STAT 1000 Assignment 1

DUE: January 25th (Wed. Eve. Section), January 26th (T/Th. Sections),
January 27th (MWF. Sections)
[11/2] 1. The following table gives the highest temperatures on record for selected cities:

City Rank Highest Temp. (◦ F )

Phoenix, AZ 1 122
Sacramento, CA 2 115
El Paso, TX 3 114
Omaha, NE 3 114
Dallas-Fort Worth 4 113
Wichita, KS 4 113
Boise, ID 5 111
San Diego, CA 5 111
Los Angeles, CA 6 110
Bismarck, ND 7 109

For each of the following column headings, identify whether the variables are categorical
and ordinal, categorical and nominal and quantitative.

Solution:
City – Categorical and Nominal.
Rank – Categorical and Ordinal.
Temp. – Quantitative.

[11/2] 2. The following table gives the best-selling albums of 1999 and the numbers sold:

Album Artist/Group Sold (millions)

Millennium Backstreet Boys 9.3
Baby One More Time Britney Spears 8.2
Ricky Martin Ricky Martin 5.9
Come on Over Shania Twain 5.5
Significant Other Limp Bizkit 4.8
Supernatural Santana 4.5
FanMail TLC 4.2
Devil Without a Cause Kid Rock 4.1
Christina Aguilera Christina Aguilera 3.4
Wide Open Spaces Dixie Chicks 3.4
For each of the following column headings, identify whether the variables are categorical
and ordinal, categorical and nominal and quantitative.

Solution:
Album – Categorical and Nominal.
Artist/Group – Categorical and Nominal.
Sold (millions) – Quantitative.
 [5] 3. Which of the following graph(s) could you use to study the following situations? (List
all that apply)

• Bar Graph
• Pie Chart
• Histogram
• Stem and leaf plot
• back-to-back stemplot
• timeplot

(a) What makes of cars do students drive?

Solution:
Bar graph, Pie chart.

(b) How old are students’ cars?

Solution:
Histogram, Stem and leaf plot

(c) How does the price of the Canadian dollar change (relative to the U.S. dollar) over
the year?

Solution:
Timeplot

(d) What are the number of medals won by each country participating in the Winter
Olympics?

Solution:
Bar graph, Pie chart.

(e) Compare the number of forest fires between Manitoba and Saskatchewan.

Solution:
back-to-back stemplot

[20] 4. The following are the weights of 54 University Females.

 100 110 112 120 121 126 126 127 127
128 129 129 129 131 131 132 135 135
135 136 137 137 137 138 140 140 141
147 148 148 151 151 151 153 154 154
156 162 162 163 165 165 170 171 171
182 185 185 191 197 200 200 213 215

(a) Construct a stem and leaf plot of the weights and comment on the distribution.

Solution:
The stemplot should be constructed by hand. The distribution of female weights
are skewed to the right. The median weight is 144 lbs. with a mean of 149
a1q4: Distribution
lbs. The range of female of Female
weights is 115 lbs. Weights Page 1
Distributions
Female Weights
Stem and Leaf
Stem Leaf Count
21 35 2
20 00 2
19 17 2
18 255 3
17 011 3
16 22355 5
15 1113446 7
14 001788 6
13 11255567778 11
12 0166778999 10
11 02 2
10 0 1

10|0 represents 100

(b) Use JMP to construct a histogram. What proportion of female students weigh
above 160 lbs.?

Solution:
 a1q4: Distribution of Female Weights P
Distributions
Female Weights

80 100 120 140 160 180 200 220

Looking at the histogram, there are 8 students with weights between 160 and
180, 5 students with weights between 180 and 200 and 4 students with weights
between 200 and 220. Therefore (8+5+4)/54 = 31.5% weigh more than 160 lbs.

(c) What is the 5-number summary for the above dataset? (Note: JMP calculates
quartiles differently, please use the method taught in class).

Solution:
The first step is to find the median. Since the observations are already ordered
we can find that the median is located in the (n + 1)/2 position. Located in the
27.5th position, between 141 and 147, therefore the median is 144.
Concentrating on the 27 observations to the left, the first quartile Q1 is located
in the 14th position. Therefore, Q1 is 131.
Concentrating on the 27 observations to the right, the third quartile Q3 is located
in the 14th (or 41st from the beginning). Therefore, Q3 is 165.
Finally, the 5 number summary is:
100 131 144 165 215

(d) If Shirley’s doctor said her weight is in the 75th percentile for all women her age,
how can she interpret this?

Solution:
For Shirley to be in the 75th percentile, this means that 25% of the population
weigh as much or more than her, while 75% weigh less than her.
 The following are the weights of 54 University Males.
137 140 142 143 148 149 149 150 150
152 152 154 156 157 157 157 158 158
158 159 159 160 161 162 162 162 162
164 165 165 165 165 165 166 166 166
167 167 167 168 168 170 172 172 173
174 174 175 177 180 181 183 184 193
(e) Use JMP to construct a histogram of male weights and comment on the distribution.

Solution: a1q4: Distribution of Male Weights

Distributions
Male Weights

130 140 150 160 170 180 190 200

The distribution of male weights is symmetric, the weights seem to be centred

between 160 and 170 with a range of 56 lbs.

(f) Identify any outliers in the dataset and draw (by hand ) an outlier boxplot.

Solution: a1q4: Distribution of Male Weights Page 1 of 1

Distributions
Male Weights

130 140 150 160 170 180 190 200

In order to identify outliers, we must construct the upper and lower fences.
The median is 163 located at the 27.5th position. Therefore, Q1 is 157 and Q3
is 168.
Therefore the 5 number summary is:
137 157 163 168 193
Therefore,
IQR = 168 − 157 = 11
Uf = Q3 + 1.5(IQR) = 168 + 1.5(11) = 184.5
 Lf = Q1 − 1.5(IQR) = 157 − 1.5(11) = 140.5

When drawing the outlier boxplot, the whiskers must extend out to the lowest
and highest observed data values INSIDE the fences. The whiskers should
extend to 142 and 184. The outliers are 137, 140 and 193. These values should
be indicated with stars. It should have been drawn by hand, the output above
is just a guideline of what the outlier boxplot should look like.

(g) Create side-by-side boxplots using JMP. (Click the little red arrow and under display
options remove points and the grand mean). Attach that output to your assignment
and compare both distributions.

Solution: a1q4sbs: Fit Y by X of Column 1 by Column 2 Page 1 of 1

Oneway Analysis of Column 1 By Column 2
220
210
200
190
180
170
Column 1

160
150
140
130
120
110
100
90
Female Male
Column 2

You can see that males have a higher mean weight than females. There is
also less variability/spread associated with male weights. The distribution of
female weights is skewed to the right, while the distribution of male weights is
symmetric.

[4] 5. Jeff invested his life savings in a carpet cleaning business in 2001. The following is the
average number of homes he has cleaned per month each year since.

Year 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011
Homes Cleaned 6.4 11.3 14.7 18.4 19.6 25.7 32.5 48.7 55.4 75.7 94.3

Use JMP to construct a time series and comment on what you see.
Instructions:

• You should have two columns, Year and Homes Cleaned.

 • Go to Analyze ⇒ Modeling ⇒ Time Series.
• Year ⇒ X, Time ID.
• Homes Cleaned ⇒ Y, Time Series ⇒ OK.
• A window talking about autocorrelation lags will open just say OK.
• Under the little red arrow remove BOTH check marked options AND go to Graph
and remove the “mean line.”
• Print out the graph and attach to you assignment.

Solution:
timeseries: Time Series of Column 2 Page 1 of 2
Time Series Column 2
100

80
Column 2

60

40
20
0
2000 2002 2004 2006 2008 2010 2012
Column 1

Time Series Basic Diagnostics

You can clearly see that there is an increasing trend. The term trend needs to be
mentioned when discussing time series, nothing about means or ranges...etc..
[8] 6. In January 2010 the fines for speeding tickets went up in the city of Winnipeg. If you
are caught going over the posted limit, you will be charged a fine of $150, plus $6.90 per
km/h over the speed limit. The fine for a speeding ticket Y is then,

Y = 150 + 6.90 X,

where X is the number of km/h you are over the posted speed limit.
The following are the number of kilometres over the posted limit from a sample of six
drivers.

15 9 21 8 7 12

(a) What is the mean and standard deviation of the number of kilomometres over the
posted limit from the above sample? (Show All Your Work ).

Solution:
P
xi 15 + 9 + 21 + 8 + 7 + 12 72
x̄ = = = = 12
n 6 6

rP
(xi − x̄)2
s=
r n−1
(15 − 12)2 + (9 − 12)2 + (21 − 12)2 + (8 − 12)2 + (7 − 12)2 + (12 − 12)2
=
r 5
140
= = 5.29
5

(b) Using the linear transformation given above, what is the mean and standard devi-
ation of the fines for a speeding ticket?

Solution:
We now want to find the mean and standard deviation of Y .

Using the linear transformation the mean of Y.

Ȳ = 150 + 6.90X̄ = 150 + 6.90(12) = $232.80

The standard deviation of Y.

SY = 6.90(SX ) = 6.90(5.29) = $36.50