Deck 9: Sampling

Question 1

A sampling method that separates the population into subgroups where each subgroup represents the entire population is called:

A) cluster sampling.
B) subgroup sampling.
C) stratified sampling.
D) systematic sampling.
E) sub-sampling.

Answer 1

A

Question 2

Which of the following is NOT true of nonprobability samples?

A) they are nonrandom sampling techniques
B) they can be prone to subconscious biases
C) they use human intervention
D) the chances of any one population member being selected into the sample can be computed
E) there is no way to determine the probability of a population member being selected into the sample, even if the population size is known

Answer 2

D

Question 3

Which of the following is NOT a practical constraint that may force sample size adjustments?

A) time pressure
B) study objective
C) cost constraint
D) data analysis procedures
E) skills of the researcher

Answer 3

E

Question 4

Sampling error can be caused by:

A) the size of the population
B) the method of the sample unit definition
C) the method of sample selection
D) the method of population selection
E) the education of the researcher

Question 5

Which of the following sample plans would NOT be considered a probability sample?

A) simple random sample
B) systematic sample
C) cluster sample
D) judgment sample
E) stratified sample

Question 6

One of the advantages of systematic sampling is that:

A) it is more representative in the final analysis.
B) the listing of the population may contain hidden periodicities.
C) it is not necessary to obtain a hard-copy listing.
D) it has "economic efficiency;" it is less time consuming and easier to select.
E) it has very little problem with sample frame error.

Question 7

In Canada a census is taken every five years of:

A) all households
B) 80% of the population
C) 1 in 5 households
D) 50% of the population
E) In Canada is a census is taken every 4 years.

Question 8

In practice, simple random sampling should be strongly considered:

A) if the population is small and can be numbered easily.
B) in telephone surveys where random digit dialing programs cannot be used to generate numbers.
C) when population units are stored in an electronic file allowing computer programs to run quota samples.
D) when a complex random sample proves too difficult for the researcher.
E) for underdeveloped countries only.

Question 9

Simple random sampling is NOT a wise choice when you have:

A) a large population.
B) a small population.
C) a sample frame in electronic format.
D) a large population that is not in electronic format.
E) a small population that is not in electronic format.

Question 10

Which of the following may be used to overcome the problems of unlisted numbers, "Do Not Call" lists, and population members without land lines?

A) systematic sampling
B) plus-one random digit dialing
C) CATI systems
D) random digit dialing
E) an online phone directory

Question 11

If we define our population as all households in the city of Montreal, Quebec, and we use the Montreal telephone directory from which to draw our sample, we would likely have:

A) a survey with sample frame error
B) a representative survey
C) a survey containing error
D) a survey with a poorly defined master list
E) a census

Question 12

Using a table of random numbers to draw a simple random sample requires that every member of the ________ be uniquely identified (i.e., numbered).

A) population
B) sample
C) numbers
D) Table
E) sample unit

Question 13

Which of the following statements is NOT true with respect to using a nonprobability method?

A) the selection technique is subjective
B) there is diminished representativeness
C) the population size is known
D) it is inherently biased
E) it is faster, takes less energy, and easier than a probability method

Question 14

An accounting of everyone in the population is known as:

A) a population
B) a sample
C) a sample unit
D) a census
E) comprehensive accounting

Question 15

Calculation of the "skip interval" is important in which sampling plan?

A) simple random sample
B) systematic sample
C) "skip" sample
D) cluster sample
E) interval sample

Question 16

A subset of the population that should represent the entire group, is known as a:

A) population
B) sample unit
C) census
D) sample
E) population set

Question 17

An entire group under study, as specified by the objectives of the research project, is known as the:

A) population
B) sample
C) sample unit
D) census
E) study group

Question 18

Which of the following statements does NOT support the concept of the "power of a sample?"

A) The energy required to perform the study will not be justified by the findings
B) The cost of a census outweighs the benefits of the results
C) The amount of time required to do a census is not available
D) A census is always preferred over a sample
E) Sample findings can be generalized to the population.

Question 19

A master list of all the members of the population is known as the:

A) sample list
B) population master list
C) master frame
D) sample frame
E) population frame

Question 20

Which of the following statements would NOT apply to the accuracy of a sample?

A) accuracy is defined as the amount of sample error due to the size of the sample
B) sample findings can be generalized to the population with a +x% approximation
C) as sample size increases, sample error decreases
D) large gains in accuracy occur all the way to a sample size of 10,000
E) "e" represents the desired accuracy for a sample

Question 21

Which of the following does the textbook note as the proper way to calculate sample size?

A) using a percentage of population formula
B) using the price-value formula
C) using a 1:10 ratio on sampling frame
D) using the "100" for local study; "1,000" for national study approach
E) using the confidence interval formula

Question 22

Tata Motors of India is marketing a new vehicle that retails for only $2,200. The vehicle will carry two persons and has a body made of fiberglass. It is designed in component parts so that if a part is broken, you can easily remove the part and replace it with a new one ordered from Tata. Tata realizes that it will take some time for countries to allow the small vehicle on public roads due to the varying safety requirements. However, Tata sees an immediate market among business firms who need inexpensive yet reliable vehicles to transport personnel around large manufacturing or warehousing facilities. One Tata manager stated: "Ninety percent of the time, company cars are used to transport only one or two persons and much of their travel is confined to the plant premises." "The new Tata vehicle will not replace the large company cars but can reduce the number of company cars a firm must buy by a substantial amount, thus saving tremendous amounts of money." Executives at Tata are interested in a sales estimate in Great Britain, their first targeted market outside of India. They will construct a sales forecast based upon a survey of companies and they know that demand will vary substantially, depending on the size of the company. Small firms will not want any vehicles, medium-sized firms may want about 5 or 10 vehicles, and large firms may want 20 to 100 vehicles. Secondary data is available that allows Tata to identify all firms in Great Britain and to know the size of the firm. If a survey is conducted to predict demand for the new Tata vehicle among business firms, which of the following sampling methods would be most appropriate?

A) simple random sample
B) judgment sample
C) stratified sample
D) cluster, area sample
E) systematic sample

Question 23

Eddie Livingston is president of Community Credit, a credit union with several locations. Eddie has been exploring the impact of service satisfaction with financial performance and is convinced that he can improve the credit union's returns if he can improve customer satisfaction. He has been contemplating a proposal from Re$earch Inc., a research firm that specializes in the financial services industry, to begin a program of improving customer satisfaction. Tanner has recommended a survey of customers to establish gaps in service as perceived by the customers. Eddie knows that the credit union has a list of all the customers and that this information is on an electronic database complete with mailing addresses and, for those having Internet service, email addresses. At the next meeting, Eddie expresses concern that sending a questionnaire to all bank customers is an inconvenience to them and he doesn't want to negatively impact customer satisfaction. The researchers from Re$earch assure Eddie that they can get the needed information for as few as a couple of hundred customers and that the results will be representative of all his credit union customers. Which of the following sample methods would most likely be appropriate?

A) simple random sample
B) judgment sample
C) stratified sample
D) cluster, area sample
E) systematic sample

Question 24

Unfortunately, many managers falsely believe that:

A) sample size is related to proper data analysis.
B) sample size is related to the representativeness of the sample.
C) sample size is determined by computer programs.
D) sample size is an irrelevant "statistical" technicality issue.
E) sample size is related to the level of accuracy desired.

Question 25

Now is NOT an ethical consideration in surveys using cellphones?

A) cellphone surveys are inherently unsafe
B) cellphone surveys are have the same ethical considerations as landline surveys
C) cellphone surveys are unevenly expensive for responses
D) most cellphone surveys are not brief
E) cellphone users are disproportionately nonadults

Question 26

If we were to graph the relationship of sample size (x-axis) to sample accuracy (y-axis), we would notice that:

A) There is a linear relationship between size and accuracy.
B) Accuracy increases quickly, up to about sample size 500, and then accuracy levels off with relatively small gains made even when sample size is increased to as much as 2,000.
C) Accuracy increases quickly, up to about sample size 5,000, and then accuracy levels off with relatively small gains made even when sample size is increased to as much as 200,000.
D) Accuracy increases quickly, up to about sample size 50, and then accuracy levels off with relatively small gains made even when sample size is increased to as much as 100.
E) We cannot graph just sample size and accuracy because we must also include the level of confidence and the variability within the sample data.

Question 27

Which of the following would be most helpful in dividing the sample into different strata?

A) a basis that will result in like responses across strata
B) a basis that will result in different responses across strata
C) a basis that is easy to identify
D) a basis that uses some surrogate indicator of identification such as SIC/NAICS codes
E) a basis that is the least expensive

Question 28

The purpose of the weighted average in stratified sampling is:

A) to provide an overall sample average that represents the true distribution of the population.
B) to provide more weight to those strata whose averages are the lowest.
C) to provide more weight to those strata whose averages are the highest.
D) to provide an overall sample average that represents the majority of the strata.
E) to provide more weight to those strata that are more important to society.

Question 29

Leslie Loewen is an entrepreneur with a small business in Steinbach, Manitoba. Working with a local engineer/inventor, Leslie has developed a new cooking device that she thinks will revolutionize cooking. The device is a small oven that is portable and uses a gas injection system to cook meals in a fraction of the time taken in a normal oven. The new system creates a very high temperature and the gas jets are located 360 degrees around the food to be cooked, thus ensuring that the food is cooked equally on all sides. Leslie and the engineer applied for a patent and then immediately sought a relationship with a large manufacturer to produce and distribute the new oven. To her surprise, when she demonstrated it to the top three manufacturers, they all had the same reaction: "We are very interested in this new invention but we would like to see some consumer research that tells us what consumers think about the device." "Will they think the temperature is too high and represents a safety issue?" "Do they really think that a roast cooked in 6 minutes will taste the same as one roasted for 2 hours?" "How much, if any, will they be willing to pay for the added convenience of time savings?" Leslie sought the services of Prairie Research Inc. (PRI) was an established research firm in the city and they recommended that they use the downtown mall in order to conduct some research that allowed consumers to use the device and taste the food cooked in the device. Leslie agreed but was concerned about the types of persons in the shopping mall. "They really won't represent our area since they will likely be mostly female and they will have higher incomes than the general population." PRI assured Leslie that this could be overcome by using which of the following sampling methods?

A) quota sample
B) purposive sample
C) stratified sample
D) representative sample
E) systematic sample

Question 30

The sample size determines:

A) representativeness
B) accuracy
C) representativeness and accuracy
D) the population statistic value
E) the mean generated from the sample statistic

Question 31

If a population were not distributed symmetrically, you would use:

A) simple random sampling.
B) systematic sampling.
C) cluster sampling.
D) stratified sampling.
E) unbalanced sampling.

Question 32

When website visitors are selected at random and asked to participate in a survey, this is an example of:

A) random online intercept sampling using simple random sampling.
B) nonrandom intercept sampling.
C) online panel sampling.
D) random online intercept sampling using systematic sampling.
E) simple random sampling.

Question 33

Snowball sampling is another name for:

A) referral sampling.
B) quota sampling.
C) convenience sampling.
D) rolling sampling.
E) simple random sample.

Question 34

Incidence rate refers to:

A) the percent of individuals in the sample who qualify to take the survey.
B) the percent of people who qualify as members of the sample frame error.
C) the percent of people not on a list who qualify as members of the sample frame error.
D) the percent of people who have been previously sampled.
E) the percent of mistakes made in sampling.

Question 35

A sampling method that separates the population into different subgroups, and then samples all of these subgroups, is called:

A) stratified sampling.
B) area sampling.
C) cluster sampling.
D) simple sampling.
E) comprehensive sampling.

Question 36

An "educated guess" as to who should represent the population is required for:

A) convenience samples.
B) judment samples.
C) quota samples.
D) referral samples.
E) hypothetical samples.

Question 37

Nonresponse refers to:

A) the number of questions that are not answered in a survey.
B) the failures by qualified respondents to take part in the survey.
C) the number of people in the population that were not asked to respond.
D) the phone numbers called during plus-one dialing that are not true phone numbers.
E) the percent of individuals in the sample who do not qualify to take the survey.

Question 38

Sampling a population in a geographical area using area sampling is a form of:

A) systematic, geographic sampling.
B) simple random sampling.
C) nonprobability sampling.
D) cluster sampling.
E) geo-group sampling.

Question 39

One of the nonprobability methods used for sampling is:

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

Question 40

If a random start is used in terms of visitors to a website, and then a skip interval is used to skip to the next visitor to ask to participate in a survey, this is an example of:

A) random online intercept sampling using simple random sampling.
B) online panel sampling.
C) statistical efficiency in online sampling.
D) random online intercept sampling using systematic sampling.
E) skip online sampling.

Question 41

A sample frame is a master list of all the members in the population.

Question 42

Consider that we have nominal data and the responses are "Yes" or "No" to the question: "The next time you order pizza, will you order Domino's?" Which of the following sets of responses shows the MOST variability?

A) 99 percent say "Yes" and 1 percent say "No"
B) 80 percent say "Yes" and 20 percent say "No"
C) 70 percent say "Yes" and 30 percent say "No"
D) 60 percent say "Yes" and 40 percent say "No"
E) 51 percent say "Yes" and 49 percent say "No"

Question 43

If we know the level of confidence, variability estimates, and the desired accuracy, there is a formula that allows us to determine:

A) z
B) the size of the sample
C) the representativeness of the sample
D) p or q
E) e

Question 44

To cope with the realities of incidence rate and nonresponse, researchers should use:

A) the sample adjustment formula.
B) always increase their sample size by 10%.
C) restrict themselves to the calculated sample size from the confidence interval formula.
D) ensure the sample size is always above 500.
E) ensure p and q are always equal to 50%.

Question 45

Which of the following is the best definition of variability?

A) it is the amount of dispersion in a data set containing interval or nominal data
B) the difference between scores in the present sample and scores in a previous sample
C) the amount of dissimilarity in ordinal data
D) amount of dissimilarity (or similarity) in respondents' answers to a particular question
E) the amount of responses in one respondent's answers to a particular survey question

Question 46

A census is defined as a subset of the population that somehow represents that entire group.

Question 47

If we assume the "highest" amount of variability when estimating p and q, then p and q are ____ and ____ respectively.

A) 50; 50
B) 1; 99
C) 0; 100
D) 1.96; 1.96
E) 2.58; 2.58

Question 48

York University wanted to see how much students graduating for their university valued their education. Although the university wanted to know who all students felt on average, the president wanted to be able to report to each of the Deans of the varying faculties. They would want to know if the responses varied depending on the degree the student obtained. This would help them with future plans by area of study. Given that the graduating classes per faculty varied greatly in size, what form of sampling would provide information to satisfy the president and the deans?

A) proportionate stratified sampling
B) judgment sampling
C) disproportionate stratified sampling
D) two-step area sampling
E) complex random sampling

Question 49

A population is defined as the entire group under study as specified by the objectives of the research project.

Question 50

Random digit dialing is an example in which simple random sampling is employed quite successfully.

Question 51

It is a researcher's responsibility to seek out a sample frame with the least amount of error at a reasonable cost.

Question 52

Nonprobability samples are those for which members of the population do not have a known chance of completing and turning in a survey.

Question 53

Marketing researchers make use of samples because obtaining information from every single person in a market is impractical.

Question 54

95 percent of the observations under the normal curve fall within ________ times the sample error.

A) + 1.64
B) + 1.96
C) + 2.58
D) + 0.95
E) + 1.95

Question 55

An amusement park owner is considering a survey to determine customer preferences for a new water ride. The owner and the researcher discuss the concept of the level of accuracy. The owner accepts a level of accuracy of + 5 percent. Assuming that the survey finds that 70 percent of the survey respondents indicate they want the ride, what does having a level of accuracy of + 5 percent accuracy actually mean?

A) that there will be a 5 percent chance that the owner will make the wrong decision as to whether not to build the new water ride
B) that the real percentage of the park's customers who prefer the new water ride falls between 0 and 5 percent
C) that there is a 95 percent chance that the owner will make the right decision as to whether or not to build the new water ride
D) that the real percentage of the park's customers who prefer the new water ride falls between 65 and 75 percent
E) that there is a 5 percent chance, + or -, that the owner will make the right decision

Question 56

With simple random sampling, the probability of being selected into the sample is found by dividing the population size by the sample size.

Question 57

Probability samples are those for which members of the population have a known chance of completing and actually turning in a survey.

Question 58

A packaged food company is looking at conducting enter the Canadian marketplace with its new line of frozen healthy after-school snacks. Before launching the product they want to determine what the best pricing strategy will be with their target market without the incurring the time or cost of a census. The research firm they hired suggested they subdivide the Canadian population into geographic areas. Given the diversity that exists across Canada, they suggested that they then select a random sample of the areas to ensure a representative sample. What form of sampling was the firm recommending?

A) eeographic sampling
B) random area sampling
C) two-step area sampling
D) stratified sampling
E) stratified random sampling

Question 59

Sampling error is defined as the difference between results obtained from a poll versus a sample survey.

Question 60

What three factors are needed to calculate sample size?

A) variability, desired accuracy, and level of confidence
B) variability, desired accuracy, and population size
C) accuracy, confidence level, and population size
D) accuracy, population size, and costs
E) variance, standard deviation, and dispersion

Question 61

In stratified sampling, subgroups are referred to as clusters.

Question 62

Due to the difficulties of obtaining responses from online respondents, many online research companies have developed panels of online respondents in order to ensure the use of probability sampling.

Question 63

Andy was a senior in college, majoring in marketing. He received a call to participate in a survey on behalf of a company that was targeting graduating seniors. At the end of the survey, Andy was asked for the name of a friend who was also a senior in marketing. This is an example of using a "snowball" sample.

Question 64

Although a judgment sample is highly subjective and therefore prone to much error, it is a quick, inexpensive, and acceptable technique.

Question 65

Mall-intercept companies often use convenience sampling to recruit respondents.

Question 66

Variability refers to how much respondents disagree in their answer to a question.

Question 67

Random online intercept sampling uses some form of random selection in order to ask visitors at websites to participate in surveys.

Question 68

A convenience sample may also be called a "quota sample."

Question 69

The skip interval used in systematic sampling is computed by dividing the population list size by the sample size.

Question 70

Instead of determining representativeness, the size of the sample affects the sample accuracy of the results.

Question 71

In stratified sampling, the population is separated into different subgroups, and then samples are taken from all of the subgroups.

Question 72

Sample size does not have to be "huge" in order to have reasonably accurate data. For example, samples that are 500 or less may provide reasonably accurate information.

Question 73

If the strata sample sizes are faithful to their relative sizes in the population, you have what is called a proportionate stratified sample design.

Question 74

Stratified samples are most appropriate when the population is known to be "skewed."

Question 75

In area sampling, the two-step approach is more costly than the one-step approach because more areas and time are involved.

Question 76

A retail store selects customers at random and gives them a card asking them to go to the store's Web site and complete a survey. This is known as invitation online sampling.

Question 77

The confidence interval formula for determining sample size applies the concepts of accuracy, variability, and confidence level to create determine sample size.

Question 78

In area sampling, the one-step approach is applied if the researcher believes that the various geographic areas (or clusters) are sufficiently identical.

Question 79

For random online intercept sampling, if the population is other than website visitors, the sample is merely an online convenience sample.

Question 80

Systematic sampling has the potential to create a sample that is almost identical in quality to samples created from simple random sampling.