Question #3: Consider a sample with data values of 27, 25, 20, 15, 30, 34, 28, and

25. Compute the 20th, 25th, 65th, and 75th percentiles.

Manual Work:

Arrange Data in Asscending order:

27 15
25 20
25 25
20 25
15 27
30 28
34 30
28 34

(a) For the 20th percentile, i=(20/100)(8)=1.6, round it "up" to 2. The 20th percentile is the 2nd data value, which is 20.
(b) For the 25th percentile, i=(25/100)(8)=2. The 25th percentile is the average of the values in the 2nd and 3rd position, which is (20+25)/2=22.5.
(c) For the 65th percentile, i=(65/100)(8)=5.2, round it "up" to 6. The 65th percentile is the 6th data value, which is 28.
(d) For the 75th percentile, i=(75/100)(8)=6.The 75th percentile is the average of the values in the 6th and 7th position, which is (28+30)/2=29.

EXCEL Stats Functional Work:

75 100 6 4.5
(a) Command: =PERCENTILE(A7:A13, 0.2) Result: 22
(b) Command: =PERCENTILE(A7:A13, 0.25) Result: 23.75
(c) Command: =PERCENTILE(A7:A14, 0.65) Result: 27.55
(d) Command: =PERCENTILE(A7:A14, 0.75) Result: 28.5
Question #5: The Dow Jones Travel Index reported what business travelers pay for hotel rooms per night in major U.S. cities. The average hotel room rates for 20 cities are as follows:

City Rate per Night

Atlanta 163
Boston 177
Chicago 166
Cleveland 126
Dallas 123
Denver 120
Detroit 144
Houston 173
Los Angeles 160
Miami 192
Minneapolis 125
New Orleans 167
New York 245
Orlando 146
Phoenix 139
Pittsburgh 134
San Francisco 167
Seattle 162
St. Louis 145
Washington D.C. 207
Sum 3181

Manual Work:
(a) Average=3181/20=$159.05
(b) Arrange data in ascending order
Position Rate Per Night
1 120
2 123
3 125
4 126
5 134
6 139
7 144
8 145
9 146
10 160 2
11 162 3
12 163 3 5.75
13 166 5
14 167 6
15 167 11
16 173 4
17 177
18 192
19 207
20 245 75 100 6 4.5
Median=($160+$162)/2=$161
(c) Mode = $167
(d) For Q1, or the 25th percentile, i=(25/100)(20)=5. Q 1 is the average of the values in the 5th and 6th position, which is ($134+$139)/2=$136.5
(e) For Q3, or the 25th percentile, i=(75/100)(20)=15. Q3 is the average of the values in the 15th and 16th position, which is ($167+$173)/2=$170

EXCEL Stats Functional Work:

(a) To find the Mean Command: =AVERAGE(B6:B25) Result: $159.05

(b) To find the Median Command: =MEDIAN(B6:B25) Result: $161
(c) To find the Mean Command: =MODE(B6:B25) Result: $167
(d) To find the firtst quartilCommand: =QUARTILE(A29:A48,1
Result: $137.75
(e) To find the third quartil Command: =QUARTILE(A29:A48,3
Result: $168.50
Question #9: The National Association of Realtors provided data showing that home sales were the slowest in 10 years.
Sample data with representative sales prices for existing homes and new homes follow. Data are in thousands of dollars:

Existing homes New Homes

315.5 275.9
202.5 350.2
140.2 195.8
181.3 525.0
470.2 225.3
169.9 215.5
112.8 175.0
230.0 149.5
177.5
Sum 1999.9 2112.2

Manual Work
(a) Arrange data in ascending order
Existing homes New Homes
112.8 149.5
140.2 175.0
169.9 195.8
177.5 215.5
181.3 225.3
202.5 275.9
230.0 350.2
315.5 525.0
470.2

Median = $181.3 thousand or $181,300

(b) Median =($215.5+$225.3)/2= $220.4 thousand or $220,400
(c) New homes has the higher median sales price with $220.4 thousand. The difference between the two median sales prices = 220.4-181.3 = 39.1 or $39,100
(d) The percentage change for existing homes over 1-year = ($181.3-$208.4)/$208.4 = -13%, which means the sales median price decreased by 13% over a 1-year period.
The percentage change for new homes over 1-year = ($220.4-$249)/$249 = -11%, which means the sales median price for new homes decreased by 11% over a 1
Therefore, existing homes has the larger percentage change in median sales price with a 13% difference in one
Existing Homes New Homes
Year Median Sales Price

1 $208.4 $249
2 $181.3 $220.4
Percentage Change -13% -11%

EXCEL Stats Functional Work:

(a) To find the Median Command: =MEDIAN(A19:A27
Result: $181.3 or $181,300
(b) To find the Median Command: =MEDIAN(B19:B27Result: $220.4 or $220,400
(c) Finding the difference Command: =IMSUB(D36,D35)Result: 39.1 or $39,100
(d) Computing percentage
Command: =(C38-C37)/C37
change Result: -13%
Command: =(D38-D37)/D37 Result: -11%
Question #17: A home theater in a box is the easiest and cheapest way to provide surround sound for a home entertainment center. A sample of prices is
shown here. The prices are for models with a DVD player and for models without a DVD player.

Models with DVD Models without

Player Price DVD Player Price
Sony HT-1800DP $450 Pioneer HTP-230 $300
Pioneer HTD-330D 300 Sony HT-DDW750 300
Sony HT-C800DP 400 Kenwood HTB-306 360
Panasonic SC-HT90 500 RCA RT-2600 290
Panasonic SC-MTI 400 Kenwood HTB-206 300
Sum ### $1,550

Manual Work:
(a) Mean price for models w/ a DVD player = $2,050/5= $410
Mean price for models w/o a DVD player = $1,550/5=$310
The additional price paid to have a DVD player included = $410-$310=$100
(b) Range for models w/ DVD player = $500-$300=$200
Range for models w/o DVD player = $360-$290=$70

Models with DVD Models without

Player Price xbar x-xbar (x-xbar)^2 DVD Player Price xbar x-xbar (x-xbar)^2
Sony HT-1800DP $450 410 40 1600 Pioneer HTP-230 $300 310 -10 100
Pioneer HTD-330D 300 410 -110 12100 Sony HT-DDW750 300 310 -10 100
Sony HT-C800DP 400 410 -10 100 Kenwood HTB-306 360 310 50 2500
Panasonic SC-HT90 500 410 90 8100 RCA RT-2600 290 310 -20 400
Panasonic SC-MTI 400 410 -10 100 Kenwood HTB-206 300 310 -10 100
Sum= 22000 Sum 3200
Variance = 5500 Variance = 800
Standard deviation = 74.1619849 Standard deviation = 28.2842712

Variance for models w/ DVD player = E25/(5-1) = 5,50

Variance for models w/o DVD player = K25/(5-1) = 80
Standard deviation for models w/ DVD player = SQRT(E26) = 74.161985
Standard deviation for models w/o DVD player = SQRT(K27) = 28.284271
This information helps one understand the different measures of variabiality or dispersion among the prices for models with and without DVD players.

EXCEL Stats Functional Work:

(a) To find the Mean Command: = AVERAGE(B5:B9) Result: $410
Command: = AVERAGE(E5:E9) Result: $310
To find
additional price Command: = F38-F39 Result: $100
paid:
(b) To find the Variance: Command: = VAR(B20:B24) Result: 5,500
Command: = VAR(H20:H24) Result: 800
To find the Standard Command: = STDEV(B20:B24Result: 74.16198
\\\\\Deviation:
Command: = STDEV(H20:H24Result: 28.28427
Question #20: The following data were used to construct the histograms of the number of days required to fill orders for Dawson Supply Inc., and J.C.
Dawson Supply Days for Delivery: 11 10 9 10 11 11 10 11 10 10
Clark Distributors Days for Delivery: 8 10 13 7 10 11 10 7 15 12

Manual Work:
Dawson Supply Days for Delivery Clark Distibutors Days for Delivery
x xbar x-xbar (x-xbar)2 x xbar x-xbar (x-xbar)2
11 10.3 0.7 0.49 8 10.3 -2.3 5.29
10 10.3 -0.3 0.09 10 10.3 -0.3 0.09
9 10.3 -1.3 1.69 13 10.3 2.7 7.29
10 10.3 -0.3 0.09 7 10.3 -3.3 10.89
11 10.3 0.7 0.49 10 10.3 -0.3 0.09
11 10.3 0.7 0.49 11 10.3 0.7 0.49
10 10.3 -0.3 0.09 10 10.3 -0.3 0.09
11 10.3 0.7 0.49 7 10.3 -3.3 10.89
10 10.3 -0.3 0.09 15 10.3 4.7 22.09
10 10.3 -0.3 0.09 12 10.3 1.7 2.89
Sum = 4.1 Sum = 60.1
Variance = 0.45555556 Variance = 6.67777778
Standard dev. = 0.67494856 Standard dev. = 2.58413966

Range=11-9=2 Range: 15-7=8

Variance=D19/(10-1)=0.455556 Variance=60.1/(10-1)=6.677778
Standard deviation=SQRT(E20)=0.674948 Standard deviation=SQRT(I20)=2.58414

Dawson has smaller range and standard deviation, it implies it has more stable delivery.

EXCEL Stats Functional Work

Command: VAR(A9:A18) Command: VAR(F9:F18)

Result: 0.455555555556 Result: 6.67777777778

Command: STDEV(A9:A18 Command: STDEV(F9:F18

Result: 0.674948557711 Result: 2.58413965911

Dawson has smaller range and standard deviation, it implies it has more stable delivery.
Question #23: Scores turned in by an amateur golfer at the Bonita Fairways Golf Course in Bonita Springs, Florida, during 200

Manual Work
(a) Average = 608/8=76 (for BOTH)
xbar x-xbar (x-xbar)^2 xbar
74 76 -2 4 71 76
78 76 2 4 70 76
79 76 3 9 75 76
2005 Season

2006 Season
77 76 1 1 77 76
75 76 -1 1 85 76
73 76 -3 9 80 76
75 76 -1 1 71 76
77 76 1 1 79 76
Sum 608 Sum = 30 Sum 608
Variance = 4.285714286
Standard dev. = 2.070196678

Variance(2005) = E15/(8-1)=4.285714286 Variance(2006) = K15/(8-1)=27.71428571

Standard deviation (2005) = SQRT(E16)=2.07019667 Standard deviation (2006) = SQRT(K16)=5.264
(b) The primary difference between both seasons performances is shown in the standard deviations. The 2006s Season data has
standard deviation, which reveals a less stable performance compared to 2005s Season. The only improvement in 2006s Season
to be that at times the golfer scored really well (higher than any of the scores in the prior season), yet he also scored poorly (at t
than any of the scores in the prior season).

EXCEL Stats Functional Work:

(a) To find the Mean: Command: = AVERAGE(B7:B14) Result: 76
Command: = AVERAGE(H7:H14) Result: 76
To find the Variance (2005): Command: = VAR(B7:B14) Result: 4.285714286
To find the Variance (2006): Command: = VAR(H7:H14) Result: 27.71428571
To find the Standard deviation (200Command: = STDEV(B7:B14) Result: 2.070196678
To find the Standard deviation (200Command: =STDEV(H7:H14) Result: 5.264435935
prings, Florida, during 2005 and 2006 are as follows:

x-xbar (x-xbar)^2
-5 25
-6 36
-1 1
1 1
9 81
4 16
-5 25
3 9
Sum = 194
Variance = 27.7142857
Standard dev. = 5.26443594

5/(8-1)=27.71428571
006) = SQRT(K16)=5.264435935
The 2006s Season data has a larger
provement in 2006s Season would have
t he also scored poorly (at times worst
Question #25: Consider the sample with data values of 10,20,12,17, and 16. Compute the z-score for each of the five observatio
Manual Work
x xbar x-xbar (x-xbar)2 Z-score
10 15 -5 25 -1.25
20 15 5 25 1.25
12 15 -3 9 -0.75
17 15 2 4 0.5
16 15 1 1 0.25
Sum 75 Sum = 64
Variance = 16
Standard dev. = 4

When calculating the z-score, one has to know the mean and standard deviation
Therefore, the Mean =75/5=15. The Variance = E9/(5-1)=16. The Standard Deviation = SQRT(E10)=4
𝑥_(𝑖 −
The z-score: (x -mean)/standard dev. 𝑥 ̅ )/𝑠

for 10 = (10-15)/4 = -1.25 which means the data values must be below 1.25 standard deviations from the mean
for 20 = (20-15)/4 = 1.25 which means the data values must be above 1.25 standard deviations from the mean
for 12 = (12-15)/4 = -0.75 which means the data values must be below 0.75 standard deviations from the mean
for 17 = (17-15)/4 = 0.5 which means the data values must be above 0.5 standard deviations from the mean
for 16 = (16-15)/4 = 0.25 which means the data values must be above 0.25 standard deviations from the mean

EXCEL Stats Functional Work:

To find the Mean Command: =AVERAGE(B4:B8) Result: 15
To find the Variance Command: =VAR(B4:B8) Result: 16
To find the Standard Deviation Command: =STDEV(B4:B8) Result: 4
Computing the z-score for each observation
10 Command: =(B4-C4)/E11 Result: -1.25
20 Command: =(B5-C5)/E11 Result: 1.25
12 Command: =(B6-C6)/E11 Result: -0.75
17 Command: =(B7-C7)/E11 Result: 0.5
16 Command: = (B8-C8)/E11 Result: 0.25
ch of the five observations.

s from the mean

s from the mean
s from the mean
from the mean
s from the mean
Question #27 Consider a sample with a mean of 30 and a standard deviation of 5. Use Chebyshev's theorem to determine the pe
a. 20 to 40
b. 15 to 45
c. 22 to 38
d. 18 to 42
e. 12 to 48

Manual Work

Chebyshev's
Ranges z-score Theorem
20 to 40 2 75%
15 to 45 3 89% 25000
22 to 38 1.6 61%
18 to 42 2.4 83%
12 to 48 3.6 92%

Mean 30
Standard Deviation 5
𝑥_(𝑖 −
Z-score: 𝑥 ̅ )/𝑠
a. (40-30)/5=2 which means the data values must be above z = 2 standard deviations from the mean
(20-30)/5=-2 which means the data values must be below z = 2 standard deviations from the mean
b. (45-30)/5=3 which means the data values must be above z = 3 standard deviations from the mean
(15-30)/5=-3 which means the data values must be below z = 3 standard deviations from the mean
c. (38-30)/5=1.6 which means the data values must be above z = 1.6 standard deviations from the mean
(22-30)/5=-1.6which means the data values must be below z = 1.6 standard deviations from the mean
d. (42-30)/5=2.4 which means the data values must be above z = 2.4 standard deviations from the mean
(18-30)/5=-2.4which means the data values must be above z = 2.4 standard deviations below the mean
e. (48-30)/5=3.6 which means the data values must be above z = 3.6 standard deviations from the mean
(12-30)/5=-3.6which means the data values must be below z = 3.6 standard deviations from the mean
(1−
Chebyshev's Theorem:1/𝑧^2 )
(1−1/2^2 ) = 0.75 or
a. 75% which means at least 75% of the data values must range b/w 2
(1−1/3^2 ) = 0.888888889 or
b. 89% which means at least 89% of the data values must range b/w 1

c. (1−1/ 〖 1.6 〗 ^2 ) = which means at least 61% of the data values must range b/w 2
0.609375 or 61%
d. (1−1/ 〖 2.4 〗 ^2 ) = 0.826388889 which means at least 83% of the data values must range b/w 1
or 83%
e. (1−1/ 〖 3.6 〗 ^2 ) = 0.922839506 which means at least 92% of the data values must range b/w 1
or 92%

EXCEL Stats Functional Work:

Z-score:
a. Command: =(C11-C17)/C18Result: 2
b. Command: =(C12-C17)/C18Result: 3
c. Command: =(C13-C17)/C18Result: 1.6
d. Command: =(C14-C17)/C18Result: 2.4
e. Command: =(C15-C17)/C18Result: 3.6

Chebyshev's Theorem:
a. Command: =(1-1/D11^2) Result: 75%
b. Command: =(1-1/D12^2) Result: 89%
c. Command: =(1-1/D13^2) Result: 61%
d. Command: =(1-1/D14^2) Result: 83%
e. Command: =(1-1/D15^2) Result: 92%
orem to determine the percentage of the data within each of the following ranges:

30000 2500 -2

s from the mean

ns from the mean
s from the mean
ns from the mean
ons from the mean
ons from the mean
ons from the mean
ons below the mean
ons from the mean
ons from the mean

a values must range b/w 20 to 40

a values must range b/w 15 to 45

a values must range b/w 22 to 38

a values must range b/w 18 to 42

a values must range b/w 12 to 48

Question #28: Suppose the data has a bell-shaped distribution with a mean of 30 and a standard deviation of 5. Use the empirica
a. 20 to 40
b. 15 to 45
c. 25 to 35

Mean 30
Standard Deviation 5
𝑥_(𝑖 −
Z-score: 𝑥 ̅ )/𝑠
a. (40-30)/5=2 which means the data values must be above z = 2 standard deviations from the mean
(20-30)/5=-2 which means the data values must be below z = 2 standard deviations from the mean
b. (45-30)/5=3 which means the data values must be above z = 3 standard deviations from the mean
(15-30)=-15 which means the data values must be below z = 3 standard deviations from the mean
c. (35-30)/5=1 which means the data values must be above z = 1 standard deviation from the mean
(25-30)/5=-1 which means the data values must be below z = 1 standard deviation from the mean

According to the Empirical rule:

a. For the ranges 20 to 40 approximately 95% of the data values will be above 2 standard deviations from the mean.

𝐷𝑎𝑡𝑎 𝑤𝑖𝑡ℎ𝑖𝑛 2 𝜎
𝑜𝑓 𝜇

b. For the ranges 15 to 45 almost all of the data values will be above 3 standard deviations from the mean.

𝐷𝑎𝑡𝑎 𝑤𝑖𝑡ℎ𝑖𝑛 3 𝜎
𝑜𝑓 𝜇
c. For the ranges 25 to 35 approximately 68% of the data values will be above 1 standard deviation from th

𝐷𝑎𝑡𝑎 𝑤𝑖𝑡ℎ𝑖𝑛 1 𝜎
𝑜𝑓 𝜇
iation of 5. Use the empirical rule to determine the percentage of data within each of the following ranges:

ations from the mean

ations from the mean
ations from the mean
ations from the mean
ation from the mean
ation from the mean

d deviations from the mean.

ns from the mean.

tandard deviation from the mean.
Question #31: The national average for the math portion of the College Board's SAT is 515. The
College Board periodically rescales the test scores such that the standard deviation is approximately
100. Answer the following questions using a bell-shaped distribution and the empirical rule for the
verbal test scores.

Tests scores
a. What is the percentage of SAT > 615
b. What is the percentage of SAT >715
c. What is the percentage of SAT b/w 415 and 515
d. What is the percentage of SAT b/w 315 and 615

Mean (𝜇) = 515

Standard deviation ( = 100
𝜎
)
a. z = (615-515)/100=1 which means the data values must be above z = 1 standard deviation from the mean. This causes 15.9%
b. z = (715-515)/100=2 which means the data values must be above z = 2 standard deviations from the mean. This causes 2.3%
c. z1 = (415-515)/100=-1 which means the data values must be within -1 and 0 standard deviations from the mean. This causes 3
z2 = (515-515)/100=0
d. z1 = (315-515)/100=-2 which means the data values must be within -2 and 1 standard deviations from the mean. This causes 8
z2 = (615-515)/100=1

a= A a=B

> 615 = 𝟏𝟓.𝟗%

𝜇 − 2𝜎 𝜇−1𝜎 𝜇 𝜇+1𝜎 𝜇+2𝜎 𝜇 − 2𝜎 𝜇−1𝜎 𝜇

C a=D 315-615= 𝟖𝟏
415-515= 𝟑𝟒.𝟏%
 a=D
415-515= 𝟑𝟒.𝟏%

𝜇 − 2𝜎 𝜇−1𝜎 𝜇 𝜇+1𝜎 𝜇+2𝜎 𝜇 − 2𝜎 𝜇−1𝜎 𝜇

he mean. This causes 15.9% of students to have a SAT math score greater than 615, according to the empirical rule.
the mean. This causes 2.3% of students to have a SAT math score greater than 715, according to the empirical rule.
om the mean. This causes 34.1% of students to have a SAT math score between 415 and 515, accoring to the empirical rule.

om the mean. This causes 81.8% of students to have a SAT math score between 315 and 615, according to the empirical rule.

> 715 = 𝟐.𝟑%

𝜇 − 2𝜎 𝜇−1𝜎 𝜇 𝜇+1𝜎 𝜇+2𝜎

315-615= 𝟖𝟏.𝟖%
𝜇 − 2𝜎 𝜇−1𝜎 𝜇 𝜇+1𝜎 𝜇+2𝜎
e empirical rule.

he empirical rule.
 x xbar x-xbar (x-xbar)2
3 6 -3 9
7 6 1 1
11 6 5 25
3 6 -3 9
6 6 0 0
30 Sum = 44
Variance = 11 11 =VAR(A3:A7)
Standard d 3.316625 3.316625 =STDEV(A3:A7)

3
7
11
3
6
8

for the 10th percentile, i=(10/100)(6)=0.6, round it up to 1. The 10th percentile is the 1st data value, which is 3.
3 =PERCENTILE(A28:A33,0.1)
for the 50th percentile, i=(50/100)(6)=3. The 50th percentile is the average of the values in the 3rd and 4th position, w
6.5 =PERCENTILE(A28:A33,0.5)
data value, which is 3.

n the 3rd and 4th position, which is (11+3)/2=7

 x xbar x-xbar (x-xbar)2
1 3 5 -2 4
2 5 5 0 0
3 11 5 6 36
4 3 5 -2 4
5 2 5 -3 9
6 6 5 1 1
30 Sum= 54
Variance = 10.8 10.8
Standard deviation
3.286335
=