Deck 4: How to Get a Good Sample

Question 1

For Questions use the following narrative
Narrative: Boat show
The annual Vacation & Boat Show in Columbus, Ohio offers four types of attractions: boats, fishing gear, outdoor equipment, and vacation planning services.Tickets sell for $6 per person, and children under 5 get in free.This year the show organizers want to find out which attraction was most popular, so they surveyed 100 people at random who attended the show, and asked them.The results showed that 67% of them liked the boats best.
{Boat show narrative} This study is an example of which type of research strategy?

A)Sample survey
B)Experiment
C)Census
D)None of the above

Answer 1

Sample survey

Question 2

What is the most important limitation of a case study?

Answer 2

Only one or a small number of individuals is studied.You cannot assume the findings can be extended to any person or situation other than the one(s) studied.

Question 3

In an experiment, you measure the result of the feature being manipulated, called the __________ variable, on an outcome, called the __________ variable.

Answer 3

(respectively): explanatory; outcome (or response)

Question 4

What type of study takes place when the sample is equal to the population?

A)A large-scale survey
B)A census
C)A nonrandom sample
D)There is no such study.The sample can never be equal to the population.

Question 5

A (an) __________ study is an in-depth examination of one or a small number of individuals.

Question 6

Which of the following news story excerpts describes the results of a meta-analysis?

A)"A recent analysis of eight international studies found that..."
B)"A recent long-term study using 100,000 participants found that..."
C)"This single study contained 10 parts; each part used a different type of statistical analysis to get the results.The results showed that..."
D)None of the above.

Question 7

When you read the results of a scientific study, which of the following should you do first?

A)Determine which type of research strategy was used (observational study, randomized experiment, etc.)
B)Look at the results and decide whether they make sense or not.
C)Jump to the part where they show the data, and see if was collected properly.
D)Decide if the results apply to your life.

Question 8

Which of the following is a research strategy that involves the researcher manipulating the participants' environment in some way?

A)Sample survey
B)Randomized experiment
C)Observational study
D)None of the above

Question 9

What is the most important advantage of using a randomized experiment vs.an observational study, in terms of the statistical results?

Question 10

For Questions use the following narrative
Narrative: Boat show
The annual Vacation & Boat Show in Columbus, Ohio offers four types of attractions: boats, fishing gear, outdoor equipment, and vacation planning services.Tickets sell for $6 per person, and children under 5 get in free.This year the show organizers want to find out which attraction was most popular, so they surveyed 100 people at random who attended the show, and asked them.The results showed that 67% of them liked the boats best.
{Boat show narrative} Specify who/what the units are in this study.

Question 11

For Questions use the following narrative
Narrative: Boat show
The annual Vacation & Boat Show in Columbus, Ohio offers four types of attractions: boats, fishing gear, outdoor equipment, and vacation planning services.Tickets sell for $6 per person, and children under 5 get in free.This year the show organizers want to find out which attraction was most popular, so they surveyed 100 people at random who attended the show, and asked them.The results showed that 67% of them liked the boats best.
{Boat show narrative} The 100 people who were surveyed make up which group?

A)The population
B)The sample
C)The sampling frame
D)None of the above

Question 12

For Questions use the following narrative
Narrative: Boat show
The annual Vacation & Boat Show in Columbus, Ohio offers four types of attractions: boats, fishing gear, outdoor equipment, and vacation planning services.Tickets sell for $6 per person, and children under 5 get in free.This year the show organizers want to find out which attraction was most popular, so they surveyed 100 people at random who attended the show, and asked them.The results showed that 67% of them liked the boats best.
{Boat show narrative} Specify the population.

Question 13

What does the word 'unit' mean, in statistical terms?

A)The unit of measurement that is used (for example feet, inches, etc.)
B)The people doing the sampling are called the sampling unit.
C)A single individual or object to be measured.
D)None of the above.

Question 14

For Questions use the following narrative
Narrative: Boat show
The annual Vacation & Boat Show in Columbus, Ohio offers four types of attractions: boats, fishing gear, outdoor equipment, and vacation planning services.Tickets sell for $6 per person, and children under 5 get in free.This year the show organizers want to find out which attraction was most popular, so they surveyed 100 people at random who attended the show, and asked them.The results showed that 67% of them liked the boats best.
{Boat show narrative} Is there a practical and accurate way to get a sampling frame for this population? If yes, explain how.If no, explain why not.

Question 15

Name one advantage that observational studies have over experiments.

Question 16

The __________ is the entire collection of units about which we would like information; the __________ is the collection of units we actually measure.

Question 17

For Questions use the following narrative
Narrative: Boat show
The annual Vacation & Boat Show in Columbus, Ohio offers four types of attractions: boats, fishing gear, outdoor equipment, and vacation planning services.Tickets sell for $6 per person, and children under 5 get in free.This year the show organizers want to find out which attraction was most popular, so they surveyed 100 people at random who attended the show, and asked them.The results showed that 67% of them liked the boats best.
{Boat show narrative} Specify the sample.

Question 18

Why do researchers conduct experiments that are randomized (that is, participants are randomly assigned to the groups being compared)?

Question 19

Which of the following is not an example of a common type of research strategy as discussed in your textbook?

A)Sample surveys
B)Randomized experiments
C)Case studies
D)All of the above are examples of common types of research strategies

Question 20

A (an) __________ is a survey in which the entire population is measured.

Question 21

With a (an) __________ sample, every conceivable group of people of the required size has the same chance of being the selected sample.

Question 22

Suppose a random sample of people from your city found that 20% of the respondents own a cell phone, and the margin of error was 3%.In other words, you are confident that between 17% and 23% of all the people in your city own cell phones, based on this study.Suppose also that 1,000,000 people live in your city.Does this mean then that 200,000 people most likely own cell phones, plus or minus 30,000; or in other words, that between 170,000 and 230,000 people most likely own cell phones? (This was found by taking the results in percentage form and multiplying by the population size.)

A)Yes.The math shows that.
B)No.The margin of error in the latter case should be larger because you are dealing with the total number of people, not the percentage of people.
C)No.The margin of error in the latter case should be smaller because you are dealing with the total number of people, not the percentage of people.
D)None of the above.

Question 23

What two things do you need in order to produce a simple random sample from the population?

Question 24

Suppose you sampled 2,500 people for a marketing survey, but your boss thinks that you should have sampled more, say 4,000 people, because he says the results would have been much more accurate, even under the tight budget and time constraints on the company.Using statistics, how would you convince your boss to agree with you?

Question 25

As the number of units in the sample increases, the margin of error __________.

Question 26

For Questions use the following narrative
Narrative: Exit poll
Suppose a recent election exit pollster reports that "Forty-eight percent of the voters polled said they voted for Candidate A.The margin of error for this survey is plus or minus 2.5 percentage points." Assume the exit poll was designed and conducted correctly.
{Exit poll narrative} About how many people were sampled?

A)40
B)1,600
C)16,000
D)Not enough information to tell.

Question 27

With a (an) __________ sample, everyone in the population must have a specified chance of making it into the sample.

Question 28

Suppose you want to find out what percentage of students at your university would pay extra fees for the use of a new recreation center, and you want a simple random sample of 100 students.Suppose you go to the current recreation center and ask every 10th student who comes in the door to participate in your survey, until you have 100 people.Does this method of sampling give you a simple random sample? Explain your answer.

Question 29

Which is better, a survey of 50,000 people who participated on an Internet web site, or a survey of 5,000 people where a computer was used to randomly choose the survey participants?

Question 30

With a random sample of 2,500 people, we usually get an estimate that is accurate to within what percent of the truth (using the general rule)?

Question 31

What is the margin of error?

A)The amount of error allowable during the implementation of a survey.
B)The amount of bias you can expect in the survey results.
C)A measure of the accuracy of survey results.
D)None of the above

Question 32

For Questions use the following narrative
Narrative: Exit poll
Suppose a recent election exit pollster reports that "Forty-eight percent of the voters polled said they voted for Candidate A.The margin of error for this survey is plus or minus 2.5 percentage points." Assume the exit poll was designed and conducted correctly.
{Exit poll narrative} What can be concluded about Candidate A?

A)48% of all voters will vote for Candidate A.
B)We are confident that between 45.5% and 50.5% of all voters will vote for Candidate A.This means he/she will win the election, because 50.5% is more than half of the votes.
C)We are confident that between 45.5% and 50.5% of the voters will vote for Candidate A.The election is 'too close to call' at this point.It could go either way.
D)None of the above

Question 33

Assume you have a sampling frame of your entire population of interest, which is comprised of 100 people's names.Which of the following sources could not be used to select a truly simple random sample of 10 people from this population?

A)Assign each person a number from 001 to 100 and choose 10 numbers using a random number table.
B)Put each of the 100 names on equal sized pieces of paper, put the names in a hat, mix thoroughly, and draw out 10 names.
C)Put the names in alphabetical order and take the first 10 names on the list.
D)Each of the above methods would yield a truly simple random sample.

Question 34

Suppose a recent election exit pollster reports that "Forty-eight percent of the voters polled said they voted for Candidate A.The margin of error for this survey is plus or minus 2.5 percentage points." Assume the exit poll was designed and conducted correctly.What percentage of all voters do you expect to vote for Candidate A? Give the most complete answer you can.

Question 35

Suppose you have a herd of 100 cows and you need to select a simple random sample of 5 cows to test for a certain disease.You call the cows in for the evening, and pick the 5 that arrive first.Is this a simple random sample? Why or why not?

Question 36

The __________ can be applied to any percent reported regarding the sample to find an estimate of the percent of the population that would respond in the same way.

Question 37

Give three major advantages to using a (well designed and conducted) sample survey rather than a census.

Question 38

You have 15 employees working for you: Bob, Sue, Jim, Alex, DJ, Ann, Leslie, Eric, Deb, Tom, Clint, Richard, Tami, Ellen, and Katie.Use the following set of random numbers (generated from the computer program called Minitab) to take a simple random sample of 3 employees to serve on the donut committee: 1453131401146111619116112912015.Which employees got chosen for the donut committee? (Keep the employees in the order given when you assign numbers to them and do not start numbering with 0, start with 1.)

A)Ellen, Tami, Bob
B)Ellen, Tami, Ellen
C)Bob, Alex, DJ
D)None of the above

Question 39

What is a probability sampling plan?

A)A sampling method where everyone in the population must have a specified chance of making it into the sample.
B)A sampling method where every conceivable group of people of the required size has the same chance of being the selected sample.
C)A sampling method where each individual in the population has an equal probability of being selected to be in the sample.
D)None of the above

Question 40

If you tried to phone someone who was selected to participate in a telephone survey, and you couldn't reach that person the first time, what should you do?

A)Give up and select another person at random to take their place in the sample.
B)Keep that person in the sample, and keep trying to get a hold of them.
C)Remove that person from the sample and don't replace them.
D)Call your neighbor and ask them to participate in the survey instead - at least you know they're home.

Question 41

What is wrong with using a list of registered voters to predict election outcomes?

Question 42

Why should you be suspicious of a survey that was conducted on a random sample of 2,000 people but was done in one night (this is typical of the 'instant polling' that goes on in the media).

Question 43

Which of the following situations could cause bias in the results of a telephone survey?

A)A phone number in the sample was found to be 'not in service' or 'disconnected'.
B)The person who answered the phone refused to participate.
C)There was no answer, so the interviewer gave up and called someone else.
D)Each of the above would cause bias in the results.

Question 44

For Questions use the following narrative
Narrative: Valentine spending
Suppose you want to find out how much money each adult will spend on Valentine's Day this year, on average.
{Valentine spending narrative} Suppose you go to a local mall the day before Valentine's Day and ask the first 50 people you see.What type of sample are you getting here?

A)A self-selected sample
B)A convenience sample
C)A cluster sample
D)A systematic sample

Question 45

Give a situation where a simple random sample would be impossible or not feasible, and a systematic sample would be necessary.

Question 46

What is one advantage of a cluster sample over a simple random sample?

Question 47

If 1,000 surveys go out and 300 of them are returned, the nonresponse rate is __________ %.

Question 48

It is difficult to survey certain groups of people, such as the homeless population, because they don't have addresses, phone numbers, or residences.Explain how you would select a sample from the homeless population in your city, and comment on how 'random' you feel it would be.

Question 49

Many large surveys use a combination of sampling methods, applying them one at a time.This is called a (an) __________ sampling plan.

Question 50

Which of the following types of samples should be avoided at all costs?

A)A haphazard sample
B)A self-selected sample
C)A volunteer sample
D)All of the above

Question 51

Explain what is wrong with a poll conducted on a TV news program that asks viewers to call in with their opinion.

Question 52

For Questions use the following narrative
Narrative: Apartment complex
Suppose you want to survey the opinions of the residents of an apartment complex.The complex contains 100 buildings, each with 8 units per building, for a total of 800 units.You decide to sample 160 of the units.
{Apartment complex narrative} Suppose 50 of the buildings (400 total units) are for singles, and 50 buildings (400 units) are for non-singles.You randomly select 80 single units and then you randomly select 80 non-single units.What sampling method did you use?

A)A systematic sample.
B)A stratified sample.
C)A cluster sample.
D)A simple random sample

Question 53

Why might a researcher choose to conduct a stratified random sample over a simple random sample? Give two reasons.

Question 54

If you come across a survey based on a haphazard, volunteer, or self-selected sample, you should __________ the results.

Question 55

For Questions use the following narrative
Narrative: Valentine spending
Suppose you want to find out how much money each adult will spend on Valentine's Day this year, on average.
{Valentine spending narrative} Suppose you are a DJ of a local radio station, so you ask people to call in with their responses.What type of sample are you getting here?

A)A self-selected sample
B)A stratified sample
C)A cluster sample
D)A systematic sample

Question 56

For Questions use the following narrative
Narrative: Apartment complex
Suppose you want to survey the opinions of the residents of an apartment complex.The complex contains 100 buildings, each with 8 units per building, for a total of 800 units.You decide to sample 160 of the units.
{Apartment complex narrative} Suppose you start at a random starting point, and select every 5th unit to be in your sample, until you sample 160 units.What sampling method did you use?

A)A systematic sample.
B)A stratified sample.
C)A cluster sample.
D)A simple random sample

Question 57

Which of the following situations will produce the most accurate results?

A)A simple random sample of 3,500 people with a 10% response rate (350 responses total).
B)A simple random sample of 500 people with a 70% response rate (350 responses total).
C)A convenience sample of 350 people with a 100% response rate (350 responses total).
D)They would all produce the same level of accuracy since each had 350 responses.

Question 58

For Questions use the following narrative
Narrative: Apartment complex
Suppose you want to survey the opinions of the residents of an apartment complex.The complex contains 100 buildings, each with 8 units per building, for a total of 800 units.You decide to sample 160 of the units.
{Apartment complex narrative} Suppose you randomly sample 20 buildings, and then select every unit in those 20 buildings to be in your sample, for a total of 160 units.What sampling method did you use?

A)A systematic sample.
B)A stratified sample.
C)A cluster sample.
D)A simple random sample

Question 59

Most of the national polling organizations in the United States now use a method of sampling where a computer determines which phone numbers to call, given information such as the possible phone number exchanges to use, and the proportion of households with each exchange.This sampling method is called __________.

Question 60

Explain why it is so important that researchers report the response rates for their surveys.