Chapter 9: Selecting the Sample Flashcards
Define: Population
Population is defined as the entire group under study as specified by the objective of the research project.
_______ tend to have a less specific definition of the population than do researchers, because they use it in a more general way.
Managers tend to have a less specific definition of the population than do researchers, because they use it in a more general way.
Define: Census
Census is defined as an accounting of the complete population.
True or False: Conducting a census is a practical way to collect data.
False: Conducting a census is a very impractical way to collect data. It is virtually impossible to obtain information from every single US household
Define: Sample
Sample is defined as a subset of the population that suitably represents that entire group.
Define: Sample Unit
Sample Unit is defined as the basic level of investigation.
The sample is a ______ of the population, and the sample unit pertains to the __________.
The sample is a subset of the population, and the sample unit pertains to the basic level of investigation.
Define: Sample Frame
A sample frame is a master source of sample units in the population.
True or False: The sample frame does not always correspond perfectly to the sample.
True: The sample frame does not always correspond perfectly to the sample.
Define: Sample Frame Error
Sample frame error is defined as the degree to which the sample frame fails to account for all of the population
What is a good way to envision sample frame error?
A good way to envision sample frame error is by comparing the list with the population and seeing to what degree the list adequately matches the targeted population.
Has the booming social media marketing phenomenon given marketing researchers an easier task or harder task?
The booming social media marketing phenomenon has given marketing researchers immense challenges because users of social media are difficult to identify.
Define: Sampling Error
Sampling error is any error in a survey that occurs because a sample is used.
Sampling error is caused by _____ factors.
Sampling error is caused by two factors: a) the method of sample selection, which includes sample frame error and b) the size of the sample
Explain two general reasons why a sample is almost always more desirable than a census.
Taking a sample is less costly and more practical, making a sample more desirable than a census. The typical researcher cannot analyze the huge amounts of data generated by a census.
Before researchers consider the size of computer or tabulation equipment to be used, they must consider the various _______ involved in handling the questionnaires and responses and transferring these responses into computer files.
Before researchers consider the size of computer or tabulation equipment to be used, they must consider the various data preparation procedures involved in handling the questionnaires or responses and transferring these responses into computer files.
All sample designs fall into one of two categories….
All sample designs fall into one of two categories: probability or nonprobability.
Define: Probability Samples
Probability samples are defined as samples in which members of the population have a known chance (probability) of being selected into the sample.
Define: Nonprobability Samples
Non-probability samples are defined as samples where the chances (probability) of selecting members from the population into the sample are unknown.
Unfortunately, the terms known and unknown are misleading… why?
The terms known and unknown are misleading; to calculate a precise probability, one would need to know the exact size of the population , and it is impossible to known the exact size of the population in most marketing research studies.
True or false: In most cases, the population size is known and stable enough to be associated with an exact number
False. In most cases, the population size is unknown and is not stable enough to be associated with an exact number.
Is the probability value calculated?
In reality, the probability value is never really calculated, but we are assured by the sample method that the chances of any one population member being selected into the sample could be computed.
Is the nonprobability value calculated?
There is no way to determine the probability with nonprobability methods even if the population size is known because the selection technique is subjective.
Nonprobability sampling uses __________, whereas probability sampling does not.
Nonprobability sampling uses human intervention, whereas probability sampling does not.
Nonprobability sampling is sometimes called __________ because it is prone to human error and even subconscious biases.
Nonprobability sampling is sometimes called “haphazard sampling” because it is prone to human error and even subconscious biases.
Name the four probability sampling methods.
The four probability sampling methods are simple random sampling, systematic sampling, cluster sampling and stratified sampling.
Define Simple Random Sampling.
Simple random sampling is defined as the probability of being selected into the sample is equal for all members of the population
What is the formula for simple random sample selection probability?
probability of selection = sample size/population size
Define the Random Device Method
The random device method involves using an apparatus of some sort to ensure that every member of the population has the same chance of being selected into the sample .
What is a familiar example of the random device method?
A familiar example of the random device method is flipping a coin to decide heads or tails.
True or false: In every case, every member of the population has the same probability of being selected as every other member of that population in the random device method.
True. Using the random device method, every member of the population has the same probability of being selected into the sample in every case.
Define systematic sampling
Using a sample frame that lists members of the population, the researcher selects a random starting point for the first sample member. A constant skip interval is used to select every other sample member from the sample frame.
Does systematic sampling have the same end result as simple random sampling?
Yes, systematic sampling has the same end result as simple random sampling, but it is more efficient.
Define: Cluster Sampling
Cluster sampling is when the sample frame is divided into groups, called clusters, each of which must be considered to be similar to the others. The researcher randomly selects a few clusters and performs a census of each one (one stage) or randomly selects more clusters and takes samples from each one (two stage).
When is cluster sampling desirable?
Cluster sampling is desirable when highly similar clusters can be easily identified.
Define: Stratified Sampling
Stratified sampling is when the population is believed to have a skewed distribution for one or more of its distinguishing factors - the researcher identifies subpopulations in the sample frame called strata. A simple random sample is then taken of each stratum. Weighting procedures may be applied to estimate population values, such as the mean.
When is stratified sampling better suited?
Stratified sampling is better suited than other probability sampling methods for populations that are not distributed in a bell-shaped pattern.
Define: Blind Draw
An example of a blind draw is writing the name of every student on an index card, placing the cards in a container, shaking the container, and ask another person to draw the sample.
Define: Random Numbers
Random numbers are numbers whose chance nature is assured.
Why is simple random sampling appealing?
Simple random sampling is an appealing sampling method simply because it embodies the requirements necessary to obtain a probability sample and, therefore, to derive unbiased estimates of the population’ characteristics. Simple random sampling guarantees that every member of the population has an equal chance of being selected into the sample. Therefore, the resulting sample will be a valud representation of the population.
What are the disadvantages of using simple random sampling?
Some disadvantages of using simple random sampling is the necessity to predesignate each population member. Complete listings are sometimes incomplete or inaccurate listings of populations and contain sample frame error. If the sample frame does not exist electronically, it can be cumbersome to manually provide unique designations for each population member.
What are the two practical applications in which simple random sample designs are employed quite successfully.
The two practical applications in which simple random sampling designs are employed successfully are random digit dialing and computer based random samples.
Define: Random Digit Dialing (RDD)
Random digit dialing is used in telephone surveys to overcome the problems of unlisted and new telephone numbers.
Define: Plus-one Dialing Procedure
Plus-one dialing procedure is a convenient variation of random digit dialing, in which numbers are selected from a telephone directory and a digit, such as “1” is added to each number to determine which telephone number is then dialed.
Which types of companies have the greatest opportunity to use RDD and plus-one dialing procedure?
Companies with credit files, subscription lists, or marketing information systems have the greatest opportunity to use this approach.
Which type of sampling has fallen in popularity since computerized databases and generated random number features have become widely available?
Systematic sampling has fallen in popularity since computerized databases and generated random number features have become widely available.
When would systematic sampling be chosen over simple random sampling?
In the special case of a physical listing of a population, systematic sampling is often chosen over simple random sampling based primarily on the economic efficiency it represents.
True or False: To use systematic sampling, it is necessary to obtain a hard-copy listing of the population.
True. To use systematic sampling, it is necessary to obtain a hard-copy listing of the population.
Define: Skip Interval
A skip interval is calculated by dividing the number of names on the list by the sample size, as can be seen in the following formula:
Skip interval = population list size/sample size