2010 Assignment Answers Ch 1-4

2010 Assignment Answers SG 15e
CHAPTER 1
WHAT IS STATISTICS?
Part I Part II Part III Part IV
1. Quantitative 6. Discrete 11. Interval 16. Ratio 21. D

2. Qualitative 7. Discrete 12. Nominal 17. Ordinal 22. C
3. Quantitative 8. Continuous 13. Nominal 18. Nominal 23. D
4. Qualitative 9. Continuous 14. Ordinal 19. Interval 24. B
5. Quantitative 10. Discrete 15. Ratio 20. Ratio 25. C
CHAPTER 2
DESCRIBING DATA: FREQUENCY TABLES, FREQUENCY

DISTRIBUTIONS, AND GRAPHIC PRESENTATION
Part I
1. B 2. A 3. B 4. B 5. C
6. C 7. A 8. C 9. A 10. D
Part II
11. Pie Chart
1
12. a, b, &c. Frequency, relative frequency, and cumulative frequency distributions:
Relative Cumulative
Class Limits Frequency Frequency Frequency
12,000 up to 16,000 3 0.088 3
16,000 up to 20,000 6 0.176 9
20,000 up to 24,000 11 0.324 20
24,000 up to 28,000 6 0.176 26
28,000 up to 32,000 7 0.206 33
32,000 up to 36,000 1 0.029 34
Total 34 1.000
d. Frequency histogram:
e. Frequency polygon:
2
f. Cumulative frequency distribution:
3
CHAPTER 3
DESCRIBING DATA: NUMERICAL MEASURES

Part I
1. C 2. C 3. D 4. A 5. D 6. B 7. A
8. B 9. A 10. B 11. D 12. B 13. B 14. A
15. C
Part II
16. a. Range: 12 – 4 = 8
X 6  12  7  12  8  4  5 54
b. Mean: X    7.71
n 7 7
c Median is 7
d. Mode is 12
e. Positively skewed, mean is greater than median.
17. Average weight = 8 pounds found by:

(10 x 7.4) + (12 x 8.2) + (6 x 8.7) = 224.6/ 28 = 8.02
18. 98.74% found by 8 (1.00)(0.98)(0.985)(0.98)(1.00)(0.985)(0.97)  1.00   8 0.90385  0.9874
596,085
19. Percent increase: GM  8  1  8 1.9544  1  (1.0874  1)  0.0874  8.74%
305,000
20. a. Range: 1370 – 887 = 483
b.Mean deviation:
,  Σ XX .
X  ,. MD    .
 n 
c. Standard deviation:
X XX ( X  X ) ( X  X )2
1136 -38.42 38.42 1476.10
1090 -84.42 84.42 7126.74
1273 98.58 98.58 9718.02
 X  X 
2
1104 -70.42 70.42 4958.98 206,151
2
1180 5.58 5.58 31.14 s    18, 740.99
n 1 12  1
1271 96.58 96.58 9327.70
1211 36.58 36.58 1338.10
s  , .  .
887 -287.42 287.42 82610.26
1008 -166.42 166.42 27695.62
1300 125.58 125.58 15770.34
1370 195.58 195.58 38251.54
1263 88.58 88.58 7846.42
14093 1294.16 206151
4
X  X 33
.  6.5 X  X 9.7  6.5
21. a. k   16
. k   16
.
s 2 s 2
   
Applying Chebyshev's theorem: ChebTh   
         .   .  %
k  . 
b. Plus or minus 2 standard deviations or about 95%.
22.
 f M 1070
a. Find the mean using formula [3-12] : X    26.75
n 40
b. Find the standard deviaition using formula [13-13]:
 f M X
2
4777.5
s   122.5  11.068
n 1 40  1
Hours f M f  M  X   M  X 2 f M X
2
M
0 up to 10 3 5 15 -21.75 473.0625 1419.188
10 up to 20 7 15 105 -11.75 138.0625 966.4375
20 up to 30 15 25 375 -1.75 3.0625 45.9375
30 up to 40 10 35 350 8.25 68.0625 680.625
40 up to 50 5 45 225 18.25 333.0625 1665.313
Total 40 1070 4777.5
5
CHAPTER 4
DESCRIBING DATA:
DISPLAYING AND EXPLORING DATA
Part I
1. D 2. D 3. D 4. B 5. D
6. C 7. D 8. B 9. D 10. C
Part II
11. Dot Plot
12. a,b&c: Quartiles and median:

P 25
L p  ( n  1)  (11  1) 3
To locate the first quartile, let P = 25 and 100 100
Then locate the 3rd observation in the array which is 23. Thus Q1 = 2.
P 75
To locate the third quartile, let P = 75 and L p  ( n  1)  (11  1) 9
100 100
Then locate the 9th observation in the array, which is 91. Thus Q3 =18.
To locate the median, let P = 50 and
P 50
L p  ( n  1)  (11  1) 6
100 100
Then locate the 6th observation in the array, which is 10. Thus Q2 = the median =10.
d. Box Plot:
6
Minimum value = 15, Q3 = 23, Q2 = 35 Q3 = 91, Maximum value = 102
Min Q1 Med Q3 Max
+ + + + + + + + +
0 10 20 30 40 50 60 70 80 90 100
e. We calculated the mean and standard deviation as follows:
 X  X 
2
12,814
X 594 s 
2
  1, 281.40
X   54 n 1 11  1
n 11
s  1281.40  35.79  35.8
3( X  Median) 3(54  35) 57
Compute Pearson’s coefficient of skewness: sk     1.592
s 35.8 35.8
Pearson’s coefficient of skewness of 1.592 indicates moderate Positive skewness. Also note that
positive skewness is indicated since mean (54) is larger than median (35).
13. a. Scatter diagram
7
b. There is a slight decline in miles per gallon as load capacity increases.
144
14. a. Percent of members having high blood pressure =  0.32  32%
449
20
b. Percent of under age 25 having low blood pressure =  0.227  23%
88
93
c. Percent medium blood pressure and over 50 =  0.453  45%
205
Less than half of those over age 50 have medium blood pressure.
CHAPTER 5
A SURVEY OF PROBABILITY CONCEPTS

Part I
1. D 2. A 3. B 4. D 5. A
6. C 7. B 8. B 9. D 10. A
Part II
11. 38%, found by 0.30 + 0.20  0.12
12. a. 0.78, found by 0.92 × 0.92 × 0.92

b. 0.22, found by (1  0.78)
10 9
13. Likelihood both increased = 0.2368, found by:   0.2368
20 19
14. Put ratings into an array: 0.46 0.59 0.64 0.72 0.76 0.81
2 1 3 1 3 1 0
a.  b.  c. X  0.66,  d. 0
6 3 6 2 6 2 6
8
15. Possible arrangements: (4)(6)(10) = 240

n! ! !
16. Different lists: n Cr   C    
r! n  r  ! !     ! !( ! )
27
17. a. P(~W) = =0.27 or 27%
100
38
b. P(A) =  0.38 or 38%
100
30
c. P(A and W) =  0.3 or 30%
100
38 27 8
d. P(A or ~W) =    0.38 + 0.27  0.08=0.57
100 100 100
0.30
e. P(A given W) =  0.41
0.73
18. C = the event that the mower is a Colt

T = the event that the mower is a Turfmaster
R = the event that the mower is a Ranger.
W =the event that the mower is brought in for a repair covered by the warranty.
This problem can be solved by computing the joint probabilities P  R and W  , P  T and W  ,
P  C and W  : P  W and R   P  W R   P  R   . .  .
P  W and T   P  W T   P  T   
. .  .
P  W and C   P  W C   P  C   . 
.  .
The given probabilities and the calculated joint probabilities are entered into the contingency table as
shown:
P(R) P(T) P(C) Total
P(W) 0.0250 0.0525 0.0375 0.115
P(~W)
Total 0.5000 0.3500 0.1500 1.000
The remaining joint probabilities can then be determined. For example,

P(~W and R) = P(R) – P(W and R) = 0.5000 - 0.0250 = 0.4750. The completed contingency table is:
P(R) P(T) P(C) Total

P(W) 0.0250 0.0525 0.0375 0.115
P(~W) 0.4750 0.2975 0.1125 0.885
Total 0.5000 0.3500 0.1500 1.000
P  C and W  .
a. P C W     .
PW  
.
9
.
b. P  T W    .
.
.
c. P  R W    .
.
CHAPTER 6
DISCRETE PROBABILITY DISTRIBUTIONS

Part 1:
1. B 2. D 3. B 4. B 5. D
6. A 7. B 8. A 9. D 10. C
Part II:
11. a. Mean:   [ xP ( x )]  2.4
Number of Connections
per Two Minutes Probability
X P(X) xP(x)  x  μ  x  μ 2
P(X)
0 0.1 0 0 – 2.4 (5.76)(0.1) = 0.576
1 0.2 0.2 1 – 2.4 (1.96)(0.2) = 0.392
2 0.1 0.2 2 – 2.4 (0.16)(0.1) = 0.016
3 0.4 1.2 3 – 2.4 (0.36)(0.4) = 0.144
4 0.2 0.8 4  2.4 (2.56)(0.2) = 0.512
 1.0 2.4  = 1.64
b. Standard deviation:   [( x   ) 2 P ( x )  1.64  128

.
n!
P( x)  ( ) x (1   ) n  x
x !(n  x )!
12. a. Exactly five:
8!
 0.75  0.25   0.208
5 3
P (5) 
5! 8  5  !
!
b. All eight: P(  )   .    .    .
!     !
c. At least seven: P(7) + P(8) = 0.267 + 0.100 = 0.367,
10
!
P(  )   .   .    .
!     !
d. At least one: [1  P (0)] = [1  0.000015] = 0.999985,
!
P(  )   .    .   .
!     !
e. Expected return:  = np = 8(0.75)= 6
!
13. a. Ten survive: P(  )   .   .    .
!    !
b. At least ten: P(at least 10) = P(10) + P(11) + P(12)
= 0.283+ 0.206 + 0.069 = 0.558
!
P(  )   .   .    .
!   !
!
P(  )   .   .    .
!    !
 x e 
P x 
x!
14. Exactly 12:
1512 e15
P  12    0.083
12!
μ x e μ
P x 
x!
15. a. No new accounts:
 e 
P     e   
.
!
b. At least one: P(x = 1) = [1 - P(0)] = [ 1 - 0.1353 ] = 0.8647
 6!  4! 
  
 6 C2   4 C 2  2!4!  2!2!  90 3
16. Two of each: P  2sm, 2 fl       0.42857
 10 C4   10!  210 7
 
 4!6! 
11
 9 C3   11 C2 
17. a. Three Cannon and two Schwinn: P  3C ,2S    0.298
 20 C5 
P  C  
  C   C   .
b. Five Cannon:
  C 
 9 C0   11 C5 
c. Five Schwinn: P  5S    0.0298
 20 C5 
d. At least one Cannon: P(at least 1C) = [ 1 - P(0m) ] = ( 1 - 0.0298 ) = 0.9702
12
CHAPTER 7
CONTINUOUS PROBABILITY DISTRIBUTIONS

Part I
1. A 2. D 3. D 4. C 5. C
6. B 7. B 8. A 9. D 10. B
Part II
11.
a. Determine the height using Formula [7 – 3]
1 1 1
P( x) =    0.05
(b  a) (55  35) 20
Draw the uniform distribution.
P(X)
0.05
X
35 55
b. The mean represents the typical test taking time. To determine the mean use Formula [7–1]:
a  b 35  55 90
=    45
2 2 2
c. To determine the standard deviation use Formula [7–2].
(b  a ) 2 (55  35) 2 (20) 2

=    33.33  5.77
12 12 12
d. The probability a particular student will take the test in less than 45 minutes is found by finding
the area of the rectangle with a height of 0.05 and a base of (45 – 35).
P(35  test time  45)  Height  Base  0.05  (45  35)  0.05  10  0.5
13
e. The probability a particular student will take between 45 and 50 minutes to take the test is found
by finding the area of the rectangle with a height of 0.05 and a base of (50 – 45).
P(45  test time  50)  Height  Base  0.05  (50  45)  0.05  5  0.25
X   120  100
12. a. 28.81%, found by z    0.8 from Appendix B.1: 0.2881
 25
b. 78.81%, found by (0.50 + 0.2881)
X   60  100
c. 5.48%, found by (0.50  0.4452), z    160
. , Appendix B.1: 0.4452
 25
150  100
d. 18.91%, found by (0.4772  0.2881), Appendix B.1: 0.4772 for z   2.00
25
e. 73.33%, found by (0.2881 + 0.4452) from parts a and c
f. 121 minutes, found by (0.50  0.2) = 0.30 which corresponds to z = 0.84. Solve for X using
X  100
z = 0.84 
25
13. 501.5 minutes or about 8 2 hours, found by (0.50  0.04) = 0.46,
X  540
z = 1.75 (negative because z is left of the mean) solve for X using z = 175
. 
22
14. a. Mean    0.05   120   6 Standard deviation   0.05  120   0.95   5.7  2.387
b. P(7 or more defective) = 0.4168, found by (0.50  0.0832)
6.5  6
z  0.21 , Appendix B.1: 0.0832
2.387
c. P(7 defective) = 0.1525, found by (0.4168  0.2643)
7.5  6
z  0.63 , Appendix B.1: 0.2357, then (0.50  0.2357) = 0.2643
2.387
14
8.5  6
d. P(more than 8) = 0.1469, found by (0.50  0.3531), z   1.05 , Appendix B.1: 0.3531
2.387
15. a. Mean: μ   .       Standard deviation σ   .      .   .
17.5  21
b.P(18 or more) = 0.8869, found by ( 0.50 + 0.3869), z   121
. ,Appendix B.1: 0.3869
2.8983
29.5  21
c. P(30 or more) = 0.0017, found by (0.50 - 0.4983), , z   2.93 , Appendix B.1: 0.4983
2.8983
.  21
115
d. P(<12) = 0.001, found by (0.5 - 0.4990), z   3.28 , Appendix B.1: 0.4990
2.8983
30.5  21
e. P(12 to 30) = 0.998, found by (0.4990 + 0.4990), z   3.28 , Appendix B.1: 0.4990
2.8983
and solution from part d.
16. a. Mean: μ   .       Standard deviation σ   .      .   . .
16.5  10
b. P(16 or more) = 0.0107, found by (0.50  0.4893), z   2.30 , Appendix B.1: 0.4893
2.8284
c. P(Exactly 14) = 0.0516, found by (0.4441  0.3925 ),
14.5  10 .  10
135
z  159
. , Appendix B.1: 0.4441 z  124
. , Appendix B.1: 0.3925
2.8284 2.8284
d. P(7 to 9) = 0.3211, found by (0.3925  0.0714)
6.5  10 9.5  10
z  124
. , Appendix B.1: 0.3925 z  018
. , Appendix B.1: 0.0714
2.8284 2.8284
e. P(7 to 15) = 0.8663, found by (0.3925 + 0.4738)
. 
from d and z   . , Appendix B.1: 0.4738
.
15
CHAPTER 8
SAMPLING METHODS AND THE CENTRAL LIMIT THEOREM

Part I
1. D 2. A 3. B 4. A 5. A
6. C 7. B 8. C 9. B 10. D
Part II
11. a. The sample is agency numbers 00, 04, 14, 15, 19, found by: Start with row two and
column two. The number is 90935. Use the first two numbers starting with 90. The column is
repeated below with the selected numbers in bold and italics.
90, 78, 97, 00, 19, 04, 14, 57, 81, 26, 25, 67, 22, 19 skip, 72, 90, 76, 36, 87, 97, 47, 25,
15
We select rental agency number 00, 04, 14, 15, 19.
b. The sample is agency numbers 02, 03, 04, 06, 15, found by: Starting at the bottom left
corner of the table, the number is 11084. Use the far right two digits starting with 84. The column
is repeated below with the selected numbers in bold and italics.
84, 43, 48, 86, 15, 91, 06, 96, 50, 35, 24, 34, 43, 38, 69, 68, 83, 99, 61, 02, 84, 69, 78, 26,
55, 90, 03, 44, 82, 37, 65, 43, 50, 74, 64, 92, 71, 81, 94, 73, 04
We select rental agency number 02, 03, 04, 06, 15.
c. Every third rental agency starting with 02 is: 02, 05, 08, 11, 14, 17.
d. The sample is agency numbers 02(LN), 06(L), 11(LNT), and 12(LT), found by: In order
to select a sample of four rental agencies so that one of each type of agency is included, we had to
skip a selection when we had already selected an agency for that category. The different agencies
are L, LN, LT and LNT. Starting at the top of column three, the number is 75997. Use the left
two digits starting with 75. The column is repeated below with the selected numbers in bold and
italics and underline.
75, 31, 06(L), 37, 93, 22, 92, 50, 91, 53, 28, 89, 93, 90, 12(LT), 37, 43, 92, 01(L) Skip,
33, 11(LNT), 40, 43, 37, 06(L) Skip, 40, 90, 38, 51, 28, 21, 89, 95, 39, 76, 95, 36, 25, 49, 47, 46,
29, 24, 93, 52, 77, 62, 04(LNT) Skip, 46, 78, We chose to move two columns to the right and
went up from there to 95, 59, 02(LN),
We select rental agency number 02, 06, 11 and 12.
e. The sample is agency numbers 03LT, 04LNT, 11LNT, 16LNT, 18LNT, found by: In
order to select a sample of five rental agencies that rent trucks, we will need to skip agencies that
only rent local (L) and those agencies that rent only local (L) and National (N). Starting at the
bottom of the third column, the number is 78957. Use the far right two digits starting with 57.
The column is repeated below with the selected numbers in bold italics and underlined:
57, 98, 28, 92, 03(LT), 68, 86, 11(LNT), 90, 84, 41, 55, 00 Skip, 99, 45, 54, 58, 28, 26,
27, 98, 35, 90, 48, 59, 35, 38, 70, 98, 38, 04(LNT), 72, 25, 39, 22, 95, 26, 04(LNT) Skip, 78, 72,
09(LN) Skip, 85, 73, 60, 97, 51, 97, 35, 84, 97, We chose to move two columns to the left and
went down from there to 59, 16(LNT), 66, 73, 32, 24, 24, 03(LT) Skip, 11(LNT) 38, 84, 91, 35,
03(LT) Skip, 24, 77, 33, 29, 11(LNT) Skip, 33, 18(LNT). We select rental agency number
03LT, 04LNT, 11LNT, 16LNT, and 18LNT,
16
17
f. The sample is agency numbers 01LN, 09LN, 17 LN, found by: In order to select a sample
of two rental agencies that rent locally and nationally, but do not rent trucks, we will need to skip
all agencies that rent trucks (T). Starting at the bottom of the fourth column of the table, the
number is 77353. Use the second and third set of digits starting with 73. The column is repeated
below with the selected numbers in bold, italics, and underlined.
73, 45, 69, 66, 09(LN), 94, 01(LN), 73, 37, 17(LN). We select agencies 01LN, 09LN, 17 LN.
g. Using the table of random numbers to select a sample of five rental agencies will result in
numerous samples depending on the starting point in the table.
5! 5  4
12. a. 10, found by 5 C2    10
2!3! 2
b.
Sample Total Mean Number
Number Bundle Pencils of Pencils
1 1,2 16 8.0
2 1,3 20 10.0
3 1,4 21 10.5
4 1,5 22 11.0
5 2,3 16 8.0
6 2,4 17 8.5
7 2,5 18 9.0
8 3,4 21 10.5
9 3,5 22 11.0
10 4,5 23 11.5
98.0
10  6  10  11  12 49
c. Population mean = 9.8 found by   9.8
5 5
98
Sample mean = 9.8 found by  9.8
10
The population mean is exactly equal to the mean of the samples
13. a. 0.005, found by: In Equation [8  2] the numerator X    2.005  2.01  0.005 is
the sampling error.
b. 0.005, found by: In Equation [8  2] the denominator  / n  0.025 / 25  0.005 is the
standard error of the distribution of sample means.
18
c. 0.8413, found by: We need to determine the likelihood that we could select a sample of
25 bottles from a normal population with a mean of 2.01 liters and a population standard
deviation of 0.025 ounces and find the sample mean to be 2.005 liters. We use formula [8-2] to
find the value of z.
X   2.005  2.01 0.005
z    1.00
 / n 0.025 / 25 0.005
The z-value expresses the sampling error in standard units. We need to compute the
probability of a z- value greater than  1.00. In Appendix B.1 we locate the probability
corresponding to a z-value of  1.00. It is 0.3413. Thus the probability of a z-value greater than
 1.00 is 0.8413, found by (0.5000 + 0.3413 ) = 0.8413.
14. 0.9948, found by: Using formula [8-2] to find the value of z.
X   1.994  2.01 0.016
z    2.56
 / n 0.025 / 16 0.00625
The z-value expresses the sampling error in standard units. We need to compute the probability of
a z- value greater than  2.56. In Appendix B.1 we locate the probability corresponding to a z-
value of  2.56. It is 0.4948. Thus the probability of a z-value greater than  2.56 is 0.9948, found
by (0.5000 + 0.4948 ) = 0.9948.
X   16.03  16.025 0.005

15. a. 0.4052, found by: z    0.24
/ n 0.125 / 36 0.02083
The z-value expresses the sampling error in standard units. We need to compute the probability
of a z- value greater than 0.24. In Appendix B.1 we locate the probability corresponding to a z-
value of 0.24. It is 0.0948. Thus the probability of a z-value greater than 0.24 is 0.4052, found
by (0.5000  0.0948 ) = 0.4052.
X   15.995  16.025 0.03

b. 0.0749, found by: z    1.44
/ n 0.125 / 36 0.02083
The z-value expresses the sampling error in standard units. We need to compute the probability
of a z- value less than 1.44. In Appendix B.1 we locate the probability corresponding to a z-
value of 1.44. It is 0.4251. Thus the probability of a z-value less than 1.44 is 0.0749, found
by (0.5000  0.4251 ) = 0.0749.
c. 0.5199, found (0.4251+0.0948 = 0.5199) or [1.000  (0.0749+0.04052)]
19
CHAPTER 9
ESTIMATION AND CONFIDENCE INTERVALS
Part I
1. C 2. A 3. D 4. B 5. C
6. A 7. B 8. A 9. D 10. D
Part II
11. The t distribution is used because σ is unknown. We use formula [9-2] to develop a 98%
confidence interval for the mean. The value of t is 2.492 (d.f. = n-1 = 24). 0.9505 up to 1.2895
 . 
ounces, found by .  .    
.  
. .
  
  
12. Use formula [9-1] since σ is known. 187.79 to 196.21, found by   .      . .
  
Yes, it appears that the mean weight has gone down since 198 is not in the 96% confidence
interval.
     
13. Use the FPC since n/N > .05. 188.13 to 195.87, found by   .      .
    
.
14. The t distribution is used because the population standard deviation is unknown.
We use Formula [9-2] to develop the confidence interval. Where: X = 2.25, s = 0.5, n = 8, and t is
2.365 at (8  1) = 7 degrees of freedom. To find the value of t we use Appendix B.2. We
substitute these values in Formula [9-2].
s 0.5
X t  2.25  2.365  2.25  0.42
n 8
The end points of the interval are: 2.25  0.42 = 1.83 and 2.25 + 0.42 = 2.67. The mean life of a
drill bit is between 1.83 hours and 2.67 hours. The claim by the manufacturer that the population
mean is 2.5 hours is not unreasonable since it is included in the 95 percent confidence interval for
the population mean.
x 192
15. 0.7574 to 0.8426, found by p   0.80
n 240
0.800  1  0.800 
0.800  1.65  0.80  0.0426  0.7574 to 0.8426.
240
20
x 244
16. 0.741 to 0.859, found by p   0.8.
n 305
0.8  0.2
0.8  2.575  0.8  0.059
305

 .   
17. 62 days, found by n 
  

 
. , 
18. 193, found by n 
  

 . 
19. 1068, found by n  .   .   
 . 

 . 
20. 849 people, found by n  .   .   
 . 
21
CHAPTER 10
ONE-SAMPLE TESTS OF HYPOTHESIS
Part I
1. D 2. B 3. D 4. A 5. C
6. B 7. B 8. D 9. C 10. C
Part II
H 0 :  = 90 H  : μ  , H 0 :   100 H  : μ  .
11. a b. c. d.
H 1 :   90 H : μ  , H1:   100 H : μ  .
12. a. I. Reject claim that mean pulse is 90 when it is 90.

II. Accept claim that mean pulse is 90 when it is not 90.
b. I. Reject claim that mean salary is greater than or equal to $262,500 when it is greater than
or equal to $262,500.
II. Accept claim that the mean salary is greater than or equal to $262,500 when it is not
greater than or equal to $262,500.
c. I. Reject claim that the mean IQ is less than or equal to 100 when it is less than or equal to
100.
II. Accept claim that the mean IQ is less than or equal to 100 when it is not less than or
equal to 100.
d. I. Reject claim that the mean number of years to complete an undergraduate degree in
business is less than or equal to 4.0 years when it is less than or equal to 4.0 years.
II. Accept claim that the mean number of years to complete an undergraduate degree in
business is less than or equal to 4.0 years when it is more than 4.0 years.
13. a. H 0 :   40 H1:   40
b. Critical value is 1.65, found by (0.50  0.05) = 0.45, If z <1.65, reject H0.
39  40
c. z  1.25
8 / 100
d. p-value = P(z < 1.25) = (0.5000  0.3944) = 0.1056 The p-value of 0.1056  0.05, do not
reject H0
e. H0 is not rejected. We do not reject the claim that it takes 40 hours to learn the statistics
program.
H 0 :   20
14. a.
H1:   20
b. Critical value is 1.65, Reject H0 if z > 1.65
22
20.8  20
c. z  137
.
3.7 / 40
d. H0 is not rejected.
e. A claim cannot be made that the mean time to side a house is more than 20 hours.
15. a. H 0 :   16 H1 :   16
b. The level of significance is 0.05.
c. The test statistic in this situation is the t distribution.
X   14.5  16 1.5
t=    3.873
s / n 1.5 / 15 0.38730
d. Critical value of t is found in Appendix B.2 for (15  1) = 14 degrees of freedom. A one-
tailed test at the 0.05 significance level. It is 1.761, since the rejection region is in the left tail.
e. Because 3.87 is to the left 1.761, the null hypothesis is rejected. The fee and fine
system has reduced the cleanup and redecorating time.
16. a. H 0 :   96 H1 :   96
b. The level of significance is 0.05.
c. & d. Use the table below to compute the mean and standard deviation
23
X X X  X X
2
X
 X  1188  99
108 9 81 n 12
 X X

2
96 3 9 4068
84  15 225 s   19.23
n 1 11
84  15 225
120 21 441
96 3 9
108 9 81
132 33 1089
72  27 729
120 21 441
72  27 729
96 3 9
1188 0 4068 Column Totals
e. The test statistic in this situation is the t distribution.
X  99  96 3
t=    0.54
s / n 19.23 / 12 5.551
f. Critical value of t is found in Appendix B.2 for (12  1) = 11 degrees of freedom. We use a
two-tailed test at the 0.05 significance level. The critical value is 2.201. Reject the null
hypothesis if the computed value of t is to the left of  2.201, or to the right of 2.201.
g. Because 0.54 is not in either rejection region, the null hypothesis is not rejected. The average
amount consumed at Wallace College is the same as the typical college student.
H  : μ  .
17. a.
H : μ  .
b. Critical value is 1.96, reject H0 if z > 1.96

 .
 .
c. z    .
 .    .  .

d. Reject H0 if the z-value calculated from the sample data exceeds 1.96.
24
e. H0 can not be rejected. There is not enough evidence to conclude that the proportion of
individuals who wait for more than 90 minutes at St. Eligius’s emergency room is greater than
0.20.
CHAPTER 11
TWO-SAMPLE TESTS OF HYPOTHESIS

Part I
1. A 2. B 3. C 4. B 5. C
6. B 7. A 8. B 9. D 10. A
Part II
 
H 0 : i   g z  .
11. a.
H1 :  i   g
b. Reject H0 if z < 2.58 or z > 2.58 c.        
 
d. p-value = 2(0.5000  0.3078) = 0.3844
e. H0 is not rejected. There is no difference in the mean amount of increase.
12. a. H 0 :  p   np H1:  p   np b. Reject H0 if t > 1.708
82,000  78,000
    ,        ,   t  1.733
c. s p   , , 1 1
35,530,000   

 15 12 
d. p -value between 0.025 and 0.05
e. H0 is rejected. Accountants at partnership level do earn larger salaries.
H 0 : 1  2
13. a.
H1 : 1  2

           
  .
df    .
         , round down to 56. t =  2.003.
b.     .
 
   
c. Reject H0 if t is < -2.003 or t > +2.003
25
X  X     
t    .
s s   .
d.
   
 
n n  
e. Reject H0, since 5.004 > 2.003, there is enough evidence to conclude that there is a mean
difference in starting salaries of men versus women chemical engineers.
H 0 : 1   2
14. a. b. Reject H0 if z < -1.65
H1 :  1   2
15  20
c. c   0.2059
100  70
 

  
.  .
z   .
 
.    
.   .    . 

 
.   
.   .   

. 
   
d. p-value = (0.5000  0.2995) = 0.2005, H0 is not rejected
e. There is not enough evidence, at α = 0.05, to conclude that the proportion of cancelled flights for
SkyBlue in Charlotte, NC is less than the proportion of cancelled flights for SouthEast in
Columbia, SC.
26
15. a. H 0:  d  0 H1:  d  0 b. Reject H0 if t >3.143
Pilot Before After d ( d - d) (d - d)2

1 255 210 45 9 81
2 230 225 5 –31 961
3 290 215 75 39 1521
4 242 215 27 –9 81
5 300 240 60 24 576
6 250 235 15 –21 441
7 215 190 25 –11 121
252 3782
36 252 3782
c. t  3.794 d  36 sd   25.1064
251064
. / 7 7 7 1
d. p-value is between 0.005 and 0.0005
e. H0 is rejected. The diet is effective in lowering cholesterol levels.
27
CHAPTER 12
ANALYSIS OF VARIANCE
Part I
1. A 2. C 3. B 4. D 5. C
6. A 7. A 8. A 9. C 10. A
Part II
11. a. H 0 : 12   22 H1: 12   22 b. Reject H0 if F > 2.59
2
125
.
c. F   7.716
0.452
d. H0 is rejected. There is more variation in the shipments by Brown Truck.
12. a. H 0 : 12   22 H1: 12   22
b. Reject H0 if F > 2.03, degrees of freedom in numerator = 20,
degrees of freedom in denominator = 24
7.352
c. F   163
.
5.752
d. H0 is not rejected. There is no difference in the variation in his golf scores when the
temperature is below 65 degree or above 65 degrees.
13. a. H 0 :  1   2   3 H1: Treatment means are not equal.

b. H0 is rejected if F is greater than 3.81.
c. To compute F we need to compute the grand mean, the mean for each group, and the
various deviations and sums.
28
 all the X values 34.25  29.54  31.09 94.88

XG     6.33
n 555 15
Providence County Mercy
X X  XG ( X  X G )2 X X  X G ( X  X G )2 X X  X G ( X  X G )2 X

5.58 -0.75 0.56 4.70 -1.63 2.64 4.50 -1.83 3.33
5.98 -0.35 0.12 6.30 -0.03 0.00 7.60 1.28 1.63
7.54 1.22 1.49 5.54 -0.79 0.62 5.80 -0.53 0.28
6.07 -0.26 0.07 7.00 0.68 0.46 7.60 1.28 1.63
9.08 2.76 7.59 6.00 -0.33 0.11 5.59 -0.74 0.54
Sum 34.25 29.54 31.09 94.88
Sum 9.82 3.82 7.40 21.04 SStotal
n 5 5 5 15
SS total    X  X G    9.82  3.82  7.40   21.04
2
 X 34.25  X 29.54  X 31.09

X   6.85 X   5.91 X   6.22
n 5 n 5 n 5
Providence County Mercy

X XX (X  X ) 2 X XX (X  X ) 2 X XX ( X  X ) 2

5.58 -1.27 1.61 4.70 -1.21 1.46 4.50 -1.72 2.95
5.98 -0.87 0.76 6.30 0.39 0.15 7.60 1.38 1.91
7.54 0.69 0.48 5.54 -0.37 0.14 5.80 -0.42 0.17
6.07 -0.78 0.61 7.00 1.09 1.19 7.60 1.38 1.91
9.08 2.23 4.98 6.00 0.09 0.01 5.59 -0.63 0.39

Sum 34.25 29.54 31.09 94.88
Sum 8.45 2.95 7.34 18.74 SStotal
n 5 5 5 15
SSE   ( X  X c ) 2 SST  SS total  SSE 2.30

1.15
 (8.45  2.95  7.34)  21.04  18.74 F 2   0.74
18.74 1.56
 18.74  2.30 12
d. H0 is rejected since F is greater than 3.81. The mean response time is not the same for the three
companies.
H0:  A   B   C
14. a.
H1: not all means are equal
b. H0 is rejected if F is greater than 6.93. c. F = 0.74
d. H0 cannot be rejected, F is not greater than 6.93. The mean charge for the surgery does
not differ among the three hospitals.
29
One-Way Analysis of Variance

Analysis of Variance
Source DF SS MS F p
Factor 2 16.93 8.47 5.64 0.019
Error 12 18.00 1.50
Total 14 34.93
Individual 95% CIs For Mean
Based on Pooled StDev
Level N Mean StDev ----------+---------+---------+------
Brand A 5 4.000 1.225 (-------*-------)
Brand B 5 2.800 1.304 (-------*-------)
Brand C 5 5.400 1.140 (-------*-------)
Pooled StDev = 1.225

MTB >.
T he Minitab output indicates that the means do not differ between brand A and brand B and
between brand A and brand C, but do differ between brand B and brand C.
15. a. The interaction plot for the delivery time data is shown below:
30
The interaction plot indicates that the line segments are reasonably parallel. There does not
appear to be an interaction between brand and order size.
b.
Analysis of Variance for Y
Source DF SS MS F P
Brand 2 208.000 104.000 14.51 0.001
Size 1 98.000 98.000 13.67 0.003
Brand*Size 2 28.000 14.000 1.95 0.184
Error 12 86.000 7.167
Total 17 420.000
The ANOVA table indicates that there is not a significant interaction between brand and
order size (p-value = 0.184 > α = 0.01). The effect of brand appears to be significant (p-
value =0.001 < α = 0.01). The effect of order size also appears to be significant (p-value
= 0.003 < α = 0.01).
31
CHAPTER 13
CORRELATION AND LINEAR REGRESSION
Part I
1. C 2. D 3. D 4. A 5. B
6. A 7. D 8. C 9. C 10. D
Part II
H0:  0 0.45 15  2
11. a. b. Reject H0 if t > 1.771 c. t  1.817
H1:   0 1   0.45 
2
d. H0 is rejected. The number of crimes and the number of police have a positive
association.
12. a. Scatter diagram.

Speed and Fuel Consumption
35
30
25
20
MPG
15
10
40 45 50 55 60 65 70
Speed
b. The following table is used to compute the coefficient of correlation:

A B C D E F G
MPG Speed
2 2
Y (Y  Y ) (Y  Y ) X ( X  X ) ( X  X ) ( X  X )(Y  Y )
22 -5 25.00 44 -11 121 55
26 -1 1.00 51 -4 16 4
21 -6 36.00 48 -7 49 42
28 1 1.00 60 5 25 5
33 6 36.00 66 11 121 66
32 5 25.00 61 6 36 30
N 6 6
Total 162 124.00 330 368 202.00
32
Y
Y  162  27 X
X 330
  55
Step 1 Compute the means:
n 6 n 6
Step 2. Compute the standard deviations using the sums in Column C and F:
(Y  Y )2 124 ( X  X ) 2 368
sy    4.98 sx    8.58
n 1 6 1 n 1 6 1
Step 3. Compute the coefficient of correlation r using the formula, the sum from Column G in the table,
and the calculated standard deviations.
r

 X  X Y Y   202

202
 0.9455  0.95
(n  1)(sx s y ) 5(4.98)(8.58) 213.642
H0:  0
c. Reject H0 if t > 2.132
H1:   0
0.95 4
t  6.08 H0 is rejected.
1  0.952
There is a positive correlation between the fuel consumption and automobile
speed.
13. a. Scatter
Cars Sold vs Number of sales People
Diagram
70
Num ber o f Cars Sold
60
50
40
30
20
10
0
0 2 4 6 8 10 12 14
Number of Sales People
b. The following table is used to determine the coefficient of correlation.
A B C D E F G
Number Number
of Cars of Sales
Sold Staff
2 2
Y (Y  Y ) (Y  Y ) X ( X  X ) ( X  X ) ( X  X )(Y  Y )
53 0.125 0.02 5 -2.125 4.52 -0.27
47 -5.875 34.52 5 -2.125 4.52 12.48
33
48 -4.875 23.77 7 -0.125 0.02 0.61

50 -2.875 8.27 4 -3.125 9.77 8.98
58 5.125 26.27 10 2.875 8.27 14.73
62 9.125 83.27 12 4.875 23.77 44.48
45 -7.875 62.02 3 -4.125 17.02 32.48
60 7.125 50.77 11 3.875 15.02 27.61
n 8 8
Total 423 288.91 57 82.91 141.1
Step 1. Compute the means using sums in Column A and D:

Y  423  52.875 X 57
Y X   7.125
n 8 n 8
Step 2. Compute the standard deviations using the sums in Column C and F:
(Y  Y )2 288.91 ( X  X ) 2 82.91
sy    6.42 sx    3.44
n 1 8 1 n 1 8 1
Step 3. Compute the coefficient of correlation r using the formula, the sum from Column G in the table,
and the calculated standard deviations.
r

 X  X Y Y   
141.1

141.1
 0.9127  0.91
( n  1)( sx s y ) 7(3.44)(6.42) 154.5936
c. Coefficient of determination is r2. Thus 0.912 = 0.8281. There is a strong positive correlation
between the two variables. About 83 percent of the variation between the number of cars sold is
accounted for by the size of the sales staff.
d. The regression equation: we computed: r = 0.91, sy = 6.42, and sx = 3.44. Thus:
sy  6.42 
br  0.91   0.91(1.8663)  1.70
sx  3.44 
We computed: Y  52.875 and X  7.125 . Thus
a Y bX
 52.875  [(1.70)(7.125)]
 52.875  12.1125  40.7625
Thus, the regression equation is:
Ŷ = a + bX = 40.76 + 1.7 X
e. The equation crosses the Y-axis at 40.76. For each additional sales person, the number of cars
sold will increase by about 1.7 cars.
34
f. Use the table to compute the standard error of estimate.
(Y  Yˆ ) 2 48.559 X bX Ŷ Y Y- Ŷ (Y- Ŷ )2

s yx   5 8.5 49.26 53 3.740 13.988
n2 82
5 8.5 49.26 47 -2.260 5.108
 8.093  2.84
7 11.9 52.66 48 -4.660 21.716
4 6.8 47.56 50 2.440 5.954
10 17 57.76 58 0.240 0.058
12 20.4 61.16 62 0.840 0.706
3 5.1 45.86 45 -0.860 0.740
11 18.7 59.46 60 0.540 0.292
SUM 48.559
g. A 95% confidence interval.
57
First compute Yˆ and X . Yˆ  40.76  1.70(10)  57.76 and X   7.125
8
1  10  7.125 
2
57.76  2.447  2.84    57.76  3.29  54.47 to 61.05

8 82.91
h. A 95% prediction interval.
1  10  7.125 
2
57.76  2.447  2.84  1    57.76  7.69  50.07 to 65.45

8 82.91
14. The null and alternative hypotheses are formulated as:
H0: β ≤ 0
H 1: β > 0
The test statistic follows the Student's t distribution with (14-2) = 12 degrees of freedom. The
alternate hypothesis given above specifies a one-tailed test in the positive direction. The critical value
for a one-tailed test using the 0.01 significance level is 2.681(Appendix B.2). Using formulal [13–6.]:
b  0 10.104
t   2.87
sb 3.522
Since 2.87 exceeds the critical value t = 2.681, the null hypothesis is rejected. There is
enough evidence to conclude that the slope of the line modeling the relationship between age,
Y, and account balance, X, differs from zero.
35
CHAPTER 14
MULTIPLE REGRESSION ANALYSIS
Part I
1. A 2. B 3. D 4. B 5. C
6. B 7. A 8. D 9. A 10. C
11. C 12. D 13. C 14. D
Part II
15.
a. The independent variable “years with firm” has the strongest correlation with salary.
b. None of the correlations among the independent variables are strong, so there is probably
not a problem with multicollinearity. However, variance inflation factors provide are better for
detecting multicollinearity since the measure the linear relationship between an independent variable
and all the other independent variables in the model.
c. To compute the VIFj’s we first need to regress each independent variable on the remaining
independent variable and obtain R j . These values of R j are: R years
 
= 0.1379, Rabsent =0.2890,
and R perform =0.1902. Next calculate each VIFj using:

VIF  .
 R j
These values are: VIFyears = 1.160, VIFabsent = 1.406, and VIFperform = 1.235. Since none of the
VIFj’s are greater than or equal to 10, we conclude that there is no problem with multicollinearity.
16.
H 0 : β1  β 2  β3  0
a.
H1 : Not all the β j  0
b. Reject H0 if F > 3.59
64110
.
213.7
c. F 3   1391
.
168.94 15.36
11
Because the computed value of 13.91 is greater than the critical value of 3.59, the null
hypothesis is rejected. Not all i equal 0.
64110
.
d. R2   0.791
810.04
Nearly 80 percent of the variation in salary is accounted for by the set of independent
variables.
17. a. H0: 1 = 0 H0: 2 = 0 H0: 3 = 0

H1: 1  0 H1: 2  0 H1: 3  0
36
b. Reject H0 if t < 2.201 or t > 2.201.
c. The null hypothesis is rejected for the independent variables years and perform (t is 4.38 and
2.25,
respectively). These variables should remain in the analysis. The null hypothesis is not rejected
for absent, therefore this variable should be deleted.
18. a. H0: 4 = 0
H1: 4  0
b. Reject H0 if t < -2.201 or t > 2.201 (the d.f. for t = 11. It is the same as for the previous model
because one variable, absent, was removed from the model and one variable, yrs x perform, was
added).
c. The null hypothesis can not be rejected since t for the interaction term is -0.222. The
interaction
between years and performance does not appear to be significant.
37
CHAPTER 15
INDEX NUMBERS
Part I
1. B 2. A 3. B 4. D 5. A
6. A 7. C 8. A 9. C 10. D
Part II
11.
Year Earnings Index Found by

2000 $1.29 100.00
2001 $1.41 109.30 (1.41  1.29)100
2002 $1.51 117.05 (1.51  1.29)100
2003 $1.52 117.83 (1.52  1.29)100
2004 $1.62 125.58 (1.62  1.29)100
2005 $1.55 120.16 (1.55  1.29)100
2006 $1.87 144.96 (1.87  1.29)100
2007 $2.18 168.99 (2.18  1.29)100
2008 $1.72 133.33 (1.72  1.29)100
2009 $1.03 79.84 (1.03  1.29)100
12. $36,280.35 found by
$79, 200
 100   $36,280.35
218.3
$9.49
13. a. 190.18 found by  100   190.18
$4.99
$18.12
b. 193.59 found by  100   193.59
$9.36
38
$1, 268.75
c. 194.52 found by  100   194.52
$652.25
1990 2010
Item Price Quantity Price
po qo po qo pt pt qo
Ground beef (per lb.) $1.39 80 $111.20 $2.79 $223.20
Milk (gal.) 1.69 100 169.00 3.25 325.00
Cookies (doz.) 1.29 95 122.55 2.59 246.05
Steak (per lb.) 4.99 50 249.50 9.49 474.50
Total $9.36 $652.25 $18.12 $1,268.75
$1, 268.75
194.52 found by  100   194.52
$652.25
d.
1990 2010
Item Price Quantity Price
po qt po qt pt qt pt qt
Ground beef (per lb.) $1.39 110 $152.90 $2.79 110 $306.90
Milk (gal.) 1.69 120 202.80 3.25 120 390.00
Cookies (doz.) 1.29 100 129.00 2.59 100 259.00
Steak (per lb.) 4.99 40 199.60 9.49 40 379.60
Total $9.36 $684.30 $18.12 $1335.50
$1,335.50
195.16 found by  100   195.16
$684.30
$1,335.50
e. 204.75 found by  100   204.75
$652.25
150.2
14. a. 110.20 found by  100   110.198 Thus the % increase is 10%
136.3
150.2
b. 110.20 found by  100   110.198
136.3
c. Net profit has increased by $13,635 from 1999 to 2009,
found by ($59,015  $45,380). The value $59,015 is found by ($65,035/ 110.2)100
39
CHAPTER 16
TIME SERIES AND FORECASTING
Part I
1. B 2. C 3. A 4. C 5. B
6. C 7. B 8. D 9. D 10. A
Part II
11. a. Plot and trend line.
b. From EXCEL, the least squares regression equation is: Yˆ  341.033  23.71 t .
c. Estimate for 2010 is $705 million, found by letting t = 15 in the trend equation:
Yˆ  341.033  23.710 t  341.033  23.710(15)  341.033  355.65  696.683 .
40
12.
Centered
Moving Moving Moving Specific
Qt. Homes Total Average Total Seasonal
2006 I 5

II 9
30 7.50
III 8 7.625 104.918
31 7.75
IV 8 7.750 103.226
31 7.75
2007 I 6 7.875 76.190
32 8.00
II 9 8.000 112.500
32 8.00
III 9 8.000 112.500
32 8.00
IV 8 8.125 98.462
33 8.25
2008 I 6 8.375 71.642
34 8.50
II 10 8.375 119.403
33 8.25
III 10 8.250 121.212
33 8.25
IV 7 8.250 84.848
33 8.25
2009 I 6 8.125 73.846
32 8.00
II 10 8.125 123.077
33 8.25
III 9

IV 8
41
Year I II III IV
2006 104.918 103.226
2007 76.190 112.500 112.500 98.462
2008 71.642 119.403 121.212 84.848
2009 73.846 123.077

Total 221.678 354.980 338.630 286.536 Total
Mean 73.893 118.327 112.877 95.512 400.609
Typical 73.781 118.147 112.705 95.367 400.000
Mean
CHAPTER 17
NONPARAMETRIC METHODS: GOODNESS-OF-FIT TESTS

Part I
1. B 2. A 3. D 4. C 5. D
6. A 7. C 8. A 9. D 10. B
Part II
H 0 : The proportions are all the same.
11. a.
H1 : The proportions are not all the same.
b. Reject H0 if > 12.592
c.
Day of week f0 fe (f0 - fe) (f0 - fe)2/ fe
Monday 20 60 40 26.67
Tuesday 30 60 30 15.00
Wednesday 20 60 40 26.67
Thursday 60 60 0 0.00
Friday 80 60 20 6.67
Saturday 130 60 70 81.67
Sunday 80 60 20 6.67
Total 420  163.35
d. The null hypothesis is rejected. There is a preference for shopping on certain

days of the week.
12. a.
H 0 : There is no difference between the sample data and the expected set of frequencies.
H1: There is a difference between the sample data and the expected set of frequencies.
b. Reject H0 if  > 4.605
c.
42
Category f0 fe (f0 - fe) (f0 - fe)2/ fe

Refuse 140 120 20 3.33
More info. 50 60 10 1.67
Donate 10 20 10 5.00
Total 200 200 10.00
d. The null hypothesis is rejected. The donation pattern was different last week.
13. a. H0: There is not a relationship between loan decision and the bank
officer.
H1: There is a relationship between loan decision and the bank officer.
b. Reject the null hypothesis if chi-square is greater than 5.991

 row total   column total 
c. Expected frequency  .
grand total

 60   175  52.5;
 80   175  70;
 60   175   52.5;
200 200 200
 60   25  7.5;
 80   25  10;
 60   25   7.5.
200 200 200
Felix Otis Foxburrow
f0 fe f0 fe f0 fe Total
Approved 50 52.50 70 70 55 52.50 175
Not approved 10 7.50 10 10 5 7.50 25
Total 60 60.00 80 80 60 60.00 200
2 
 50  52.5 2   70  70  2     5  7.5 2
 1.9047  1.905
52.5 70 7.5
The null hypothesis is not rejected. There is not a relationship between the loan decision and
the bank officer.
43
14. A statistical software package was used to calculate the mean and the standard deviation of
the 125 observations for charges. The sample mean and standard deviation were found to be
$8,028.14 and $2,103.43, respectively. To test for a normal distribution, the expected frequencies
for each class in the distribution are calculated under the assumption that the expected
distribution is normal. The z-scores for the boundaries of the classes are calculated using the
sample mean and sample standard deviation to estimate µ and σ in the formula:
The expected frequencies are found by multiplying the area (probability) for each class by the
total number of observations (125) as shown in the table below. After computing the expected
frequencies under normality, the goodness-of-fit test can be conducted. The null and alternative
hypotheses are:
Expected
H0: The population follows Charges Z-Values Area Found by Frequency
the normal distribution. under 5 under -1.44 0.075 0.5000-0.4250 9.375
5 up to 6 -1.44 to -0.96 0.0935 00.4250-0.3315 11.6875
H1: the population does not 6 up to 7 -0.96 to -0.49 0.1449 0.3315-0.1875 18.1125
follow the normal 7 up to 8 -0.49 to -0.01 0.1822 0.18750-0.0053 22.775
distribution. 8 up to 9 -0.01 to 0.46 0.1833 0.0053+0.1780 22.9125
9 up to 10 0.46 to 0.93 0.1478 0.3257-0.1780 18.475
10 up to 11 0.93 to 1.41 0.0954 0.4212-0.3257 11.925
The critical value of chi-square, 11 up to 12 1.41 to 1.89 0.0494 0.4705-0.4212 6.175
12 or more 1.89 or more 0.0295 0.5000-0.4705 3.6875
for 9-1-2 =6 degrees of freedom and a significance level of .05 is found in Appendix B.3. From
Appendix B.3 using the .05 significance level we find that the critical value of  2 is 12.592. Our decision
rule is to reject the null hypothesis if the calculated value of the test statistic is greater than 12.592. The
test statistic is calculated using text formula [17-1]:
44
2  
L
bf  f gO
M o
P e
2
M
N f e P
Q
The calculations are provided in the table:
Expected
Charges Z-Values Area Found by Frequency
The computed value of the under 5 under -1.44 0.075 0.5000-0.4250 9.375
5 up to 6 -1.44 to -0.96 0.0935 00.4250-0.3315 11.6875
test statistic is 27.79. Since 6 up to 7 -0.96 to -0.49 0.1449 0.3315-0.1875 18.1125
7 up to 8 -0.49 to -0.01 0.1822 0.18750-0.0053 22.775
this value is greater than the 8 up to 9 -0.01 to 0.46 0.1833 0.0053+0.1780 22.9125
9 up to 10 0.46 to 0.93 0.1478 0.3257-0.1780 18.475
10 up to 11 0.93 to 1.41 0.0954 0.4212-0.3257 11.925
critical value of 12.592, we
11 up to 12 1.41 to 1.89 0.0494 0.4705-0.4212 6.175
12 or more 1.89 or more 0.0295 0.5000-0.4705 3.6875
rejct the null hypothesis that Total = 27.79
the data is from a normal
population.
45
CHAPTER 18
NONPARAMETRIC METHODS: ANALYSIS OF RANKED DATA

Part I
1. D 2. C 3. D 4. D 5. C
6. A 7. A 8. B 9. C 10. D
Part II
11. a. H0: There is no difference in the tax liability between the two firms ( = 0.50)
H1: There is a difference in the tax liability of the two firms. (  0.50)
b. Reject H0 if there are 0, 1, 2, 10, 11, or 12 + signs
c. See Table for problem 12, for number of plus (+) signs.
d. There are 4 plus signs so the null hypothesis is not rejected. There is no
difference in the
tax liability between the two accounting firms.
12. a. H0: There is no difference in the tax liability between the two firms.
H1: There is a difference in the tax liability of the two firms.
b. Reject H0 if the smaller of the two rank sums is 17 or less.
c.
Taxpayer Sheets Square Differ Absolute Rank R+ R
Scwind 18.9 28.0 9.1 9.1 11.0 11
Gankowski 33.1 24.8 8.3 8.3 9.5 9.5
Virost 38.2 28.0 10.2 10.2 12.0 12.0
Williamson 30.2 38.0 7.8 7.8 8.0 8.0
Govito 30.7 31.7 1.0 1.0 2.0 2.0
Trares 30.9 25.7 5.2 5.2 6.0 6.0
Willbond 28.1 30.7 2.6 2.6 4.0 4.0
Fowler 27.2 29.9 2.7 2.7 5.0 5.0
Hawley 30.2 31.0 0.8 0.8 1.0 1.0
Hall 26.2 34.5 8.3 8.3 9.5 9.5
Sanchez 33.4 35.3 1.9 1.9 3.0 3.0
Naymik 33.6 28.2 5.4 5.4 7.0 7.0
Total 34.5 43.5
46
d. Because the smaller rank sum is 34.5, the null hypothesis is not rejected. There is not a
difference in the tax liability.
13. a. H0: The two distributions are the same. H1: The distributions are not the same.
b. The null hypothesis is rejected if z is less than 1.96 or z is greater than 1.96.
c.
Copier A Rank Copier B Rank
12,965 11 4,462 1
13,145 12 4,990 2
13,504 14 5,106 3
13,603 15 5,844 4
13,727 16 7,470 5
13,833 17 7,740 6
13,925 18 8,429 7
14,438 19 9,954 8
14,948 21 10,957 9
15,202 22 12,532 10
13,338 13
14,828 20
21,641 23
23,045 24
28,110 25
Total 165 160
    
 
z   .
       

d. H0 can not be rejected since 1.941 is not greater than 1.96.
e. There is not enough evidence to conclude that there is a difference between the two distributions.
14. a.
Show Husband Rank Wife Rank d d2
General Hospital 1 10 3 8 2 4
Regis and Kelly 10 3 19 1.5 1.5 2.25
All My Children 3 7.5 2 9.5 -2 4
Days of Our Lives 5 4.5 7 5 -0.5 0.25
The View 4 6 17 3 3 9
Oprah 5 4.5 19 1.5 3 9
One Life to Live 2 9 2 9.5 -0.5 0.25
Dr. Phil 3 7.5 4 6.5 1 1
Let’s Make a Deal 16 1 9 4 -3 9
Judge Judy 12 2 4 6.5 -4.5 20.25
59
47
48
  . 
b. rs    .
   
There is a moderately strong correlation between the ranks between the husband and the wife.
CHAPTER 19
STATISTICAL PROCESS CONTROL AND QUALITY MANAGEMENT

Part I
1. B 2. A 3. A 4. C 5. D
6. C 7. D 8. B 9. D 10. C
Part II
11. There are a total of 700 complaints. Determine the % of complaints in each category by dividing
each category count by 700. Order complaint caqtegories in descending order by corresponding
percent. Compute cumulative percent for this order as shown in the table. The Pareto Chart follows.
Category No. % Rank Cat. in Rank Order % Cum. %

In-flight 46
Service 6.57 7 Lost Luggage 34.29 34.29
Flight Delays 123 17.57 2 Flight Delays 17.57 51.86
Ticketing 48 6.86 6 Flight Cancel 13.57 65.43
Reservations 49 7.00 5 Flight Security 8.43 73.86
Flight Security 59 8.43 4 Reservations 7.00 80.86
Lost Luggage 240 34.29 1 Ticketing 6.86 87.71
Flight Cancel 95 13.57 3 In-flightService 6.57 94.29
Other 40 5.71 8 Other 5.71 100.00
49
b. Most of SkyBlue’s complaints are attributed to lost luggage, delayed or cancelled flights, and
flight security. SkyBlue should try to improve service in these areas first.
12. Month Total Mean Range

Jan 6.0 1.20 0.6
Feb 5.7 1.14 0.9
March 3.5 0.70 0.7
April 6.6 1.32 1.0
May 3.9 0.78 0.9
TOTAL 5.14 4.1
514
. 41
.
a. Mean   1028
. Average range   0.82
5 5
.  .  .   .  .
Limits are LCL = 0.555 and UCL = 1.501
b. For range: UCL = 2.115(0.82) = 1.734 LCL = 0(0.82) = 0
50
51 0.17  0.83
13. p  0.17, so 0.17  3  0.170  0.206
300 30
The LCL = 0 and the UCL = 0.376
65
14. c   4.333 c  3 c  4.333  3 4.333  4.333  6.245
15
15. a. P  X   | π  
. ,n     . found by, ( 0.122 + 0.270 + 0.285 )
b. P  X   | π  .,n     . found by ( 0.012 + 0.058+ 0.137 )
39 0.056  0.944 
16. a. p  0.056 so 0.056  3  0.056  0.069 so
700 100
b. 13 rods found by 0.125 x 100
17. a.
Mean Range 6.3825

Average mean   12765
.
9:00 1.2775 0.04 5
11:00 1.2700 0.03 017
.
1:00 1.2800 0.04 Average range   0.034
5
3:00 1.2725 0.03
5:00 1.2825 0.03
TOTAL 6.3825 0.17
1.2765  0.729(0.034)
The LCL = 1.252 and the UCL = 1.301
b. For range: UCL = 2.282(.034) = 0.0776
LCL = 0(0.034) = 0
51
CHAPTER 20
AN INTRODUCTION TO DECISION THEORY

Part I
1. C 2. D 3. B 4. A 5. A
6. B 7. C 8. C 9. A 10. B
Part II
11. a.
Acts Improves Recession

Build new $100,000 $40,000
Expand 25,000 5,000
Do nothing 0 0
b. E(A1) = 0.25 ($100,000) + 0.75 ($40,000) = $5,000
E(A2) = 0.25 ($25,000) + 0.75 ($5,000) = $2,500
E(A3) = 0.25 (0) + 0.75 (0) = 0
c. EMV = 0.25 ($100,000) + 0.75 (0) = $25,000
EVPI = ( $25,000  $2,500 ) = $22,500
d. Opportunity loss table
Acts Improves Recession

Build new 0 $40,000
Expand $75,000 5,000
Do nothing 100,000 0
e. The decision alternative with the largest expected value is to expand the current facility. The
cost of the uncertainty is $22,500. This is the expected value of perfect information.
52
12.
a,
States of Nature
Acts Fuel Price Fuel Price Stays Fuel Price
Increases the Same Decreases
No change $0 $0 $0
Buy New $1.6 billion $.4 billion -$.5 billion
Retrofit $.98 billion $.48 billion -$.07 billion
b. E(A1) = 0.60 ($0) + 0.30 ($0) + 0.10($0) = $0
E(A2) = 0.60 ($1.6 billion) + 0.30 ($.4 billion) + 0.10(-$.5 billion)= $1.03 billion
E(A3) = 0.60 ($.98 billion) + 0.30 ($.48 billion) + 0.10(-$.07 billion)= $.725 billion
c. EMV = 0.60($1.6 billion) + 0.30($.48 billion)+0.10($0) = $1.104 billion
EVPI = ( $1.104 billion $1.03 billion) = $.074 billion = $74,000,000
d. The alternative with the largest expected monetary value is A 2. So, they should buy the new
fuel efficient aircraft. The expected value of perfect information is $74 million dollars. This is
the upper limit on the amount of money that they should spend for information that would
reduce the uncertainty in the decision problem.
53

2010 Assignment Answers Ch 1-4

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

2010 Assignment Answers Ch 1-4

Uploaded by

Copyright:

Available Formats

2010 Assignment Answers SG 15e

1. Quantitative 6. Discrete 11. Interval 16. Ratio 21. D

DESCRIBING DATA: FREQUENCY TABLES, FREQUENCY

12. a, b, &c. Frequency, relative frequency, and cumulative frequency distributions:

f. Cumulative frequency distribution:

DESCRIBING DATA: NUMERICAL MEASURES

17. Average weight = 8 pounds found by:

18. 98.74% found by 8 (1.00)(0.98)(0.985)(0.98)(1.00)(0.985)(0.97)  1.00   8 0.90385  0.9874

b. Plus or minus 2 standard deviations or about 95%.

b. Find the standard deviaition using formula [13-13]:

12. a,b&c: Quartiles and median:

To locate the median, let P = 50 and

Minimum value = 15, Q3 = 23, Q2 = 35 Q3 = 91, Maximum value = 102

Min Q1 Med Q3 Max

e. We calculated the mean and standard deviation as follows:

13. a. Scatter diagram

b. There is a slight decline in miles per gallon as load capacity increases.

A SURVEY OF PROBABILITY CONCEPTS

12. a. 0.78, found by 0.92 × 0.92 × 0.92

15. Possible arrangements: (4)(6)(10) = 240

18. C = the event that the mower is a Colt

The remaining joint probabilities can then be determined. For example,

P(R) P(T) P(C) Total

DISCRETE PROBABILITY DISTRIBUTIONS

b. Standard deviation:   [( x   ) 2 P ( x )  1.64  128

c. At least seven: P(7) + P(8) = 0.267 + 0.100 = 0.367,

d. At least one: [1  P (0)] = [1  0.000015] = 0.999985,

b. At least ten: P(at least 10) = P(10) + P(11) + P(12)

= 0.283+ 0.206 + 0.069 = 0.558

b. At least one: P(x = 1) = [1 - P(0)] = [ 1 - 0.1353 ] = 0.8647

d. At least one Cannon: P(at least 1C) = [ 1 - P(0m) ] = ( 1 - 0.0298 ) = 0.9702

CONTINUOUS PROBABILITY DISTRIBUTIONS

a. Determine the height using Formula [7 – 3]

Draw the uniform distribution.

c. To determine the standard deviation use Formula [7–2].

(b  a ) 2 (55  35) 2 (20) 2

b. 78.81%, found by (0.50 + 0.2881)

e. 73.33%, found by (0.2881 + 0.4452) from parts a and c

13. 501.5 minutes or about 8 2 hours, found by (0.50  0.04) = 0.46,

b. P(7 or more defective) = 0.4168, found by (0.50  0.0832)

c. P(7 defective) = 0.1525, found by (0.4168  0.2643)

15. a. Mean: μ   .       Standard deviation σ   .      .   .

and solution from part d.

16. a. Mean: μ   .       Standard deviation σ   .      .   . .

c. P(Exactly 14) = 0.0516, found by (0.4441  0.3925 ),

d. P(7 to 9) = 0.3211, found by (0.3925  0.0714)

e. P(7 to 15) = 0.8663, found by (0.3925 + 0.4738)

SAMPLING METHODS AND THE CENTRAL LIMIT THEOREM

X   16.03  16.025 0.005

X   15.995  16.025 0.03

c. 0.5199, found (0.4251+0.0948 = 0.5199) or [1.000  (0.0749+0.04052)]

12. a. I. Reject claim that mean pulse is 90 when it is 90.

b. Critical value is 1.65, Reject H0 if z > 1.65

b. The level of significance is 0.05.

c. The test statistic in this situation is the t distribution.

b. The level of significance is 0.05.

e. The test statistic in this situation is the t distribution.

b. Critical value is 1.96, reject H0 if z > 1.96

TWO-SAMPLE TESTS OF HYPOTHESIS

d. p-value = 2(0.5000  0.3078) = 0.3844

e. H0 is not rejected. There is no difference in the mean amount of increase.

12. a. H 0 :  p   np H1:  p   np b. Reject H0 if t > 1.708