Research Methods Chapter #7
What are four ways of selecting a biased sample of a population of interest? Which subsets are more likely to be selected in each case?
1. Convenience Sampling- uses samples that are chosen merely on the basis of who is easy to access 2. Purposive Sampling- studying only one kind of people 3. Snowball Sampling- starting off with two participants and having them recruit their own subjects (acquaintances) 4. Quota Sampling- wanting equal proportions of each population
quota sampling
A biased sampling technique in which a researcher identifies subsets of the population of interest, sets a target number for each category in the sample, and nonrandomly selects individuals within each category until the quotas are filled.
purposive sampling
A biased sampling technique in which only certain kinds of people are included in a sample.
stratified random sampling
A form of probability sampling; a random sampling technique in which the researcher identifies particular demographic categories of interest and then randomly selects individuals within each category.
oversampling
A form of probability sampling; a variation of stratified random sampling in which the researcher intentionally overrepresents one or more groups.
self-selection
A form of sampling bias that occurs when a sample contains only people who volunteer to participate.
population
A larger group from which a sample is drawn; the group to which a study's conclusions are intended to be applied. Also called population of interest.
cluster sampling
A probability sampling technique in which clusters of participants within the population of interest are selected at random, followed by data collection from all individuals in each cluster.
systematic sampling
A probability sampling technique in which the researcher counts off members of a population to achieve a sample, using a randomly chosen interval (e.g., every nth person, where n is a randomly selected number).
multistage sampling
A probability sampling technique involving at least two stages: a random sample of clusters followed by a random sample of people within the selected clusters.
representative sample
A sample in which all members of the population of interest are equally likely to be included (usually through some random method), and therefore the results can generalize to the population of interest. Also called unbiased sample.
biased sample
A sample in which some members of the population of interest are systematically left out, and as a consequence, the results from the sample cannot generalize to the population of interest. Also called unrepresentative sample.
census
A set of observations that contains all members of the population of interest.
snowball sampling
A variation on purposive sampling, a biased sampling technique in which participants are asked to recommend acquaintances for the study.
In your own words, describe the difference between random sampling and random assignment
Random assignment is only used in experimental designs. (treatment group and comparison group) Random assignment enhances internal Random sampling is where researchers create a sample using some random method (i.e drawing names from a hat). Random sampling also uses external validity
Why are convenience, purposive, snowball, and quota sampling not examples of representative sampling?
You're not making a random sample with any of these.
What sample size is often cited as the optimal balance between accuracy and effort? a. 1,000 b. 2,000 c. 100 d. 500
a. 1,000 FEEDBACK: Larger Samples Are Not More Representative — A random sample of size of 1,000 allows the generalization to a population with an error margin of plus or minus 3 percent. Making the effort to double the sample size to 2,000 only gains 1 percent on the error margin, which isn't generally considered worth the effort.
Externally valid samples are most important for some research questions than for others. For which of the following research questions will it be most important to use an externally valid sampling technique? a. Estimating the proportion of U.S. teens who are depressed b. Testing the association between depression and illegal drug use in U.S. teens c. Testing the effectiveness of support groups for teens with depression
a. Estimating the proportion of U.S. teens who are depressed
A political research center obtains a list of phone numbers for all registered voters in Texas and uses a random number generator to select 1,000 of the phone numbers to call. They ask each voter which gubernatorial candidate they plan to vote for in the upcoming election. What is the population of interest that the research center wants to generalize to? a. all registered voters in Texas b. all Texans c. all Americans d. all of the people likely to vote for the Republican candidate for governor
a. all registered voters in Texas
Which of the following is considered a biased sampling method? a. convenience sampling b. simple random sampling c. cluster sampling d. stratified random sampling
a. convenience sampling FEEDBACK: Convenience Sampling — A convenience sample is chosen on the basis of who is easy to access. This is not typically representative of the entire population from whom the researchers wish to generalize.
Beth is working on a research study focused on attention span in children. Among the participants, the group of 11-year-old boys is underrepresented. Beth asks her 11-year-old brother to distribute flyers about participation in the study to his male classmates and soccer team. What type of sampling is this? a. random b. self-selected c. snowball d. multistage
c. snowball FEEDBACK: Settling for an Unrepresentative Sample: Biased Sampling Techniques — Beth is finding a member of a group that is rare (for her sample) and asking that member to recruit others for the sample.
random assignment
The use of a random method (e.g., flipping a coin) to assign participants into different experimental groups.
convenience sampling
Choosing a sample based on those who are easiest to access and readily available; a biased sampling technique.
What are five techniques for selecting a representative sample of a population of interest? Where does randomness enter into each of these five selection processes?
1. Simple Random Sampling: i.e using computer programs that generate numbers that are random 2. Cluster Sampling and Multistage Sampling: i.e researcher wanting to randomly sample college students in the state of Pennsylvania, for example, he could start with a list of colleges (clusters), randomly select five of those colleges (clusters) and then include every student from each of those five colleges in the sample 3. Stratified Random Sampling: i.e researchers might want to be sure their sample of 1,000 Canadians include people of South Asian descent in the same proportion as in the Canadian population (which is 4%). They might have two categories (strata) in their population: South Asian Canadians and other Canadians. In a sample of 1,000 they would make sure to include at least 40 members of the category of interest (South Asian Canadians). All 1,000 members of both Caterogies are selected at random. 4. Oversampling: the oversampling of a population (refer to above) 5. Systematic Sampling: using numbers to systematically choose (counting off in class)
simple random sampling
The most basic form of probability sampling, in which the sample is chosen completely at random from the population of interest (e.g., drawing names out of a hat).
probability sampling
The process of drawing a sample from a population of interest in such a way that each member of the population has an equal chance of being included in the sample, usually via random selection. Also called random sampling.
sample
The group of people, animals, or cases used in a study; a subset of the population of interest.
Mr. Stratford is the president of a national organization of lesbian, bisexual, gay, and transgender people in the United States. He wants to survey 1,000 members of his organization about the position they want the organization to take on several political issues. He knows that transgender people make up only 5 percent of his organization, but he wants to make sure that their views are accurately represented. He decides that he will randomly sample 100 transgender members and then adjust the final results so that transgender people are weighted to their actual proportion in the organization. What type of sampling is Mr. Stratford using? a. oversampling b. quota sampling c. cluster sampling d. snowball sampling
a. oversampling FEEDBACK: Oversampling — Oversampling is when the researcher intentionally overrepresents one or more groups.
A ________ is the entire set of people in which the researchers are interested. a. population b. quota sample c. biased sample d. representative sample
a. population FEEDBACK: Populations and Samples — A population is the entire set of people or products in which you are interested.
Dr. Lawrence is the director of Counseling Services at her university. She is planning to conduct a survey of 100 students at the university to see how aware they are of the counseling services that are offered at the university. She wants the proportion of males and females in her sample to reflect the proportion in the university as a whole (55 percent female and 45 percent male). Dr. Lawrence plans to stand in the Student Union and ask people to participate until she has given the survey to 55 females and 45 males. What type of sampling method is Dr. Lawrence going to use? a. quota sampling b. stratified random sampling c. cluster sampling d. multi-stage sampling
a. quota sampling
The student government at a college is interested in determining how important intercollegiate sports are to the students there. Since all students have e-mail accounts, they are able to send a survey to all the students. About 50 percent of the students respond. Which is the most likely bias in this sample? a. self-selection bias b. a bias from contacting only those the student government could easily contact c. convenience sampling bias d. random sampling bias
a. self-selection bias FEEDBACK: When Is a Sample Biased? — There is no way to know if the 50 percent of the students who responded were representative of the entire student body or the reasons they chose to answer.
A sample is always __________ a population. a. smaller than b. unrelated to c. the same size as d. larger than
a. smaller than FEEDBACK: Populations and Samples — A population is the entire set of people a researcher is interested in, and a sample is a smaller set taken from that population.
The directors of an annual community concert want to find the musical preferences of the audience. The ushers place a survey card on every sixth seat beginning with the second seat (2 and 6 were chosen from a random number table). All of the cards are returned as the audience leaves. Which type of sampling is being used? a. systematic sampling b. cluster sampling c. multistage sampling d. stratified random sampling
a. systematic sampling FEEDBACK: Obtaining a Representative Sample: Probability Sampling Techniques — This is systematic sampling as it involves sampling every nth member of the audience, starting at a random point, where n is chosen at random also.
Mr. Stratford is the president of a national organization of lesbian, bisexual, gay, and transgender people in the United States. He wants to survey 1,000 members of his organization about the position they want the organization to take on several political issues. He knows that transgender people make up only 5 percent of his organization, but he wants to make sure that their views are accurately represented. He decides that he will randomly sample 100 transgender members and then adjust the final results so that transgender people are weighted to their actual proportion in the organization. Is Mr. Stratford collecting a representative sample? a. Yes, because 1,000 people is enough to make a representative sample. b. Yes, because the transgender people in the final sample were sampled randomly from the population of transgender people in the organization. c. No, because straight people are not included in the sample. d. No, because the transgender people are over-represented in the final sample.
b. Yes, because the transgender people in the final sample were sampled randomly from the population of transgender people in the organization. FEEDBACK: Oversampling — Oversampling is a variation of stratified random sampling. Since people are randomly selected from the population, it is a representative sample.
Which sample would be most likely to represent the population of American teenagers? a. a purposive sample of 1,250 U.S. teenagers b. a cluster sampling of 1,000 teenagers from around the United States c. a convenience sample of 1,200 U.S. teenagers d. a snowball sampling of 1,500 teenagers from around the United States
b. a cluster sampling of 1,000 teenagers from around the United States FEEDBACK: Figure 7.5 — Cluster sampling will create a representative sample, which makes this the best option. For making a representative sample, the sample size is not as important as the sampling method.
Dr. Rhodes is interested in how differing levels of light affect how people perceive color. He finds participants for this research study by making an announcement in several psychology classes at his university. What kind of sampling method is Dr. Rhodes using? a. systematic sampling b. convenience sampling c. snowball sampling d. cluster sampling
b. convenience sampling FEEDBACK: Ways to Get a Biased Sample — Dr. Rhodes is using a sample of people who are readily available to participate — a convenience sample.
Dr. Jennings is doing a study on the experience of being a racial minority on a college campus. He goes to the Asian Student Association, Black Student Union, and Hispanic Student Group on his campus to recruit participants for his study. Dr. Jennings only includes Asians, African-Americans, and Hispanic participants in his study. What type of sampling is Dr. Jennings using? a. quota sampling b. purposive sampling c. cluster sampling d. systematic sampling
b. purposive sampling FEEDBACK: Purposive Sampling — Purposive sampling is when only a certain kind of people are sampled and when those people are sampled in a non-random way.
Which of the following is most important for enhancing external validity? a. a large sample size b. random sampling c. using measures that are valid and reliable d. random assignment
b. random sampling FEEDBACK: Random Sampling Versus Random Assignment — Random sampling enhances external validity, and random sampling enhances internal validity.
A college administrator knows that 70 percent of the students at his college are from out of state, so he decides to make sure that he includes 70 out-of-state students and 30 in-state students in his survey about admission practices at the college. He has a list of all of the out-of-state and all of the in-state students currently enrolled at the college. He randomly selects 70 students from the out-of-state list and 30 students from the in-state list. What sampling method is he using? a. multi-stage sampling b. stratified random sampling c. cluster sampling d. quota sampling
b. stratified random sampling FEEDBACK: Stratified Random Sampling — In stratified random sampling, the researcher selects particular demographic categories on purpose and then randomly selects individuals within each of the categories.
Which of the following is considered a representative sampling method? a. convenience sampling b. systematic sampling c. snowball sampling d. self-selected sampling
b. systematic sampling FEEDBACK: Systematic Sampling — Systematic sampling is a representative sampling method of sampling that involves selecting two random numbers (i.e., 2 and 4). The first number tells you where to start sampling (the second person) and the second number tells you how often to sample (every fourth person).
Which of the following samples is most likely to generalize to its population of interest? a. A convenience sample of 12,000 b. A quota sample of 120 c. A cluster sample of 120 d. A self-selected sample of 120,000
c. A cluster sample of 120
A researcher's population of interest is New York City dog owners. Which of the following samples is most likely to generalize to this population of interest? a. A sample of 25 dog owners visiting dog-friendly New York City parks b. A sample of 25 dog owners who have appointments for their dogs at veterinarians in the New York City area c. A sample of 25 dog owners selected at random from New York City pet registration records d. A sample of 25 dog owners who regularly log into the nycdog.org website
c. A sample of 25 dog owners selected at random from New York City pet registration records
Dr. Lawrence is the director of Counseling Services at her university. She is planning to conduct a survey of 100 students at the university to see how aware they are of the counseling services that are offered at the university. She wants the proportion of males and females in her sample to reflect the proportion in the university as a whole (55 percent female and 45 percent male). Dr. Lawrence plans to stand in the Student Union and ask people to participate until she has given the survey to 55 females and 45 males. Is Dr. Lawrence collecting a representative sample? a. Yes, because the sample includes a representative proportion of males and females. b. No, because 100 people is not enough for a representative sample. c. No, because the participants are selected nonrandomly. d. Yes, because all of the students in her sample attend her university.
c. No, because the participants are selected non randomly. FEEDBACK: Quota Sampling — In quota sampling participants are chosen nonrandomly so it is not a representative sampling method.
Which sample would be most likely to represent the population of American teenagers? a. a snowball sampling of 1,500 teenagers from around the United States b. a convenience sample of 1,200 U.S. teenagers c. a cluster sampling of 1,000 teenagers from around the United States d. a purposive sample of 1,250 U.S. teenagers
c. a cluster sampling of 1,000 teenagers from around the United States
What kind of sample is best for external validity? a. the largest sample possible b. a sample that includes the majority of the population c. a sample where each member of the population has an equal chance of being selected d. a sample that can be collected as quickly as possible
c. a sample where each member of the population has an equal chance of being selected FEEDBACK: Generalizability: Does the Sample Represent the Population? — In terms of external validity, the best sample is a representative sample — one in which every member of the population has an equal chance of being selected.
Which of the following is most important for enhancing external validity? a. using measures that are valid and reliable b. a large sample size c. random sampling d. random assignment
c. random sampling
________ is when you study every member of a population. a. A biased sample b. A representative sample c. Oversampling d. A census
d. A census FEEDBACK: Populations and Samples — A census is when every member of a population is studied.
Which of the following four terms does not belong? a. Generalizable sample b. Externally valid sample c. Representative sample d. Biased sample
d. Biased sample
Dr. Rhodes is interested in how differing levels of light affect how people perceive color. He finds participants for this research study by making an announcement in several psychology classes at his university. Should Dr. Rhodes be concerned about using this sampling method? a. No, because his sample is representative of college students. b. Yes, because his sample will not be representative of people in general. c. Yes, because external validity is very important for the type of claim he is making. d. No, because external validity probably doesn't matter for the type of claim he is making.
d. No, because external validity probably doesn't matter for the type of claim he is making. FEEDBACK: When a Representative Sample Is Not the Top Priority — Since Dr. Rhodes is not making a frequency claim, external validity is not a priority. Therefore, he should not be concerned about using a convenience sample.
A political research center obtains a list of phone numbers for all registered voters in Texas and uses a random number generator to select 1,000 of the phone numbers to call. They ask each voter which gubernatorial candidate they plan to vote for in the upcoming election. What sampling method is being used? a. multistage sampling b. systematic sampling c. stratified random sampling d. simple random sampling
d. simple random sampling FEEDBACK: Simple Random Sampling — The research center has a list of the entire population, and they are randomly sampling from that population.
A political research center obtains a list of phone numbers for all registered voters in Texas and uses a random number generator to select 1,000 of the phone numbers to call. They ask each voter which gubernatorial candidate they plan to vote for in the upcoming election. What is the population of interest that the research center wants to generalize to? a. all Americans b. all Texans c. all of the people likely to vote for the Republican candidate for governor d. all registered voters in Texas
d. all registered voters in Texas FEEDBACK: Simple Random Sampling — The sample will be representative of the population that it was sampled from — all registered voters in Texas.
The superintendent of schools in a small town in Ohio made a lot of policy changes to the way school administration worked in his district. A researcher at a nearby university wanted to look at what teachers in his district thought about the changes. The researcher made a list of all of the schools in the district and used a random number generator to select a sample of five schools from the district. Then the researcher interviewed every teacher at each of those five schools. What sampling method did the researcher use? a. simple random sampling b. purposive sampling c. systematic sampling d. cluster sampling
d. cluster sampling FEEDBACK: Cluster Sampling and Multistage Sampling — In cluster sampling, clusters of participants (schools) within a population of interest (the school district) are randomly selected, and then all individuals in each selected cluster are included in the study.
Dr. Rhodes is interested in how differing levels of light affect how people perceive color. He finds participants for this research study by making an announcement in several psychology classes at his university. What kind of sampling method is Dr. Rhodes using? a. cluster sampling b. systematic sampling c. snowball sampling d. convenience sampling
d. convenience sampling
Typically, in which type of claim is it most important to have a random sample? a. anecdotal b. causal c. association d. frequency
d. frequency FEEDBACK: When a Representative Sample is Not a Top Priority — Random sampling is linked to external validity and that is often the main concern in frequency claims. Associations and causes can often be determined without random samples.
The campus safety committee has asked Professor Ibrahim to study bicycling on his campus. He trains two observers and has them observe the number of cyclists and their safety at various points around campus. He selects ten observation locations at random from the places bicycles can be ridden on campus and five one-hour spans of time at random from the daylight hours for each place. He has his observers make observations at each of the ten places for each of the five time spans. What type of sampling is he using? a. simple random sampling b. systematic sampling c. stratified random sampling d. multistage sampling
d. multistage sampling FEEDBACK: Obtaining a Representative Sample: Probability Sampling Techniques — He has chosen a random set of places (clusters) and a random set of times within those places, so it is a multi-stage sampling procedure.
Dr. Lawrence is the director of Counseling Services at her university. She is planning to conduct a survey of 100 students at the university to see how aware they are of the counseling services that are offered at the university. She wants the proportion of males and females in her sample to reflect the proportion in the university as a whole (55 percent female and 45 percent male). Dr. Lawrence plans to stand in the Student Union and ask people to participate until she has given the survey to 55 females and 45 males. What type of sampling method is Dr. Lawrence going to use? a. multi-stage sampling b. stratified random sampling c. cluster sampling d. quota sampling
d. quota sampling FEEDBACK: Quota Sampling — In quota sampling the researcher identifies subsets of the population of interest and then sets a target number for each category in the sample.
