Sie sind auf Seite 1von 24

# Chapter 6

## Continuous Probability Distributions

Learning Objectives
1.

Understand the difference between how probabilities are computed for discrete and continuous
random variables.

2.

Know how to compute probability values for a continuous uniform probability distribution and be
able to compute the expected value and variance for such a distribution.

3.

Be able to compute probabilities using a normal probability distribution. Understand the role of the
standard normal distribution in this process.

4.

5.

## Be able to compute probabilities using an exponential probability distribution.

6.

Understand the relationship between the Poisson and exponential probability distributions.

Solutions:

6-1

Chapter 6

1.

a.
f (x)
3
2
1
x
.50

2.

1.0

1.5

2.0

b.

P(x = 1.25) = 0. The probability of any single point is zero since the area under the curve above
any single point is zero.

c.

d.

a.
f (x)
.15
.10
.05
x
0

3.

10

b.

c.

d.

E ( x) =

e.

Var( x) =

20

10 + 20
= 15
2
(20 10) 2
= 8.33
12

a.

6-2

30

40

f (x)
3 / 20
1 / 10
1 / 20
x
110

120

130

Minutes

4.

b.

c.

d.

E ( x) =

120 + 140
= 130 minutes
2

a.
f (x)
1.5
1.0
.5
x
0

5.

b.

c.

P(x .30)

d.

a.

## Length of Interval = 310.6 - 284.7 = 25.9

= 1 (.30) = .30

1
for 284.7 x 310.6

f ( x) = 25.9
0 elsewhere

b.

## Note: 1/25.9 = .0386

P(x < 290) = .0386(290 - 284.7) = .2046

c.

d.
e.

## P(290 x 305) = .0386(305 - 290) = .5790

P(x 290) = .0386(310.6 - 290) = .7952

6-3

140

Chapter 6

6.

a.

b.

c.

## P ( x < 11.98) + P ( x > 12.02)

1 44 2 4 43 1 44 2 4 43
.005(8) = .04 .64 = .08(8)
Therefore, the probability is .04 + .64 = .68

7.

a.

## P(10,000 x < 12,000) = 2000 (1 / 5000) = .40

The probability your competitor will bid lower than you, and you get the bid, is .40.

b.

c.

d.

## Yes, the bid that maximizes expected profit is \$13,000.

The probability of getting the property with a bid of \$13,000 is
P(10,000 x < 13,000) = 3000 (1 / 5000) = .60.
The probability of not getting the property with a bid of \$13,000 is .40.
The profit you will make if you get the property with a bid of \$13,000 is \$3000 = \$16,000 13,000. So your expected profit with a bid of \$13,000 is
EP (\$13,000) = .6 (\$3000) + .4 (0) = \$1800.
If you bid \$15,000 the probability of getting the bid is 1, but the profit if you do get the bid is only
\$1000 = \$16,000 - 15,000. So your expected profit with a bid of \$15,000 is
EP (\$15,000) = 1 (\$1000) + 0 (0) = \$1,000.

8.

= 10

70

9.

80

90

100

a.

=5

6-4
35

40

45

50

55

60

65

## Continuous Probability Distributions

b.

.6826 since 45 and 55 are within plus or minus 1 standard deviation from the mean of 50.

c.

.9544 since 40 and 60 are within plus or minus 2 standard deviations from the mean of 50.

10.

-3
a.

.3413

b.

.4332

c.

.4772

d.

.4938

11. a.

.3413

b.

.4332

c.

.4772

d.

.4938

e.

.4987

12. a.

.2967

b.

.4418

c.

d.
e.

## .0910 + .5000 = .5910

.3849 + .5000 = .8849

f.

13. a.

b.

c.

14. a.

-2

-1

+1

+2

+3

## These probability values are read directly

from the table of areas for the standard
normal probability distribution. See
Table 1 in Appendix B.

Using the table of areas for the standard normal probability distribution, the area of .4750
corresponds to z = 1.96.

6-5

Chapter 6

b.

## Using the table, the area of .2291 corresponds to z = .61.

c.

Look in the table for an area of .5000 - .1314 = .3686. This provides z = 1.12.

d.

Look in the table for an area of .6700 - .5000 = .1700. This provides z = .44.

15. a.

Look in the table for an area of .5000 - .2119 = .2881. Since the value we are seeking is below the
mean, the z value must be negative. Thus, for an area of .2881, z = -.80.

b.

c.

d.

## Look in the table for an area of .4948; z = 2.56.

e.

Look in the table for an area of .1915. Since the value we are seeking is below the mean, the z
value must be negative. Thus, z = -.50.

16. a.

Look in the table for an area of .5000 - .0100 = .4900. The area value in the table closest to .4900
provides the value z = 2.33.

b.

Look in the table for an area of .5000 - .0250 = .4750. This corresponds to z = 1.96.

c.

Look in the table for an area of .5000 - .0500 = .4500. Since .4500 is exactly halfway between .
4495 (z = 1.64) and .4505 (z = 1.65), we select z = 1.645. However, z = 1.64 or z = 1.65 are

d.

Look in the table for an area of .5000 - .1000 = .4000. The area value in the table closest to .4000
provides the value z = 1.28.

17.

= 527, = 160
a.

z=

700 527
= 1.08
160

b.

z=

100 527
= 2.67
160

c.

## At 700, z = 1.08 from part (a)

At 450, z =

450 527
= .48
160

P(450 < x < 700) = P(-.48 < z < 1.08) = .8599 - .3156 = .5443
d.

z=

300 527
= 1.42
160

6-6

= 30 and = 8.2

18.
a.

At x = 40, z =

40 30
= 1.22
8.2

## P(z 1.22) =.5000 + .3888 = .8888

P(x 40) = 1 - .8888 = .1112
b.

At x = 20, z =

20 30
= 1.22
8.2

## P(z > -1.22) =.5000 + .3888 = .8888

P(x 20) = 1 - .8888 = .1112
c.

A z-value of 1.28 cuts off an area of approximately 10% in the upper tail.
x = 30 + 8.2(1.28) = 40.50
A stock price of \$40.50 or higher will put a company in the top 10%
We have = 156.76 and = 138.01

19.
a.

Z =

416 156.76
1.88
138.01

P(x > 5.0) = P(z > 1.88) = 1 - P(z < 1.88) = 1 - .9699 = .0301
The rainfall exceeds 416 mm in 3.01% of the Februarys.
b.

Z =

70 156.76
.63
138.01

P(x < 3.0) = P(z < -.63) = P(z > .63) = 1 - P(z < .63) = 1 - .7357 = .2643
The rainfall is less than 70 mm in 26.43% of the Februarys.
c.

z = 1.28 cuts off approximately .10 in the upper tail of a normal distribution.
x = 156.76 + 1.28(138.01) = 333.413
If it rains 333.413 mm or more, February will be classified as extremely wet.

20.
a.

At x = 10,

z=

10 15.3
= 1.35
3.94

## P(z < -1.35) = P( z > 1.35) = .5000 - .4115 = .0885

So, P(x < 10) = .0885

6-7

Chapter 6

b.

At x = 20,

z=

20 15.3
=1.19
3.94

## P(z > 1.19) = .5000 - .3830 = .1170

So, P(x > 20) = .1170
11.7% of people logged on over 20 hours.
c.

A z-value of .84 cuts off an area of approximately .20 in the upper tail.
x = 15.3 + .84 (3.94) = 18.61
A person must spend 18.61 or more hours logged on to be classified a heavy user.

21.

From the normal probability tables, a z-value of 2.05 cuts off an area of approximately .02 in the
upper tail of the distribution.
x = + z = 100 + 2.05(15) = 130.75
A score of 131 or better should qualify a person for membership in Mensa.

6-8

## Continuous Probability Distributions

Use = 441.84 and = 90

22.
a.

At 400
z=

400 441.84
.46
90

At 500
z=

500 441.84
.65
90

## P(0 z < .65) = .2422

P(-.46 z < 0) = .1772
P(400 z 500) = .1772 + .2422 = .4194
The probability a worker earns between \$400 and \$500 is .4194.
b.

Must find the z-value that cuts off an area of .20 in the upper tail. Using the normal tables, we find
z = .84 cuts off approximately .20 in the upper tail.
So, x = + z = 441.84 + .84(90) = 517.44
Weekly earnings of \$517.44 or above will put a production worker in the top 20%.

c.

At 250, z =

250 441.84
2.13
90

## P(x 250) = P(z -2.13) = .5000 - .4834 = .0166

The probability a randomly selected production worker earns less than \$250 per week is .0166.
23. a.
b.

z=

60 80
= 2 Area to left is .5000 - .4772 = .0228
10

At x = 60
z=

60 80
= 2
10

z=

75 80
= .5
10

At x = 75

c.

z=

90 80
=1
10

## Therefore 15.87% of students will not complete on time.

(60) (.1587) = 9.522
We would expect 9.522 students to be unable to complete the exam in time.

6-9

Chapter 6

24. a.

x =

s=

xi
= 902.75
n

( xi x ) 2
= 114.185
n 1

b.

At 800
z=

800 902.75
.90
114.185

## P(x 800) = P(z -.90) = 1 - P(z .90) = 1 - .8159 = .1841

The probability trading volume will be less than 800 million shares is .1841
c.

At 1000
z=

1000 902.75
.85
114.185

## P(x 1000) = P(z .85) = 1 - P(z .85) = 1 - .8023 = .1977

The probability trading volume will exceed 1 billion shares is .1977
d.

## A z-value of 1.645 cuts off an area of .05 in the upper tail

x = + z = 902.75 + 1.645(114.185) = 1,090.584
They should issue a press release any time share volume exceeds 1,091 million.

= 442.54, = 65

25.
a.

z=

400 442.54
= .65
65

b.

z=

300 442.54
= 2.19
65

c.

## At x = 400, z = -.65 from part (a)

At x = 500, z =

500 442.54
= .88
65

P(400 < x < 500) = P(-.65 < z < .88) = .8106 - .2578 = .5528
26. a.

= np = 100(.20) = 20

6 - 10

## Continuous Probability Distributions

2 = np (1 - p) = 100(.20) (.80) = 16
= 16 = 4
b.

c.

P (23.5 x 24.5)
z=

24.5 20
= +1.13
4

Area = .3708

z=

23.5 20
= +.88
4

Area = .3106

d.

P (17.5 x 22.5)
z=

17.5 20
= .63
4

Area = .2357

z=

22.5 20
= +.63
4

Area = .2357

e.

P (x 15.5)
z=

15.5 20
= 1.13
4

Area = .3708

## P (x 15.5) = .5000 - .3708 = .1292

27. a.

= np = 200(.60) = 120
2 = np (1 - p) = 200(.60) (.40) = 48
= 48 = 6.93

b.

c.

P (99.5 x 110.5)
z=

99.5 120
= 2.96
6.93

Area = .4985

z=

110 120
= 1.37
6.93

Area = .4147

## P (99.5 x 110.5) = .4985 - .4147 = .0838

6 - 11

Chapter 6

d.

P ( x 129.5)
z=

129.5 120
= +1.37 Area = .4147
6.93

e.

## Simplifies computation. By direct computation of binomial probabilities we would have to

compute
P (x 130) = f (130) + f (131) + f (132) + f (133) + ...

28. a.

In answering this part, we assume it is not known how many Democrats and Republicans are in the
group.

= np = 250(.47) = 117.5
2 = np(1-p) = 250(.47)(.53) = 62.275
= 62.275 = 7.89
Half the group is 125 people. We want to find P(x 124.5).
At x = 124.5, z =

124.5 117.5
= .89
7.89

## P(z .89) = .5000 - .3133 = .1867

So, P(x 124.5) = .1867
We estimate a probability of .1867 that at least half the group is in favor of the proposal.
b.

## For Republicans: np = 150(.64) = 96

For Democrats: np = 100(.29) = 29
Expected number in favor = 96 + 29 = 125

c.

It's a toss up. We expect just as many in favor of the proposal as opposed.

= 4.7410 = 2.18
c.

At x = 6.5,

z=

6.5 4.99
= .69
2.18

6 - 12

At x = 5.5,

z=

5.5 4.99
= .23
2.18

## P(z .23) = .5000 + .0910 = .5910

P(5.5 x 6.5) = .7549 - .5910 = .1639
Our estimate of the probability is .1639.
d.

At x = 3.5,

z=

3.5 4.99
= .68
2.18

## P(x -.68) = .5000 + .2518 = .7518

So, P(x 3.5) = .7518
Our estimate of the probability that at least 4 are unemployed is .7518.
30. a.

= np = (800)(0.41) = 328
= np(1 p) = (800)(0.41)(0.59) = 13.9111
I would expect 328 to agree that Microsoft is a monopoly.

b.

At x = 300.5
z=

300.5 328
= 1.98
13.9111

## P(x 300.5) = 0.5000 - 0.4761 = 0.0239

The probability that 300 or fewer agree that Microsoft is a monopoly is 0.0239.

c.

## Use = n(1 - p) = 800(0.59) = 472

= 13.9111 as in part a.
Find P(x > 450.5)
At x = 450.5
z=

450.5 472
= 1.55
13.9111

6 - 13

Chapter 6

## P(x > 450.5) = 0.5000 + 0.4394 = 0.9394

The probability that there are over 450 that do not agree Microsoft is a monopoly.
31. a.

= np = 120(.75) = 90
= np(1 p) = (120)(.75)(.25) = 4.74
The probability at least half the rooms are occupied is the normal probability: P(x 59.5).
At x = 59.5
z=

59.5 90
= 6.43
4.74

b.

At x = 99.5
99.5 90
= 2.00
4.74

z=

c.

At x = 80.5
z=

80.5 90
= 2.00
4.74

32. a.

b.

c.
d.

## P(x 6) = 1 - P(x 6) = 1 - .5276 = .4724

P(4 x 6) = P(x 6) - P(x 4) = .5276 - .3935 = .1341

33. a.

P ( x x0 ) = 1 e x0 / 3

b.

c.

d.

e.

6 - 14

34. a.
b.
c.

## P(x < 10) = 1 - e-10/20 = .3935

P(x > 30) = 1 - P(x 30) = 1 - (1 - e-30/20 ) = e-30/20 = .2231
P(10 x 30) = P(x 30) - P(x 10)
= (1 - e-30/20 ) - (1 - e-10/20 ) = e-10/20 - e-30/20
= .6065 - .2231 = .3834

35. a.
f(x)
.09
.08
.07
.06
.05
.04
.03
.02
.01
x
6

12

18

b.

c.

d.

## P(x 30) = 1 - P(x < 30)

24

= 1 - (1 - e-30/12)
= .0821
36. a.
b.
c.

37. a.

50 hours
P(x 25) = 1 - e-25/50 = 1 - .6065 = .3935
P(x 100) = 1 - (1 - e-100/50)
= .1353
P(x < 2) = 1 - e-2/2.78 = .5130

b.

c.

## P(x > 2.78) = 1 - P(x 2.78) = 1 - (1 - e-2.78/2.78 ) = e-1 = .3679

This may seem surprising since the mean is 2.78 minutes. But, for the exponential distribution, the
probability of a value greater than the mean is significantly less than the probability of a value less
than the mean.

6 - 15

Chapter 6

38. a.

If the average number of transactions per year follows the Poisson distribution, the time between
transactions follows the exponential distribution. So,

1
of a year
30

and

1
1
=
= 30
1/ 30

b.

1
1

## P x > = 1 P x = 1 (1 e 30 /12 ) = e 30 /12 = .0821

12
12

The probability of no transaction during January is the same as the probability of no transaction
during any month: .0821

c.

## Since 1/2 month is 1/24 of a year, we compute,

1

30 / 24
P x
= 1 .2865 = .7135
= 1 e
24

39. a.

1
for 200 x 225

f ( x) = 25
0 elsewhere

b.

c.

d.

## E (x) = (200 + 225)/2 = 212,500

If she waits, her expected sale price will be \$2,500 higher than if she sells it back to her company
now. However, there is a 0.40 probability that she will get less. Its a close call. But, the expected
value approach to decision making would suggest she should wait.

6 - 16

## Continuous Probability Distributions

40. a.

For a normal distribution, the mean and the median are equal.

= 63,000
b.

Find the z-score that cuts off 10% in the lower tail.
z-score = -1.28
Solving for x,
1.28 = x 63,000
15,000
x = 63,000 - 1.28 (15000) = 43,800
The lower 10% of mortgage debt is \$43,800 or less.

c.

At x = 80,000
z=

= 1.13
15, 000

d.

## Find the z-score that cuts off 5% in the upper tail.

z-score = 1.645. Solve for x.
1.645 =

x 63, 000
15, 000

## x = 63,000 + 1.645 (15,000) = 87,675

The upper 5% of mortgage debt is in excess of \$87,675.
41. a.

= 1 - P(9.85 x 10.15)

P(defect)

## = 1 - P(-1 z 1) = 1 - .6826 = .3174

Expected number of defects = 1000(.3174) = 317.4
b.

## P(defect) = 1 - P(9.85 x 10.15)

= 1 - P(-3 z 3) = 1 - .9974 = .0026
Expected number of defects = 1000(.0026) = 2.6

c.

Reducing the process standard deviation causes a substantial reduction in the number of defects.

= 80,734

42.
a.

## z = -1.645 cuts off .05 in the lower tail

So,

6 - 17

Chapter 6

1.645 =

=
c.

75,422 80,734

75,422 80,734
= 3,229
1.645

At 80,400

z=

80,400 80,734
= .10
3,229

z=

78,410 80,734
= .72
3,229

At 78,410

P (80,400 < x < 78,410) = P (-.72 < z < -.10) = .2642 - .0398 = .2244
c.

## z = 1.88 cuts off approximately .03 in the upper tail

x = 80,734 + 1.88 (3,229) = 86,804.52
The households with the highest 3% of expenditures spent more than NT\$86,804.

= 10,000

43.
a.

= 1500

At x = 12,000
12, 000 10, 000
= 1.33 Area to left is .9082
1500
P(x > 12,000) = 1.0000 - .9082 = .0918
z=

b.

At .95
z = 1.645 =

x 10, 000
1500

## Therefore, x = 10,000 + 1.645(1500) = 12,468.

95%

10,000
12,468 tubes should be produced.

6 - 18

0.05

12,468

44. a.

At x = 200
z=

200 150
= 2 Area = .4772
25

b.

45. a.

## Expected Profit = Expected Revenue - Expected Cost

= 200 - 150 = \$50
Find P(80,000 x 150,000)
At x = 150,000
z=

= 0.78
30, 000

z=

= 1.56
30, 000

At x = 80,000

## P(x 80,000) = .5000 - .4406 = 0.0594

P(80,000 x 150,000) = 0.7823 - 0.0594 = 0.7229
b.

At x = 50,000
z=

= 2.56
30, 000

c.

## Find the z-score cutting off 95% in the left tail.

z-score = 1.645. Solve for x.
1.645 =

x 126, 681
30, 000

## x = 126,681 + 1.645 (30,000)

= 176,031
The probability is 0.95 that the number of lost jobs will not exceed 176,031.

46. a.

At 400,

6 - 19

Chapter 6

z=

400 450
= .500
100
Area to left is .3085

At 500,
z=

500 450
= +.500
100
Area to left is .6915

## P(400 x 500) = .6915 - .3085 = .3830

38.3% will score between 400 and 500.
b.

At 630,
z=

630 450
= 1.80
100

## 96.41% do worse and 3.59% do better .

c.

At 480,
z=

480 450
= .30
100
Area to left is .6179

47. a.

At 75,000
z=

## 75, 000 67, 000

1.14
7, 000

P(x > 75,000) = P(z > 1.14) = 1 - P(z 1.14) = 1 - .8729 = .1271
The probability of a woman receiving a salary in excess of \$75,000 is .1271
b.

At 75,000
z=

## 75, 000 65,500

1.36
7, 000

P(x > 75,000) = P(z > 1.36) = 1 - P(z 1.36) = 1 - .9131 = .0869
The probability of a man receiving a salary in excess of \$75,000 is .0869
c.

At x = 50,000
z=

## 50, 000 67, 000

2.43
7, 000

P(x < 50,000) = P(z < -2.43) = 1 - P(z < 2.43) = 1 - .9925 = .0075
The probability of a woman receiving a salary below \$50,000 is very small: .0075
d.

The answer to this is the male copywriter salary that cuts off an area of .01 in the upper tail of the
distribution for male copywriters.
Use z = 2.33

6 - 20

## x = 65,500 + 2.33(7,000) = 81,810

A woman who makes \$81,810 or more will earn more than 99% of her male counterparts.

= .6

48.

At 2%
z = -2.05
z=

x = 18

2.05 =

18
.6

0.02

=19.23

18

49.

## Use normal approximation to binomial.

a.

= np = 50 (.75) = 37.5

= np (1 p ) = 50(.75)(.25) = 3.06
At x = 42.5
z=

x 42.5 37.5
=
= 1.63

3.06

## P(0 z 1.63) = .4484

Probability of an A grade = .5000 - .4484 = .0516 or 5.16% will obtain an A grade.
b.

At x = 34.5
z=

34.5 37.5
= .98
3.06

At x = 39.5
z=

39.5 37.5
= .65
3.06

## P(-.98 z .65) = .3365 + .2422 = .5787

or 57.87% will obtain a C grade.

6 - 21

Chapter 6

c.

At x = 29.5
29.5 37.5
= 2.61
3.06

z=

## P(z -2.61) = .5000 + .4955 = .9955

or 99.55%of the students who have done their homework and attended lectures will pass the
examination.
d.

= np = 50 (.25) = 12.5

## (We use p = .25 for a guess.)

= np (1 p ) = 50(.25)(.75) = 3.06
At x = 29.5
z=

29.5 12.5
= 5.55
3.06

P(z 5.55) 0
Thus, essentially no one who simply guesses will pass the examination.
50. a.

= np = (240)(0.49) = 117.6
Expected number of wins is 117.6
Expected number of

## Expected payoff = 117.6(50) - 122.4(50) = (-4.8)(50) = -240.

The player should expect to lose \$240.
b.

To lose \$1000, the player must lose 20 more hands than he wins. With 240 hands in 4 hours, the
player must win 110 or less in order to lose \$1000. Use normal approximation to binomial.

= np = (240)(0.49) = 117.6
= 240(.49)(.51) = 7.7444
Find P(x 110.5)
At x = 110.5
z=

110.5 117.6
= .92
7.7444

## P(x 110.5) = 0.5000 - 0.3212 = 0.1788

The probability he will lose \$1000 or more is 0.1788.
c.

Find P(x 120.5)
At x = 120.5

6 - 22

z=

120.5 117.6
= .37
7.7444

## P(x 120.5) = 0.5000 - 0.1443 = 0.3557

The probability that the player will win is 0.3557. The odds are clearly in the houses favor.
d.

To lose \$1500, the player must lose 30 hands more than he wins. This means he wins 105 or fewer
hands.
Find P(x 105.5)
At x = 105.5
z=

105.5 117.6
= 1.56
7.7444

## P(x 105.5) = 0.5000 - 0.4406 = 0.0594

The probability the player will go broke is 0.0594.
51. a.

b.

## P(x 45) = 1 - e-45/36 = 1 - .2865 = .7135

Therefore P(15 x 45) = .7135 - .3408 = .3727

c.

## P(x 60) = 1 - P(x < 60)

= 1 - (1 - e-60/36) = .1889

52. a.

b.

f(x) = 7e-7x

c.

## P(x > 1) = 1 - P(x < 1) = 1 - [1 - e-7(1)] = e-7 = .0009

d.

12 seconds is .2 minutes
P(x > .2) = 1 - P(x < .2) = 1- [1- e-7(.2)] = e-1.4 = .2466

53. a.
b.

1
e x / 24.7 .0405e .0405 x
24.7
P(x < 30) = 1 - e-.0405(30) = 1 - .2967 = .7033
P(x < 10) = 1 - e-.0405(10) = 1 - .6670 = .3330
P(10 < x < 30) = .7033 - .3330 = .3703

c.

## From part (b), P(x < 30) = .7033

P(x > 30) = P(x 30) = 1 - P(x < 30) = 1 - .7033 = .2967

6 - 23

Chapter 6

54. a.
b.

1
= 0.5 therefore = 2 minutes = mean time between telephone calls

## Note: 30 seconds = .5 minutes

P(x .5) = 1 - e-.5/2 = 1 - .7788 = .2212

c.

d.

6 - 24