Chapter 1: Sections 1.1, 1.2, & 1.
4
Introduction to Statistics
What is/are Statistics?
In general, the practice of statistics involves studying information that has been collected so that
we can learn more about the group of individuals we’re interested in. The process of statistics is:
1. Formulate a question you want to know
2. Collect information to answer the question
3. Describe the information you collected
4. Draw conclusions about your question (by using appropriate statistical methods)
Statistics are also summary values acquired from a sample (Chapter 3)
Why statistics are important to understand?
! Every day we are barraged with them!
● the risk of getting a disease ● the percentage of voters supporting a particular candidate ● a
baseball player's batting average ● the probability of getting an A in a course ●the odds of it raining
It is important to be wise consumers of the statistics you are presented with every day - to know what
questions to ask to know if they are accurate.
Be savvy, not swayed =
Make knowledgeable, informed decisions instead of being influenced by people with an agenda
[Link]
The Language of Statistics
__________________ refers to the entire collection of individuals (all of them) being studied about
o All KSU students
o All individuals of a specific type, such as all honeybees
o All of the used vehicles sold at a specific auto dealership, like Townsville Auto
__________________ is a subset (smaller portion) of the population (only some of them)
o Some KSU students out of all KSU students
o Some of the individuals of a specific type, like some honeybees out of all of them
o Some of the used vehicles sold at the Townsville Auto dealership
A good sample should be a mini version of the population the sample was taken from
The quality of the sample selected will impact how much the information from our sample can
tell us about the original population the sample was taken from
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 1
A sample is considered to be a good sample if it is ___________________________ of the population,
meaning the characteristics of the individuals in the sample must reflect the characteristics of the
individuals in the population.
__________________ represents the sample size, which is the number of individuals in your sample.
Practice: Populations & Samples
1. Suppose 42% of all KSU students were born in Georgia. Does this 42% represent a population or
a sample?
2. Suppose 200 KSU students were surveyed, and 46% of them said they were born in Georgia.
Does this 46% represent a population or a sample?
3. Suppose the average highway miles per gallon for a sample of 40 used vehicles sold from the
Townsville Auto Dealership was 27.05. Does this 27.05 represent a sample or population?
4. Only 12 men have walked on the moon. The average time these men spent on the moon was
43.92 hours. Does this average of 43.92 hours represent a population or a sample? Source:
[Link]
Data
The information collected is called _____________ and describes characteristics of an individual either
Numerically, such as height or number of siblings
Non-numerically, such as gender or blood type
→ Data values that summarize a characteristic of the entire population are called __________________
→ Data values that summarize a characteristic of a sample are called ____________________________
Practice: Parameters & Statistics
1. Suppose 42% of all KSU students were born in Georgia. Is this 42% a parameter or a statistic?
2. Suppose 200 KSU students were surveyed, and 46% of them said they were born in Georgia. Is
this 46% a parameter or a statistic?
3. Suppose the average highway miles per gallon for a sample of 40 used vehicles sold from the
Townsville Auto Dealership was 27.05. Is this 27.05 a parameter or a statistic?
4. Only 12 men have walked on the moon. The average time these men spent on the moon was
43.92 hours. Is this average of 43.92 hours a parameter or a statistic? Source:
[Link]
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 2
Variables
The characteristics collected on the individuals are called ___________________.
These characteristics vary from one individual to the next, even though some individuals may
have the same characteristics.
Examples of possible variables include hair color, age, weight, race, favorite song, health status,
etc.
1. Quantitative variables: ______________________________________________________________
_____________________________________________________________________________________
a. There are two types of quantitative variables
i. _________________: Quantitative variables that can be listed and are usually
obtained by counting. This includes any value that can only be a whole number.
ii. _________________: Quantitative variables that can take on any value within a
given interval.
1. Sometimes continuous variables are rounded off to the nearest whole
number and presented as discrete variables, but if they can be any value
between two numbers, they are continuous variables.
2. Example: the weight of an object
a. Can be rounded off and presented as 1 gram, BUT
b. Can also be measured to as many decimal places as a scale allows,
for example, 1.29345 grams
2. Categorical variables (qualitative variables): _____________________________________________
a. It is important to realize that a number can be used to represent categorical data, such as
with a zip code or ID number, but you CANNOT meaningfully get a numerical average for
categorical variables.
b. There are two types of categorical variables
i. __________________: Categorical variables with categories that have a natural
order, for example like a Likert scale: dislike, neutral, like; income group labeled as
low, medium, and high; or letter grades: A, B…
ii. __________________: Categorical variables with categories that do NOT have a
natural order, as with gender, race, colors, etc.
1. _________________ variables are nominal categorical variable with ONLY
one individual in each category like a SSN, ID number, phone number. It can
be numerical, but it doesn't make sense to add them or get their average.
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 3
Practice: Variables
1. Suppose the Excel TownsvilleCarData file represents the population of all used vehicles sold by the
Townsville Auto dealership since it opened. Determine each type of variable in the data set.
Make: WheelDrive:
Model: Doors:
Year: Size:
Fuel: Style:
HP: HwyMPG:
Cylinders: CityMPG:
Transmission: MSRP:
Sampling
It is usually impossible to examine every member of a large population, so instead, we select a group of
a manageable size of individuals that we can examine from the population.
This is called ___________________________, which means collecting a sample, or subset, of
individuals from the population.
It is VERY important that the characteristics of the individuals in the sample _______________________
the characteristics of the individuals in the population, because we will use the information from the
sample to understand and draw conclusions about the population the sample came from.
The best way to do this is by using a __________________________ sampling method.
A ______________________ random sampling, also called an _________ method is a method by which
each possible combination of individuals that could be in your sample is equally likely. It is like a lottery.
For example, suppose that 10,000 lottery tickets are sold and 5 of them will be randomly drawn as the
winning tickets. Each possible collection of 5 tickets that can be formed is equally likely to be the group
of five tickets drawn.
In ______________________ random sampling, the population is divided up into groups, called strata,
then a random sample is drawn from each group (each stratum). This type of sampling is useful when
the groups differ from one another, but the individuals within each group tend to be alike based on
some characteristic (variable) relevant to the situation.
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 4
In ______________________ random sampling, items are drawn from the population in groups called
clusters. This type of sampling is useful when the population is too large and spread out for simple
random sampling to be feasible. The population gets divided into groups, and a random selection of the
groups determines which groups get to be in the sample.
In ______________________ random sampling, items are ordered, and every kth item is chosen to be
included in the sample. This type of sampling is sometimes used to sample products as they come off an
assembly line, in order to check that they meet quality standards.
Source: Essential Statistics, 3rd Edition, Navidi & Monk
Random sampling methods are the best, but sometimes, a random sample is very difficult or not
possible. In those cases, the best we can do is take a sample by some convenient method.
A ______________________ sample is a sample that is not drawn by a random method. This type of
sampling is not recommended, because it can incorporate ___________________ into the sample.
______________________ ______________________ samples are another form of non-random
sampling. This type of sampling is often used by media sources to engage the audience. For example, a
radio announcer will invite people to call the station and give their opinion on a particular topic. This
type of sample is never reliable, because people who volunteer to respond tend to have much stronger
opinions, whether negative or positive, than the typical population.
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 5
Practice: Sampling methods
A . Suppose that Townsville Auto sold 11,914 used vehicles since it first opened. The dealership owner,
Joe, wants to analyze the data but prefers to work with a more manageable size. So, Joe decides to take
a sample size of them. Which sampling method is represented by the following?
A. Joe lists all the used vehicles and identifies every 100 th vehicle for his sample.
____________________
B. Joe just uses the information from the last 40 used vehicles sold from his lot.
___________________
C. Townsville Auto has sold used vehicles made from 1990-2017, a span of 27 years. Joe randomly
selects 5 of those 27 years, and then samples each vehicle made during each of those 5 years.
___________________
D. Joe takes a numbered list of all the used vehicles and uses a random number generator to select
40 numbers. The vehicles corresponding to those numbers are selected for the sample.
____________________
E. Joe recognizes that the type of transmission a vehicle has could affect the values for the
variables. There are also many more automatic transmission vehicles on the list than other
types. That means, he may even only get automatics in his sample, which would under-
represent vehicles with other transmission types. So, he separates them by transmission type
and takes a random sample from each type. (He then combines the samples together into one.)
___________________
Bias
___________________ occurs when the sampling method used systematically favors certain outcomes.
A study conducted by a procedure that tends to overestimate or underestimate a population
value is said to be ___________________________.
A sample taken by a method that is not representative of the population the sample was taken
from is said to be ___________________________.
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 6
A study conducted by a procedure that produces the correct result on the average is said to be
___________________________.
A sample taken by a method that produces a sample representative of the population the
sample was taken from is said to be ___________________________.
Sources of bias
Voluntary Response Bias
Voluntary response sampling tends to attract people with ___________________________________,
but those opinions do not necessarily reflect the opinions of the general population. So, voluntary
response surveys are considered ___________________________.
Self-interest Bias
Many advertisements contain data about their product being superior. The advertiser, however, may
not report any data that tends to show that the product is inferior. People who have a self-interest in
the outcome of an experiment or research study have an incentive to use ______________ methods.
Social Acceptability Bias
People may not respond ___________________________ if they feel they will be judged or get into
trouble for the true response. For example, a pollster may ask “Did you vote in the last presidential
election?” People who chose not to vote may be reluctant to answer “No,” because they are concerned
that not voting is socially unacceptable.
Leading Question Bias
Sometimes questions are worded in a way that ____________________________________________
___________________________. For example, a politician asks, “Do you favor decreasing the heavy tax
burden on middle-class families?” The words “heavy” and “burden” suggest that taxes are too high and
encourage a “Yes” response.
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 7
Non-Response Bias
Because people cannot be forced to answer questions or to participate in a study, there is usually a
percentage of people who refuse to do so. These people are called ______________________________.
Often, the opinions of those who do not respond are different from the opinions of those who do
respond. So, results from surveys in which a large percentage do not respond are often biased.
Sampling Bias
Sampling bias occurs when some members of the population are _______________________________
to be included in the sample than others. For example, a phone survey only during daytime may only
include people who do not work during the daytime.
More Than One Bias
Sometimes, there is more than one type of bias. Consider the following question to parents of school
children where only 30% responded. ‘‘Do you support improving public schools by issuing school
bonds?’’ This example exhibits _______________ bias because parents of school children may be more
likely to support increased spending on schools. There is also______________________________ bias,
because the question is worded to suggest a positive response by saying "improving public schools."
Finally, there is ________________________ bias, because only 30% of those sampled responded.
A Big Sample Does Not Make Up for Bias
A sample is useful only if it is drawn by a method the represents the ______________________ it was
taken from. If you use a ________________ method to draw a sample, then drawing a big sample
doesn’t help. For example, voluntary response surveys often draw several hundred thousand people to
participate. Although the sample is large, it is unlikely to represent the population well, so the results
are basically meaningless.
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 8
Practice: Sampling bias
A. A podcaster invites listeners to call the show to express their opinion about a political issue.
Would this survey be reliable, and if not, what type(s) of bias may be present?
B. A political lobbyist wants to determine whether someone is likely to vote in the next election
and asks a random sample of people, “Did you vote in the last presidential election?” Would this
survey be reliable, and if not, what type(s) of bias may be present?
C. Using a random number generator, 500 of the 80,000 people attending a professional football
game were randomly selected by seat number to complete a survey about their opinions on
using tax money to upgrade the football stadium. The owner of the stadium correctly reports
that a majority (more than 50%) of the 500 people surveyed support using tax money to
upgrade the stadium. Would this survey be reliable, and if not, what type(s) of bias may be
present?
D. A frozen yogurt chain is considering opening a new store in a particular city. Before opening, the
company wants to know the percentage of households in that city that regularly visit a frozen
yogurt shop. The market researcher obtains a list of households in that city, randomly selects
175 of them, and then mails a questionnaire that asks about the frozen yogurt eating habits and
flavor preferences. Of the 175 questionnaires mailed, nine are returned. Would this survey be
reliable, and if not, what type(s) of bias may be present?
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 9
E. In a factory producing portable fans, every 75th fan is inspected for defects. The defective rate
for these fans is reported to be 3%. Would these results be reliable, and if not, what type(s) of
bias may be present?
F. A group of biologists wants to estimate the abundance of barrel cactus in a desert. They divide
the desert into a grid of 100 rectangular areas but exclude 10 of those areas because they are
difficult to access. The biologists then measure the density of cactus in a randomly selected
sample of 40 of the 90 accessible areas. (Problem taken from 5.58, Mind on Statistics, 4th
Edition, Utts/Heckard). What type(s) of bias could occur if the 10 hard to reach areas were more
densely populated with barrel cacti than the other areas?
G. In a survey conducted by representatives of the nuclear power industry, people were asked the
question: “Do you favor the construction of nuclear power plants in order to reduce our
dependence on foreign oil?” A group opposed to the use of nuclear power conducted a survey
with the question: “Do you favor the construction of nuclear power plants that can kill
thousands of people in an accident?” Would either of these surveys be reliable, and if not, what
type(s) of bias may be present?
Deal STAT 1401 Chapter 1- © McGraw Hill and modified by Holly Deal, with permission Page 10