M1 Drop Box: Textbook Assignment

Section 1.1

Problem 6. Interpretation (Lucy’s survey)

Lucy’s observations do not apply to all adults because her survey is not based on a random or
representative sample of the general adult population. Since she surveyed only her friends, the
group is likely to share common characteristics, making it non-generalizable. From the
description of the survey group, we cannot draw any conclusions regarding the age, gender, or
education level of the participants unless Lucy specifically gathered and shared that information.

Problem 8. Advertising: Auto Mileage

(a) The variable in this case is the median gas mileage for brand-new vehicles.

b) Representing a measured amount (mpg), the variable is quantitative.

(c) We are assuming that all newly-manufactured automobiles were part of the population
included in the sample.

Problem 12. Organisational Levels of Evaluation

(a) Ordinal (because it rates performance levels), salesperson's performance.

(b) The stock price of the company: the ratio (because the expense is a quantifiable quantity with
a real zero point).

(c) Proposed brand names: nominal (since names are only labels without any inherent hierarchy).

(d) The chief executive officer's private office temperature: interval (the temperature may be
measured, but the Fahrenheit scale does not have a real zero).

(e) A ratio of income over the last five years, with a real zero point for income as it is a
quantifiable variable.

(f) Nominal (a colour is a category label without intrinsic order)—the colour of the product's
packaging.

Section Fourteen: Evaluation of Educators

When using statistical approaches, Form B is the way to go. Data analysis, including average
calculations and statistical tests, is made simpler by using a quantitative scale (1–5). The
difficulty in conducting statistical analyses is heightened by the fact that Form A is qualitative
and open-ended.

Section 1.2

Problem 2. Statistical Literacy: Difference between a Simple Random Sample and a Systematic
Sample

 A simple random sample guarantees that each and every individual in the population is
given an equal opportunity to be chosen. "Typically, a generator that produces random
numbers or lottery technique is used to assign a number to each member in the
population, and then the numbers are selected at random.
 In a systematic sample, each member of the population is chosen at random from a list. A
new person is picked at random every kth iteration after the initial one. While picking the
first person is completely at random, there is a predetermined procedure for choosing
subsequent participants.

Problem 8. Analytical Thinking: Statistics Class Participants (a) Does the random selection
process ensure that every student is included in the sample?

 No, the odds of selection are not in everyone's favour. The selection process is based on a
coin flip; students from the top or bottom two rows might be chosen. If the coin lands
heads, students in rows 3 and 4 will be chosen. If it lands tails, students in rows 1 and 2
will not be chosen.
 (b) Is it possible to include students sitting in row 3 with students sitting in row 2 in your
sample? Is your sample a simple random sample?
Due to the nature of the sampling procedure, it is not feasible to combine students from
rows 2 and 3, since the method only permits the selection of the first or final two rows as
independent groups. Due to the fixed rows used for selection and the fact that not every
person has an equal probability of being included in the sample, this cannot be called a
simple random sample.
  (c) Give an example of how to choose 20 students at random from a class of 40.
 Assign a number between 1 and 40 to each student in a class of 40. This will provide a
basic random sample of 20 individuals. Next, choose 20 numbers at random from 1 to 40
using a random number generator. Don't replace any of the numbers. We shall include in
our sample the kids whose numbers match those.

Problem 20. Techniques for Sampling: Medical

 (a) Compile a complete roster of all patients released from mental health establishments.
Make a tally of how long each patient was in the hospital: 2 days or less, 3-7 days, 8-14
days, and more than 14 days. Select individuals at random from every category.
 The population is classified in this way according to the average duration of hospital
stays, and a random sample is drawn from each stratum.
 (a) Gather all mental health facility discharge lists. To get the sample, we'll utilise a
random-number table and assign each patient a number.
 Because each patient is assigned a unique number and the selection procedure is based on
chance, we may say that this is a basic random sample.
 (c) Incorporate all patients into the discharge lists of the randomly chosen hospitals,
which should be a subset of MMH institutions throughout five regions.
 The fact that all patients at the randomly chosen hospitals make this a cluster sample, and
the fact that the hospitals themselves are clusters define the sampling method.
 (d) At the beginning of the year, instruct each MMH facility to survey every 500th patient
discharged.
The methodical selection of every 500th patient from a list characterises this sample as
systematic.
 (e) Tell all mental health centres to submit in surveys of ten patients who were released
this week.
 Due to the lack of a strict random selection process, this sample is predicated on the
convenience of collecting data from ten patients who were released that week.

Section 1.3
Problem 2. Statistical Literacy: Double-Blind Procedure
In a double-blind procedure, neither the participants nor the researchers know who is receiving
the placebo or the new drug. In this experiment, participants in both the control group and
treatment group would be randomly assigned to receive either the placebo or the new drug. Both
groups would take pills that look identical in appearance, so participants cannot tell which one
they are taking. Similarly, the researchers administering the pills or collecting data would not
know which group a participant belongs to.

Benefits of a double-blind procedure include:

 Reducing bias: Since neither the participants nor the researchers know who is receiving
the treatment, there is less chance of bias influencing the results.
 Improved reliability: It eliminates the placebo effect, where participants' expectations
may affect outcomes, and prevents researchers from unintentionally influencing the study
through their behavior or expectations.

Problem 6. Interpretation: Echo Generation’s Classification of Luxuries vs. Necessities

The results from 2006 may not fully reflect how the Echo generation would classify items in
2016. Reasons include:

 Economic changes: Over a decade, inflation, income levels, and economic conditions
change, which may influence how people perceive luxuries and necessities.
 Technological advances: New products and services that didn’t exist or weren’t as
widespread in 2006 (e.g., smartphones, streaming services) could be considered
necessities in 2016, affecting the classification.
 Social changes: The Echo generation’s values and lifestyle may evolve over time,
shifting their perception of what constitutes a luxury or necessity.

Problem 8. General: Gathering Data

(a) The incidence of malpractice lawsuits filed by low-income and elderly patients is half that of
higher-income patients, according to an examination of 31,000 patients from New York hospitals
(Journal of the American Medical Association).
 The research relies on sampling as it examines a subset (31,000 patients) of the whole
population.

(a) Aviators used sophisticated flight simulators to examine the impact of wind shear on
landing and takeoff procedures.

Because it requires computer programmes to simulate how aircraft react to wind shear, this
research makes use of simulation.

(c) The National Football League looked at all of the league's scoring events, including
touchdowns and field goals, to see whether field goals were more common than touchdowns
(USA Today).

Because it examines every single football score from the league, this research employs a
census method.

(d) Subjects in an Australian research comprised 588 individuals, both male and female, who
had precancerous skin lesions. Half of the participants received a sunscreen-containing skin
cream with an SPF of 17, while the other half received a placebo cream. According to the
New England Journal of Medicine, those who used sunscreen in conjunction with sun
protection had a lower incidence of new precancerous skin lesions after seven months.

Because variables (sunscreen usage vs. inactive cream) are being controlled and the effects
on skin lesions are being observed, this research may be considered an experiment..

Section 2.1

Problem 2. Using the class boundaries of 10–19, 20–29, 30-39, and 40–49, what might possibly
go wrong in terms of statistical literacy?

One issue with these class boundaries is that they don't account for all possible data points. There
is a discrepancy between the data set's maximum value of 52 and the final class's maximum
value of 49. Hence, the frequency table will not include the values ranging from 50 to 52. To
resolve this, broaden the class limitations to include the whole range, such as 50-59 or above.
Problem 6. Basic Computation: Finding Class Width and Class Limits
To create a frequency table with 5 classes from a data set with a low value of 10 and a high value
of 120:

1. Class width formula:

Class width=High value−Low valueNumber of classes=120−105=1105=22\text{Class

width} = \frac{\text{High value} - \text{Low value}}{\text{Number of classes}} = \
frac{120 - 10}{5} = \frac{110}{5} =
22Class width=Number of classesHigh value−Low value=5120−10=5110=22

2. Class limits:
The first class will start at 10 and extend for a width of 22. The limits would be:
o Class 1: 10–31
o Class 2: 32–53
o Class 3: 54–75
o Class 4: 76–97
o Class 5: 98–120

Problem 8. Critical Thinking: Shape of Histogram for College Rankings

Since the colleges are ranked from 1 (best) to 100 (worst), with no ties, the shape of the
histogram will likely be uniform. This is because each rank is equally likely, assuming the
colleges are evenly distributed across the rankings.

Problem 10. Critical Thinking: Salary Data

(a) Histogram using class boundaries 53.5, 99.5, 145.5, 191.5, 237.5, 283.5:
The histogram would show that most of the salaries are clustered between 53.5 and 99.5, with
one value (280) falling in the last class (237.5–283.5).

(b) Outlier and Possible Owner’s Salary:

Yes, the last data value of 280 thousand dollars appears to be an outlier because it is significantly
higher than the other salaries. It could potentially be the owner's salary.
(c) New histogram after eliminating the 280 thousand dollar salary:
With the new class boundaries (53.5, 62.5, 71.5, 80.5, 89.5, 98.5), the new histogram will reflect
the salary distribution of most employees more accurately because it excludes the outlier and
focuses on the typical range of salaries (between 54 and 98 thousand dollars).

Problem 16. Medical: Glucose Testing (Using Six Classes)

The data set ranges from 45 to 109, so let's determine the class width and class limits.

1. Class width formula:

Class width=109−456=646≈10.67≈11\text{Class width} = \frac{109 - 45}{6} = \

frac{64}{6} \approx 10.67 \approx 11Class width=6109−45=664≈10.67≈11

(Round up to the nearest whole number for convenience.)

2. Class limits:
The class limits would be:
o Class 1: 45–55
o Class 2: 56–66
o Class 3: 67–77
o Class 4: 78–88
o Class 5: 89–99
o Class 6: 100–110

These class limits and widths will allow you to create a frequency table and a histogram to
represent the glucose levels.

Section 2.2

Problem 6. Here is the cluster bar graph showing the influence of advertising on large purchases
by age group. The percentages of people in the 18–34 and 45–54 age groups who reported being
influenced or not influenced by ads are clearly displayed.
For part (a) of the question: Jenna was misled because the vertical scales of the original graphs
were different". By using the same scale for both age groups, the difference becomes more
noticeable. You can easily observe that a higher percentage of the 45–54 age group reported
being influenced by ads compared to the 18–34 age group.

Problem 10. Here is the pie chart showing the allocation of professional time for college
professors based on the data provided. The largest portion of time is dedicated to teaching (51%),
followed by research (16%), with smaller percentages for professional growth, community
service, service to the college, and consulting outside the college.
Section 2.3

Problem 6. Stem-and-Leaf Displays for Golf Scores

(a) First-Round Scores:

Stem Leaves
6 567
6 99
7 011123
7 111234455
7 6667
(b) Fourth-Round Scores:

Stem Leaves
6 899
6 999
7 00111122
7 11112334
7 24

(c) Interpretation:

 Lowest Scores: The lowest first-round score was 65, while the lowest fourth-round score
was 68. So, the lowest scores were lower in the first round.
 Highest Scores: The highest first-round score was 75, and the highest fourth-round score
was also 75. Therefore, the highest scores were the same in both rounds.

Overall, the fourth-round scores tended to be higher than the first-round scores, with a slight shift
towards higher numbers. This might indicate that the course was more challenging in the fourth
round, or the players were fatigued.