Problem Sheet-2 Solutions

Binomial and Poisson

Statistics for Business and Economics 5.34 to 5.43 and 5.46 to 5.51 Solutions:

6
34. a. f (2) =   (.23)2 (.77)4 = .2789
 2

b. P(at least 2) = 1 - f(0) - f(1)

 6  6
= 1 −   (.23)0 (.77)6 −   (.23)1 (.77)5
 0 1

= 1 - .2084 - .3735 = .4181

10 
c. f (0) =   (.23)0 (.77)10 = .0733
0

n
35. a. f ( x) =   ( p) x (1 − p)n − x
 x

10!
f (3) = (.30)3 (1 − .30)10−3
3!(10 − 3)!

10(9)(8)
f (3) = (.30)3 (1 − .30)7 = .2668
3(2)(1)

b. P(x  3) = 1 - f (0) - f (1) - f (2)

10!
f (0) = (.30)0 (1 − .30)10 = .0282
0!(10)!

10!
f (1) = (.30)1 (1 − .30)9 = .1211
1!(9)!

10!
f (2) = (.30)2 (1 − .30)8 = .2335
2!(8)!

P(x  3) = 1 - .0282 - .1211 - .2335 = .6172

36. a. Probability of a defective part being produced must be .03 for each part selected; parts must be
selected independently.

b. Let: D = defective
G = not defective
Chapter 5

Experimental Number
1st part 2nd part Outcome Defective
D (D, D) 2

D G
(D, G) 1 .

G
D (G, D) 1

G
(G, G) 0

c. 2 outcomes result in exactly one defect.

d. P(no defects) = (.97) (.97) = .9409

P (1 defect) = 2 (.03) (.97) = .0582

P (2 defects) = (.03) (.03) = .0009

37. a. Yes. Since the employees are selected randomly, p is the same from trial to trial and the trials are
independent. The two outcomes per trial are loyal and not loyal.

Binomial n = 10 and p = .25

10!
f ( x) = (.25) x (1 − .25)10 − x
x !(10 − x)!

10!
b. f (0) = (.25)0 (1 − .25)10 −0 = .0563
0!(10 − 0)!

10!
c. f (4) = (.25)4 (1 − .25)10 − 4 = .1460
4!(10 − 4)!

d. Probability (x > 2) = 1 - f (0) - f (1)

From part (b), f(0) = .0563

10!
f (1) = (.25)1 (1 − .25)10 −1 = .1877
1!(10 − 1)!

Probability (x > 2) = 1 - f (0) - f (1) = 1 - (.0563 + .1877 ) = .7560

38. a. .90

b. P(at least 1) = f (1) + f (2)

 Discrete Probability Distributions

2!
f (1) = (.9)1 (.1)1
1! 1!

= 2(.9)(.1) = .18

2!
f (2) = (.9)1 (.1) 0
2! 0!

= 1(.81)(1) = .81

 P(at least 1) = .18 + .81 = .99

Alternatively

P(at least 1) = 1 – f (0)

2!
f (0) = (.9)0 (.1)2 = .01
0! 2!

Therefore, P(at least 1) = 1 - .01 = .99

c. P(at least 1) = 1 - f (0)

3!
f (0) = (.9)0 (.1)3 = .001
0! 3!

Therefore, P(at least 1) = 1 - .001 = .999

d. Yes; P(at least 1) becomes very close to 1 with multiple systems and the inability to detect an attack
would be catastrophic.

39. a. Using the 20 golfers in the Hazeltine PGA Championship, the probability that a PGA professional
golfer uses a Titleist brand golf ball is p = 14/20 = .6

For the sample of 15 PGA Tour players, use a binomial distribution with n = 15 and p = .6.

15!
f (10) = (.6)10 (1 − .6)15−10 =.1859
10!5!

Or, using the binomial tables, f (10) = .1859

b. P(x > 10) = f (11) + f (12) + f (13) + f (14) + f (15)

Using the binomial tables, we have

.1268 + .0634 + .0219 + .0047 + .0005 = .2173

c. E(x) = np = 15(.6) = 9
d. Var(x) = 2 = np(1 - p) = 15(.6)(1 - .6) = 3.6

 = 3.6 = 1.8974
Chapter 5

n
40. a. f ( x) =   ( p) x (1 − p)n − x
 x

15!
f (4) = (.28) 4 (1 − .28)15− 4
4!(15 − 4)!

15(14)(13)(12)
f (4) = (.28)4 (1 − .28)11 = .2262
4(3)(2)(1)

b. P(x  3) = 1 - f (0) - f (1) - f (2)

15!
f (0) = (.28)0 (1 − .28)15 = .0072
0!(15)!

15!
f (1) = (.28)1 (1 − .28)14 = .0423
1!(14)!

15!
f (2) = (.28)2 (1 − .28)13 = .1150
2!(13)!

P(x  3) = 1 - .0072 - .0423 - .1150 = .8355

41. a. f (0) + f (1) + f (2) = .0115 + .0576 + .1369 = .2060

b. f (4) = .2182

c. 1 - [ f (0) + f (1) + f (2) + f (3) ] = 1 - .2060 - .2054 = .5886

d.  = n p = 20 (.20) = 4

42. a. p = ¼ = .25

n
f ( x) =   ( p) x (1 − p)n − x
 x

 20 
f (4) =   (.25)4 (1 − .25)20− 4
4

20! 20(19)(18)(17)
f (4) = (.25) 4 (.75)16 = f (4) = (.25) 4 (.75)16 = .1897
4!(20 − 4)! 4(3)(2)(1)

b. P(x  2) = 1 – f(0) – f(1)

Using the binomial tables f(0) = .0032 and f(1) = .0211

P(x  2) = 1 – .0032 - .0211 = .9757

c. Using the binomial tables f(12) = .0008

 Discrete Probability Distributions

And, with f (13) = .0002, f (14) = .0000, and so on, the probability of finding that 12 or more
investors have exchange-traded funds in their portfolio is so small that it is highly unlikely that p =
.25. In such a case, we would doubt the accuracy of the results and conclude that p must be greater
than .25.

d.  = n p = 20 (.25) = 5

43. E(x) = n p = 35(.23) = 8.05 (8 automobiles)

Var(x) = n p (1 - p) = 35(.23)(1-.23) = 6.2

 = 6.2 = 2.49

3x e −3
44. a. f ( x) =
x!

32 e −3 9(.0498)
b. f (2) = = = .2241
2! 2

31 e −3
c. f (1) = = 3(.0498) = .1494
1!

d. P(x  2) = 1 - f (0) - f (1) = 1 - .0498 - .1494 = .8008

2 x e −2
45. a. f ( x) =
x!

b.  = 6 for 3 time periods

6 x e −6
c. f ( x) =
x!

22 e −2 4(.1353)
d. f (2) = = = .2706
2! 2

6 6 e −6
e. f (6) = = .1606
6!

45 e −4
f. f (5) = = .1563
5!

46. a.  = 48 (5/60) = 4
3 -4
f (3) = 4 e = (64) (.0183) = .1952
3! 6

b.  = 48 (15 / 60) = 12
10 -12
f (10) = 12 e = .1048
10 !
Chapter 5

c.  = 48 (5 / 60) = 4 I expect 4 callers to be waiting after 5 minutes.

0 -4
f (0) = 4 e = .0183
0!

The probability none will be waiting after 5 minutes is .0183.

d.  = 48 (3 / 60) = 2.4
0 -2.4
f (0) = 2.4 e = .0907
0!

The probability of no interruptions in 3 minutes is .0907.

47. a. 30 per hour

b.  = 1 (5/2) = 5/2

(5 / 2)3 e − (5 / 2)
f (3) = = .2138
3!

(5 / 2)0 e − (5 / 2)
c. f (0) = = e − (5 / 2) = .0821
0!

7 0 e −7
48. a. f (0) = = e −7 = .0009
0!

b. probability = 1 - [f(0) + f(1)]

71 e −7
f (1) = = 7e −7 = .0064
1!

probability = 1 - [.0009 + .0064] = .9927

c.  = 3.5

3.50 e −3.5
f (0) = = e −3.5 = .0302
0!

probability = 1 - f(0) = 1 - .0302 = .9698

d. probability = 1 - [f(0) + f(1) + f(2) + f(3) + f(4)]

= 1 - [.0009 + .0064 + .0223 + .0521 + .0912] = .8271

Note: The Poisson tables were used to compute the Poisson probabilities f(0), f(1), f(2), f(3) and f(4)
in part (d).
100 e −10
49. a. f (0) = = e −10 = .000045
0!

b. f (0) + f (1) + f (2) + f (3)

 Discrete Probability Distributions

f (0) = .000045 (part a)

101 e −10
f (1) = = .00045
1!

Similarly, f (2) = .002267, f (3) = .007567

and f (0) + f (1) + f (2) + f (3) = .010329

c. 2.5 arrivals / 15 sec. period Use  = 2.5

2.50 e −2.5
f (0) = = .0821
0!

d. 1 - f (0) = 1 - .0821 = .9179

50. Poisson distribution applies

a.  = 1.25 per month

1.250 e −1.25
b. f (0) = = .2865
0!
1.251 e −1.25
c. f (1) = = .3581
1!

d. P(More than 1) = 1 - f (0) - f (1) = 1 - 0.2865 - 0.3581 = .3554

 x e− 
51. a. f ( x) =
x!

30 e −3
f (0) = = e −3 = .0498
0!

b. P(x  2) = 1 - f (0) - f (1)

31 e −3
f (1) = = .1494
1!

P(x  2) = 1 - .0498 - .1494 = .8008

c. µ = 3 per year

µ = 3/2 = 1.5 per 6 months

1.50 e −1.5
d. f (0) = = .2231
0!

Other question solutions:

1) i. 0.5551
 Chapter 5

ii. At least 4

2) 0.0170

3)
i. A=1/5
ii. P(X > 10) = exp(-2), P(X<5) = 1 – exp(-1), P(5<X<10) = exp(-1) – exp (-2)

4) 0.8369

5) 0.1043

6)
a. 0.7373
b. 0.6778
c. 0.7373
d. 0.6778
e. 0.5

7) n=730, p=1/365
a. Using Binomial, P(X=2) = 0.27104, P(X>=2) = 0.59437
b. Using Normal, np=2, npq = 1.994520548, P(X=2) = 0.276690, P(X>=2) = 0.638345
c. Using Poisson, np=2, P(X=2) = 0.27067, P(X>=2) = 0.59399

8) (a) 20C5 (.08)5 (.92)15 = .0145 (b) 20C0 (.08)0(.92)20 = .1887 (c) 20C20 (.08)20(.92)0 =
.0000000000000000000001

9) .0867

10) .00044

11) .0432

12) Probability that it will work (0 defective components) 100C0 (.005)0 (.995)100 = .606
Probability that it will not work perfectly is 1 - .606 = .394 or 39.40%

13) (i) 0; (ii) 0.6321, (iii) 0.1954

14) (i) λ = 0.3, 1 - P(X=0) = 0.2592; (ii) λ=1, P(X=0)=0.3679

15) λ=3, P(X>=1) = 1 – P(X=0) = 0.9502