus, the event of interest is:
P(x < 3)
To use the Poisson table, go to the column headed λt = 6 . Then find the values
of x from the left hand column. The desired probability is:
P(x < 3) = 0.1512

5.53 To determine this probability we recognize that because the sampling is without
replacement and the sample size is large relative to the size of the population, the
hypergeometric distribution applies. The following steps can be used:

Step 1: Define the population size and the combined sample size.
The population size is N = 10 and the combined sample size is n = 3
Step 2: Define the event of interest.
We are interested in the event described by getting
P ( x 2 red and =
= n − x 1 green = ) ?
Step 3: Determine the number of each category in the population.
The population contains X = 3 red and N-X = 7 green.
Step 4: Compute the desired probability using the hypergeometric distribution.
CnN−−xX * C xX C310−−2 3 * C23 C17 * C23 (7)(3) 21
P (=
x 2)= = = = = = 0.175
CnN C310 C310 120 120
Thus, the probability of selecting 2 red and 1 green from a population with 3 red and
7 green is 0.175.

5.55
a.
Step 1: Determine the population size, N, and the sample size, n. The population size, N, is
the number of manufacturing plants and is equal to 11. The sample size, n, is the number
of plants selected for a performance evaluation and is equal to 4.
Step 2: Define the event of interest. The event of interest is the probability that exactly one
plant outside the United States are included in the performance evaluation P(x = 1)
Step 3: Determine the number of successes in the population and the number of successes
in the sample. In this case the number of successes in the population is the number of

Copyright ©2024 Pearson Education, Inc.

86
 plants located outside the United States, which is 1. Therefore x = 1. The number of
successes in the sample is the number of plants outside the United States included in the
performance evaluation and is equal to 1. Therefore, x = 1.
Step 4: Compute the desired probability using the following equation:
C
N−X
*C X C *C
11− 4 4
P ( x) = n − x N x = P ( x = 1) = 4−1 11 1 = 0.4242
Cn C4
b.
Step 1: Determine the population size, N, and the sample size, n. The population size, N, is
the number of manufacturing plants and is equal to 11. The sample size, n, is the number
of plants selected for a performance evaluation and is equal to 4.
Step 2: Define the event of interest. The event of interest is the probability that exactly three
plants in the United States are included in the performance evaluation P(x = 3)
Step 3: Determine the number of successes in the population and the number of successes
in the sample. In this case the number of successes in the population is the number of
plants located in the United States, which is 7. Therefore X = 7. The number of successes in
the sample is the number of plants in the United States included in the performance
evaluation and is equal to 3. Therefore, x = 3.
Step 4: Compute the desired probability using the following equation:
C
N−X
*C X C *C
11− 7 7
P ( x) = n − x N x = P( x = 3) = 4−3 11 3 = 0.4242
Cn C4
c.
Step 1: Determine the population size, N, and the sample size, n. The population size, N, is
the number of manufacturing plants and is equal to 11. The sample size, n, is the number
of plants selected for a performance evaluation and is equal to 4.
Step 2: Define the event of interest. The event of interest is the probability that two or more
plants outside the United States are included in the performance evaluation P(x > 2)
Step 3: Determine the number of successes in the population and the number of successes
in the sample. In this case the number of successes in the population is the number of
plants located outside the United States, which is 4. Therefore X = 4. The number of
successes in the sample is the number of plants outside the United States included in the
performance evaluation and is equal to 2 or more. Therefore, x > 2.

Step 4: Compute the desired probability using the following equation:

P(x > 2) = P(x =2) + P (x = 3) + P(x = 4), where
C
N−X
*C X
P( x) = n − x N x
Cn
C *C
11− 4 4
P( x = 2) = 4− 2 11 2 = 0.3818
C4
C *C
11− 4 4
P( x = 3) = 4−3 11 3 = 0.0848
C4
C *C
11− 4 4
P( x = 4) = 4− 4 11 4 = 0.0030
C4
Therefore, the P(x > 2) = 0.4696

Copyright ©2024 Pearson Education, Inc.

87
5.57
C nN−−xX C xX C 410−−37 C 37
3(35)
a. P(x = 3) = = = 0.5 ; =
C N
n C 210 10
4

b. P(x = 5) = 0 since the sample size, n, is 4, the maximum number of successes is 4.

C 10 −7 7
4− 4 C 4 1(35)
c. P(X ≥ 4) = P(X = 4) = 0.5 + = = 0.1667 = 0.1667
C 10 210
4
d. Since P(x > 3) = 0.1667, P(x > 2) = 0.5 + 0.1667 = 0.6667 > 0.25; then x’ = 2.

5.59 If the quality standards are being satisfied, the mean defects per sheet is 3.5. Thus the
segment size is 1 sheet. However, the customer inspected 2 sheets (2 segments) so we
have
= = 7 . They discovered 10 defects in the two sheets and we are
λt (3.5)(2)
interested in the probability of ten or more defects as follows:
P ( x ≥ 10) =1 − P ( x ≤ 9)
We go to the Poisson table and the column headed λt = 7 . Then find the values of x
from the left-hand column as follows:
P ( x ≥ 10) = 1 − 0.8305 = 0.1695
There is a 0.1695 chance that 10 or more defects would be found in two sheets even
though the average is supposed to be 7 defects in two sheets. Although this is not a
high probability, it is certainly possible to see this result when the quality standards are
being satisfied. Thus, there is no cause to say that the quality does not meet the
standards.

5.61 This is a situation in which the sampling will be performed without replacement from a
finite population when the sample size is large relative to the population size. As such,
the desired probability can be computed using the hypergeometric distribution. The
event of interest is:
C xX1 1 * C xX2 2 * C xX3 3 C710 * C05 * C05 (120)(1)(1) 120
(
P x=1 7, x=
2 0, x=
3 0)
= N
= 20
= = = 0.0015
Cn C7 77,520 77,520
The probability of all seven stocks being “large caps” is 0.0015. This means that in only
15 chances in ten thousand would this happen due to chance so it is very likely that the
sampling was not done using random selection as directed by the customer.

5.63
a. Step 1: Determine the population size and the combined sample size.
The population size and sample size are
N = 20 and n = 5.
Step 2: Define the event of interest.
The technician needs to determine
P(x = 4).
Step 3: Determine the number of successes in the population and the number of successes
in the sample.

Copyright ©2024 Pearson Education, Inc.

88
 In this situation, a success is the event that the technician selects a non-defective
processor. There are 20 – 4 = 16 ( = x) successes in the population and 4 (5 – 1 =
x) in the sample.
Step 4: Compute the desired probabilities using Equation 5-9.
CnN−−xX C xX C520− 4−16C416 4(1820)
P(x = 4) = = = = 0.4696
CnN C520 15504
C nN−−xX C xX C 520−3−16 C 316
6(560)
b. P(x = 3) = = = 0.2167 =
C N
n C 1550420
5

a. The technician will have enough processors if he selects 3 or more non-defective

processors. Thus, noting that
C 520 −16 16
−5 C 5 1(4368)
P(x = 5) = = = 0.2817
C 520 15504
The probability is
P(x ≥ 3) = 0.4696 + 0.2167 + P(X = 5) = 0.6863 + 0.2817 = 0.9680

5.65
a. The desired event can occur is they all select fruit trees or pine trees or maple trees.
The probabilities of these outcomes are:
C10 • C 80 • C14 210 • 1 • 1
P(4,0,0) = 4 0
= = .0058
32
C4 35,960
C10 8 14
0 • C4 • C0 1 • 70 • 1
P(0,4,0) = = = .0019
C432
35,960
C10 8
0 • C0 • C4
14
1 • 1 • 1,001
P(0,0,4) = = = .0278
C432
35,960
The overall probability is found by summing these: .0058 + .0019 + .0278 =
.0355
C10 8 14
0 • C 3 • C1 1 • 56 • 14
b. P(0,3,1) = = = .0218
C432
35,960
C10 8 14
0 • C2 • C2 1 • 28 • 91
c. P(0,2,2) = = = .0709
C432
35,960

5.67
a. The average demand for one hour is Poisson distributed with a mean of 50. Therefore
the average demand over a two hour period is 2*50 = 100 which is also Poisson
distributed. The probability that demand will exceed 115 is equal to 1-Probability
(Demand < 115) = 1-0.9368 = 0.0632.
b. The probability of running out of spicy hot dogs when 115 are stocked is 0.0632.
Thus, the owner will have to stock more than 115. As the number stocked increases
the probability of stocking out decreases. By stocking 120 spicy hot dogs the
probability that demand will exceed supply is 0.02267, which is less than the desired

Copyright ©2024 Pearson Education, Inc.

89
 probability of a stockout of 0.025. Note that the Probability (Demand < 120) =
0.97733. The probability that demand will be greater than 120 is 1-0.97733 =
0.02267. By stocking 120 Spicy Dogs the probability of being out of hot dogs is less
than 0.025.

5.69
C xS11 C xS22 C xS33 C531C353C216 169911(23426)(120)
a. P(x1, x2, x3) = = = = 0.02759
CnN C10100 17,310,309,456,440
b. P(10,0,0) = 0.0000026
c. P(6,0,4) = 0.00008

5.71
a.
Sum of Scratches = 8
b. Step 1: Define the segment unit. Since the company’s goal is to have no more
than an average of one scratch per set of pocket billiard balls and that sixteen balls
are in a set, the segment unit is 16 balls.
Step 2: Determine the mean of the random variable. One scratch per set of balls is
the company’s goal. Therefore, the mean will be λ = 1.
Step 3: Determine the segment size t and then calculate λt. Since there are 16
balls per set, the 48 balls that were selected is the same as 3 (48/16) sets of balls.
So t = 3.
So the average number per set would be λt = 1(3) = 3.
c. Step 4: Define the event of interest and use the Poisson formula or the Poisson
tables to find the probability.
Here 8 scratches were observed. Since the 8 exceeds the expected number (λt =
1(3) = 3), Elaine would want to find P(x ≥ 8):
Cumulative Distribution Function
Poisson with mean = 3
x P( X <= x )
7 0.988095
P(X ≥ 8) = 1 – P(X ≤ 7) = 1 – 0.9881 = 0.0119.
d. It is very unlikely that as many or more than 8 scratches would occur in 48 balls if
the company’s goal had been met. Therefore, she would believe that the goal has
not been met.

Copyright ©2024 Pearson Education, Inc.

90
End of Chapter Exercises

5.73 As the sample size is increased for a given level of the probability of success, p, the
probability distribution becomes more symmetric, or bell-shaped.

5.75
a. Let Si = a success is obtained on the ith trial and Fi = a failure is obtained on the ith trial.
P(S2|S1) = ½. P(S2|F1) = 2/2 = 1. Thus, the probability of getting a success on the
second trial depends upon what occurs on the first trial. This means the trials are
dependent.
b. P(S1) = 2/3.
P(S2) = P[(S1 and S2) or (F1 and S2)] = P(S1 and S2) + P(F1 and S2) = P(S2|S1)P(S1) +
P(S2|F1)P(F1) = (1/2)(2/3) + (2/2)(1/3) = 2/3, and
P(S3) = P[(S3 and S2 and F1) or P(S3 and F2 and S1)] = P(S3 and S2 and F1) + P(S3 and
F2 and S1) = P(S3| F2 and S1)P(F2 and S1) + P(S3| S2 and F1)P(S2 and F1) = P(S3| F2 and
S1)P(F2| S1)P(S1) + P(S3| S2 and F1)P(S2| F1)P(F1) = (1/1)(1/2)(2/3) + (1/1)(2/2)(1/3) =
2/3.
Therefore, the probability of a success is the same (2/3) for all three trials. This
indicates that the probability of a success being constant does not imply that the trials
are independent.

5.77
a. This means that the managing editor should expect to see 0.80 errors per ad. While most
ads will not have an error, some will have as many as 4 errors.
X P(x) xP(x)
0 0.56 0.00
1 0.21 0.21
2 0.13 0.26
3 0.07 0.21
4 0.03 0.12
0.80
b. standard deviation = 1.0954 Variance = 1.20
x P(x) xP(x) x-E(x) [x-E(x)]2 [x-
E(x)]2P(x)
0 0.56 0.00 -0.8000 0.6400 0.3584
1 0.21 0.21 0.2000 0.0400 0.0084
2 0.13 0.26 1.2000 1.4400 0.1872
3 0.07 0.21 2.2000 4.8400 0.3388
4 0.03 0.12 3.2000 10.2400 0.3072
0.80 1.2000
These values measure the variation in the number of printing errors from ad to ad in the
newspaper.

Copyright ©2024 Pearson Education, Inc.

91
5.79 n = 9 cans; p = .50 (if in control)
P(x = 9) = P(x < 9) – P(x < 8) = 0 .0020
Thus, there is a 0.002 chance that this sample result would occur from a process that is in
control. Because this is such a small probability, we would likely conclude that the
process is not in control. The filling process tends to overfill.

5.81
C nN--xX • C Xx
Use the Hypergeometric distribution with: P(x) =
C nN
Then with N = 20; n = 4; X = 4; x = 0
C 20 -4
4-0 • C 0
4
1,820 • 1
P(x > 1) = 1 – P(x = 0). P(0) = 20
= = .3756 .
C4 4,845
1-0.3756 =0.6244.

5.83
x P(x) xP(x)
0 0.2 0
1 0.2 0.2
2 0.2 0.4
3 0.2 0.6
4 0.2 0.8
2.0
a. The expected number of defectives is equal to 2. This means that on the average of
several shipments Stafford Productions should expect the number of defectives to be
2. It does not mean that each shipment will have exactly 2 defects.
b.
X P(x) xP(x) x-E(x) [x-E(x)]2 [x-E(x)]2P(x)
0 0.2 0 -2 4 0.8
1 0.2 0.2 -1 1 0.2
2 0.2 0.4 0 0 0
3 0.2 0.6 1 1 0.2
4 0.2 0.8 2 4 0.8
2 2
The standard deviation is equal to 1.4142. This is the square root of the average
squared deviation from the mean. It is a measure of average deviation from the mean
number of defective products based on the probability distribution.
c. This probability distribution is called a Uniform Distribution since the probability of
each outcome is equally likely (0.2). Often times if there is no estimate or past
history to base the probability on people will use the uniform distribution.

Copyright ©2024 Pearson Education, Inc.

92
5.85
x P(x) xP(x) x-E(x) [x-E(x)]2 [x-E(x)]2P(x)
-1000 0.1 -100 (1,750) 3,062,500 306,250
0 0.1 0 (750) 562,500 56,250
500 0.3 150 (250) 62,500 18,750
1000 0.3 300 250 62,500 18,750
2000 0.2 400 1,250 1,562,500 312,500
750 712,500

y P(y) yP(y) y-E(y) [y-E(y)]2 [y-E(y)]2P(y)

-1000 0.2 -200 (1,100) 1,210,000 242,000
0 0.4 0 (100) 10,000 4,000
500 0.3 150 400 160,000 48,000
1000 0.05 50 900 810,000 40,500
2000 0.05 100 1,900 3,610,000 180,500
100 515,000
a. E(x) = 750; E(y) = 100
b. StDev(x) = 844.0972; StDev(y) = 717.635
c. CV(x) = 844.0972/750 = 1.1255
CV(y) = 717.635/100 = 7.1764
d. Student answers will vary but they should comment on the fact that you cannot
compare standard deviations of datasets with different means. They should be
standardized by calculating the coefficient of variation. In this case it shows that the
2nd stock is actually more risky than the 1st stock.

5.87
a. Let x = the number of non-smoking rooms given to the tour guide.
20−12 12
C10 −6 C 6 70(924)
P(x = 6) = = = 0.3501
20 184756
C10
b. P(x ≤ 5) = 1 – P(x ≥ 6) = 1 – P(x = 6) – P(x = 7) – P(x = 8) – P(x= 9) –
20−12 12 20−12 12 20−12 12 20−12 12
C10 −7 C 7 C10 −8 C8 C10 −9 C 9 C10 −10 C10
P(x = 10) = 1- 0.3501 - - - - =1–
20 20 20 20
C10 C10 C10 C10
0.3501 – 0.2400 – 0.075 – 0.0095 – 0.0004 = 0.3250.

5.89
a. Exactly 15 carry-on = 0.01178
b. Fewer than 5 who check bags = 0.42067
c. More than 10 successes = 0.9999

Copyright ©2024 Pearson Education, Inc.

93
5.91
a. Probability machine is stopped = 0.00758
b. Probability machine is not stopped when defect rate is 1.1% = 0.98224
c. Expected Value = n*p. If p = .008 then need to sample 125 parts to find one defective
on average.

5.93
a. Probability of exactly 8 purchases = 0.08879
b. Probability of more than 15 purchases = 0.0926

5.95
a.
Sum of Defectives
Sum of Defectives = 36
So then proportion of defectives is 36/[20(90)] = 0.02.
b. E(X) = µ = np = 20(0.02) = 0.4; σ = npq = 20(0.02)(1 − 0.02) = 0.6261.
c. µ ± σ = 0.4 ± 3(0.6261) = (-1.4783, 2.2783). Since it is impossible to have a negative
number here the limits are (0, 2.2783)
d. P(0 ≤ X ≤ 2.2783) = P(0 ≤ X ≤ 2). So the probability that the number of defectives is
beyond the control limits equals 1 – P(X ≤ 2).
Cumulative Distribution Function
Binomial with n = 20 and p = 0.02
x P( X <= x )
2 0.992931
So 1 – P(X ≤ 2) = 1 – 0.9929 = 0.0071.

Copyright ©2024 Pearson Education, Inc.

94