Ch 2 Exam Reivew
Identify the following examples as either small-N or large-N designs.
small-N designs: - Researchers administer 50 trials of a memory task to a patient with anterograde amnesia. - Researchers give patients with dissociative identity disorder different treatments; then they take the treatments away to see how effective they were. large-N designs: - Researchers compare the average performance of 15 early-decision college students to the average performance of 15 typical students. - Forty participants complete 25 trials of a "go/no-go" task designed to measure decision making.
Match each term to the correct description.
- counterbalancing: presenting the levels of the independent variable to participants in different sequences - manipulation check: an extra dependent variable that can be used to help researchers evaluate how well an experimental manipulation worked - replication: conducting multiple studies on the same question to get more precise estimates - pilot study: study completed separately from the main study to confirm the effectiveness of a manipulation
Fill in the blanks to complete the passage about an example of a study with a small-N design.
A drought in California created the opportunity for a study on the effectiveness of fines in promoting water conservation (Agras et al., 1980). Researchers studied three comparable California cities—two that imposed fines at different times and a third that did not impose fines at all. Researchers used the water consumption data from the 3 years before the onset of the fines as a baseline and then gathered subsequent consumption data through the end of the drought. They assessed the effectiveness of fines by examining water consumption the month following the end of the drought. In regard to the monitoring of water consumption, this study was a(n) multiple-baseline design. In the study, researchers capitalized on real-life circumstances to study water conservation, which demonstrates the prioritization of external validity.
Fill in the blanks to complete the passage about an example of a quasi-experiment.
After a new city law goes into effect, a restaurant chain begins displaying the nutrition information for its menu items. The restaurant owner records the sales of the 15 highest-calorie menu items on three occasions: once a month before the change in menu display, once the week of the change, and once a month after the change. The owner observes that the sale of the high-calorie menu items dropped, while overall sales remained steady. This study uses a(n) interrupted time-series design. The quasi-independent variable is menu labeling and the dependent variable is sales of high-calorie menu items.
Fill in the blanks to complete the passage about the process of compiling the statistical results of several studies.
Besides replication, another way to increase the strength or significance of a particular finding is to review the scientific literature about that finding and conduct a study that compiles the results of similar studies into one statistic. This type of study is called a(n) meta-analysis, and the statistic typically calculated in it is a(n) effect size.
Fill in the blanks to complete the passage about experiments that use different participants for the different conditions.
Experiments that compare different participants who are placed in different conditions are known as independent-groups designs. There are two basic forms of this design. The first is the posttest-only design, in which participants are tested on the dependent variable only once after the manipulation. The second is the pretest/prottest design, in which participants are tested on the dependent variable before and after the manipulation.
Fill in the blanks to complete the passage about an example of a study with a null effect
Frances decides to conduct a second study on concreteness and memory in a laboratory setting. She creates a list of 12 concrete items (e.g., pencil and table) and a list of 12 abstract items (e.g., justice and freedom). Participants view each word for 1 second and then recall them in order. The study shows a null effect, and almost all the participants remembered all the words on both lists. Frances' study has a null effect likely because of a ceiling effect, which led to not enough between-groups variability. To eliminate this problem, Frances should consider making the task more difficult.
Identify whether each example is either a quasi-experiment or a true experiment.
Quasi-experiment: - Researchers examine bad classroom behavior following recess at a school that has one recess period versus another school that has two. - Researchers track sick days taken at a company after each occasion that the company assigns mandatory overtime. - Researchers look for differences in texting behavior between baby boomers and members of Generation Z. true experiment: - Researchers randomly assign volunteers for a video game study to play either a violent game or a nonviolent game for 6 months. - Researchers randomly assign two separate groups to complete two different mindfulness strategies to see which strategy results in less stress.
Fill in the blanks to complete the passage about studies conducted in the real world.
Some studies are conducted in a real-world situation, or a(n) field setting. These studies are often in ecological validity: they are likely to be encountered in everyday life. Even though some researchers believe real-world settings are superior, many others claim that laboratory studies can have experimental realism -- in other words, even though the study is taking place in a controlled environment, it still evokes behavior and emotions that are realistic.
Fill in the blanks to complete the passage about how researchers prioritize validities when making causal claims.
To establish a causal claim, researchers often prioritize internal validity over external validity. While researchers hope to generalize their findings to other people and settings, in experiments, they focus more on ensuring the independent variable does not accidentally systematically vary with another variable.
Fill in the blanks to complete the passage about the modes that researchers enter when they are prioritizing certain validities.
When a researcher attempts to test specific aspects of a hypothesis or theory, this process is called theory-testing mode, and in this mode the researcher is typically prioritizing internal validity,. On the other hand, when a researcher is prioritizing external validity in an attempt to apply findings to a broader population, this process is called generalization mode.
Fill in the blanks to complete the passage about experiments with independent variables that cannot be manipulated.
While a(n) experiment includes a manipulated independent variable in order to see the change in a dependent variable, a(n) quasi-experiment includes an independent variable that cannot truly be manipulated by the experimenter. Because participants cannot be randomly assigned to levels of the independent variable, this type of research has nonequivalent control groups.
Label each figure with the type of correlation it best represents.
anser in image
Dr. Okafor ran a study on the efficacy of the therapy sessions he designed to treat depression. Select the figure that indicates there was a regression threat in his study.
answer in image
Jevonte is investigating whether type of exam (essay versus multiple choice) affects the grades of students with varying levels of test anxiety (high versus low). Jevonte also wants to add an additional participant variable of gender. Select the graph that would not represent a three-way interaction in Jevonte's data.
answer in image
Researchers conducted several replication studies surrounding a paradigm initially developed by Deese (1959). With this paradigm, when participants are given a list of words to recall that has to do with a particular word but does not include it, they tend to falsely recall this word, even though it was not on the list. For example, if participants are given a list that includes the words sandal, towel, sunscreen, and waves, then they would falsely remember the word beach even though it was not
conceptual replication: The researchers used a different list of words from the original study. direct replication: The researchers used the same list of words and the same procedure as the original study. replication-plus-extension: The researchers administered the words one at a time to some participants, while administering them all at once to others.
Which of the following strategies are potential ways to prevent individual differences from obscuring group differences?
correct answers: - increase the number of participants - use a within-groups design incorrect answers: - use validated scales - use an independent-groups design
Which of the following strategies are potential ways to avoid testing threats?
correct answers: - add a comparison group - use alternative forms of the test - use a posttest-only design incorrect answers: - use a masked design - remove participants scores from the pretest
Asher is recording children's playground behavior to investigate the differences between third, fourth, fifth, and sixth graders. For each session, he sits on the swings with a notebook and counts the sizes of groups and types of activities for each grade. Asher notices that several children in each grade come over to the swings, but then walk away once they notice him sitting there. Because they walk away, they are not counted in the study. Asher finds that the younger grades tend to do more
demand characteristics
Which of the following examples represent factorial designs?
factorial designs: - Researchers found that the effectiveness of a bullying intervention depended on whether or not the student had been previously bullied. - Experts found that younger people quit smoking faster using nicotine patches, but older people quit faster using nicotine gum. not factorial designs: - Researchers found that the older people are, the more conservative they are. - Over 6 weeks, those who took part in a college mental health program were more likely to do well on final exams than those who did not.
Which of the following are factors that can contribute to a null effect in a study?
factors: - weak manipulation - situation noise - floor effect not factors: - too much power - large sample size
Label each issue with the solution that would best prevent within-groups variability from obscuring group differences.
individual differences: within-groups design situation noise: experimental control measurement error: - reliable, precise scales - more measurements
Select the research design that is the most susceptible to a maturation threat.
one group -> measure on DV -> IV Level 1 -> measure on DV
What criterion for causation is clearly established by manipulating the independent variable?
temporal precedence
Sora is examining whether more hours of sleep and higher quality of sleep decrease stress in college students. She asks her participants to report their level of stress, the number of hours of sleep the night before, quality of sleep the night before, and other demographic variables. Match each questionable research practice to the corresponding scenario that might occur in Sora's study. Labels can be used more than once.
HARKing: - After looking at her results, Sora decides to restate her hypothesis as "more sleep increases stress." underreporting null findings: - Sora finds that stress is not associated with quality of sleep, so she does not include it in her results. p-hacking: - After looking at her results, Sora decides to control for several new variables, including gender. - Sora's results are almost significant, so she removes two participants who slept only 2 hours.
What type of approach do researchers use when they investigate causality with a variety of correlational studies that all point in a single, causal direction?
pattern and parsimony
Several different labs around the world attempted to replicate a classic study on the facial feedback hypothesis (Strack et al., 1988). The idea is that people would find cartoons funnier when holding a pen between their teeth, mimicking a smile, than when holding a pen between their mouth, mimicking a pout. The results across the 17 labs revealed that the 95% CI included zero. Which of the following statements are possible explanations for these results?
possible explanations: - The replication studies were conducted in a different setting that affected the results. - The original study may have engaged in practices that led to fluke results. not possible explanations: - The replication studies were direct replications rather than conceptual replications. - The sample size in the original study was too large, which affected the replicability of results.
Professor Horvat designs a study to assess the work satisfaction and home-life satisfaction of a group of graduate students. She administers the same measures of work and home-life satisfaction on two occasions, 1 year apart. Label each correlation that Professor Horvat discovers with the type of correlation it represents.
- autocorrelation: Job satisfaction at the first time point is correlated with job satisfaction at the second time point. - cross-lag correlation: Home-life satisfaction at the first time point is strongly correlated with job satisfaction at the second time point. - cross-sectional correctional: At the first time point there is a strong correlation between work satisfaction and home-life satisfaction.
Fill in the blanks to complete the passage about three types of small-N designs.
A(n) stable-baseline design monitors a small number of participants for a long period of time before a treatment begins in order to learn what behaviors are typical without treatment. A(n) multiple-baseline design staggers the start time of an intervention across different individuals. Finally, a(n) reversal design introduces a treatment and then removes it to see whether the previous behavior will return.
Fill in the blanks to complete the passage about an example of a study with a null effect.
Frances is conducting a study on concreteness and memory in her dorm room with several of her hallmates. She creates a list of 12 concrete items (e.g., pencil and table) and a list of 12 abstract items (e.g., justice and freedom). Her hallmates view each word for 1 second and then recall them in order. Contrary to Frances' prediction, the study shows a null effect. The study has a null effect likely because of situation noise, which led to too much within-groups variability.
Fill in the blanks to complete the passage about cases in which the independent variable doesn't make much difference in an experiment.
If a researcher determines that the independents variable makes no significant difference in the dependent variable, they are concluding a(n) null effect. This could either be the truth (the variables really are not related) or be due to design flaws in the experiment. There are several design flaws that may produce such a result. A(n) weak manipulation can occur when the change in the independent variable is not strong enough to affect the dependent variable. Or the dependent variable might not be responsive enough to detect change from the independent variable; in other words, it could be a(n) insensitive measure. Additionally, scores from the dependent variable can spontaneously cluster near the top of possible scores, known as the ceiling effect, or near the bottom of possible scores, known as the floor effect-- these phenomena can make covariance undetectable.
Fill in the blanks to complete the passage about ways to replicate studies.
If a researcher wants to reproduce a previous study, they can do so in multiple ways. A(n) direct replication involves recreating previous work as closely as possible to match the original. Scientists can also conduct a(n) conceptual replication, in which a study uses different procedures to recreate a finding similar to the original. Finally, a(n) replication-plus-extension involves copying the original experiment and including additional variables to answer new questions.
Identify the true and false statements about multiple-regression analyses.
True statements: - The largest beta in a multiple-regression analysis is the predictor that has the strongest relationship with the criterion variable. - A multiple-regression analysis can control for more than one variable at a time. False statements: - A multiple-regression analysis that accounts for third variables can establish causality. - Multiple regression establishes temporal precedence as long as it controls for potential third-variable problems.
Fill in the blanks to complete the passage about an example of a quasi-experiment facing threats to internal validity.
Two universities are involved in a study of how student retention and attitudes toward campus life are affected by a new pre-first-year summer visit program at one of the schools. The schools, both state universities in the same state, were closely matched in student-body characteristics to avoid the threat of selection effects. However, in the fall of the first year of the program, the school that was serving as the control was struck by a rare fall tornado, which did damage to several campus buildings. This event could lead to a(n) selection-history threat.
Fill in the blanks to complete the passage about an example of a study with a factorial design.
Vanhong designs a study in which she has a group of younger adults (18-24 years old) and a group of older adults (50-65 years old) recite a poem by memory, once in front of a large audience and once in a room by themselves. She counterbalances the order of these tasks between participants. She has the participants rate their level of anxiety right before they recite the poem each time. the factorial notation for Vanhong's study is 2 x 2 and it is a(n) mixed factorial design.
Fill in the blanks to complete the passage about a certain kind of experimental issue.
When a researcher inadvertently creates a condition with a fundamentally diffrent type of participant than another condition, this can create a selection effect. Researchers can combat this issue by using random assignment to arbitrarily assign participants to each level. In some cases, especially with smaller sample sizes, researchers will deliberately assign participants to groups so that each group has a similar makeup for a particular attribute they are concerned about. This is known as creating matched groups.
Fill in the blanks to complete the passage about experiments with more than one independent variable.
When an experiment tests all possible combinations of more than one independent variable, it is often referred to as a(n) factorial design. These designs can show that the effect of one independent variable depends on the level of another independent variable, also known as a(n) interaction effect. These effects typically have two types. If you were to display the data in a line graph, one type would show the data from one independent variable intersecting with the data from the other, or a(n) crossover interaction. The second type graphed in the same way would show the data points moving away from one another as the dependent variables increases, or a(n) spreading interaction.
Fill in the blanks to complete the passage about the flaws that threaten the internal validity of experiments.
When researchers inadvertently create a flaw that is a threat to the internal validity of their experiment, it is known as a(n) design confound variability. If these flaws coincide with the experimental manipulation and call into question whether it is the manipulation or the flaws that affect the dependent variable, this is known as systematic variability variability. If the flawed part of the experiment is randomly distributed in the groups and doesn't have a pattern, this is known as unsystematic variability variability and does not necessarily pose a threat to internal validity.
Label each transparent research practice with its alternative questionable research practice.
answer in image
What is typically the most important effect that is uncovered in a factorial design?
interaction effect
Iva is studying whether eating meals in the cafeteria is linked to weight gain during the first year of college. She asks all the incoming first-year students about their weights and the number of cafeteria meals they eat each week in the fall, and then she collects the weights and number of cafeteria meals per week from them again at the end of the spring term. Identify the type of correlation that Iva should examine for each goal.
- cross-lag correlation: Iva wants to find out whether weight in the fall is correlated with the number of cafeteria uses in the spring. - autocorrelation: Iva wants to find out whether weight in the fall is correlated with weight in the spring. - cross-sectional correlation: Iva wants to find out whether weight in the fall is correlated with weight in the spring.
Timur has collected some longitudinal data on self-esteem and social media use at two time points 1 year apart. Label each of Timur's findings with the type of correlation it represents.
- cross-sectional correlation: Social media use at Time 1 was negatively correlated with self-esteem at Time 1. - cross-lag correlation: Social media use at Time 1 was positively correlated with self-esteem at Time 2. - autocorrelation: Social media use at Time 1 was positively correlated with social media use at Time 2.
There are several threats that specifically apply to one-group, pretest/posttest experiments. Match each threat to the correct definition.
- history threat: Participants' responses are altered by an event outside the control or interest of the study. - instrumentation threat: The way the researcher measures a variable changes over the course of an experiment. - testing threat: Participants' future performance is changed because of their interaction with a measure. - regression threat: Extreme scores gravitate back toward average. - attrition threat: More participants from one group or condition decline to continue participating than from another. - maturation threat: Participant behavior changes spontaneously over time.
Label each study with the correct study design.
- repeated-measures design: Terrance wants to find out whether sweet or salty snacks make people more satisfied. He first gives everyone a salty snack and has them rate their level of satisfaction. Then, he gives everyone a sweet snack and has them rate their level of satisfaction again. - matched-groups design: Jafari wants to control for intelligence in his study. He sorts the list of participants according to their IQ scores and then forms groups, making sure the groups are balanced in terms of IQ scores. Finally, he randomly assigns each group to one of the conditions of his study. - concurrent-measures design: Kiana designs a study to examine the juice preferences of preschool children. She has the children drink a small cup of apple juice and then a small cup of orange juice. She then asks the children which of the two was their favorite. - pretest/posttest design: Rukmini is running a study to examine the effect of music genre on mood. She randomly assigns participants to three conditions: rock, jazz, and country. She has the participants rate their mood, then listen to their assigned music for 20 minutes, and then fill out the mood questionnaire again.
Fill in the blanks to complete the passage about factorial designs with two independent variables.
In a factorial design with two independent variables, researchers would need to review one interaction effect(s) and two main effect(s). If each independent variable has two levels, this design would also yield four marginal mean(s), which are the averages of each level of an independent variable across all levels of the independent variable.
Fill in the blanks to complete the passage about within-groups designs.
In a within-groups design, each participant experiences all levels of the independent variable. There are two types of this design. The first is the repeated-measures design, in which researchers expose participants to various levels of the independent variable and measure the dependent variable after each exposure. The second is the concurrent-measures design, in which participants interact with the various levels of the independent variable simultaneously.
Fill in the blanks to complete the passage about the problems that can occur in within-groups designs.
In a within-groups design, exposing participants to one level of the independent variable can change how they respond to the other levels of the independent variable. This problem is generally referred to as a(n) order effect effect, of which there are various types. One specific type is known as a(n) carryover effect effect. This occurs when exposure to one level of the independent variable contaminates how other levels of the independent variable are perceived. Another type is a(n) practice effect, which occurs when participants change their responses because of repetition of the dependent variable rather than because of the independent variable itself. It is also possible that repeated exposure to the independent variable may cause participants to guess the hypothesis of the experiment, also known as a(n) demand characteristic effect.
Fill in the blanks to complete the passage about designs with varying numbers of participants.
In single-N designs, researchers study one participant extensively in order to extract as many data as possible. small-N designs are similar in that they treat each individual as a separate experiment, but instead of one participant, they use a few. Finally, large-N designs recruit many participants and are concerned with the data of the sample as a whole.
Fill in the blanks to complete the passage about studies that include a manipulated variable.
When researchers manipulate a variable in a study, they are carrying out a(n) experiment. The manipulated variable is often called the independent variable. A manipulated variable always has more than one level, or condition. Researchers measure the dependent variable to determine the effect of the manipulated variable on it. Researchers often keep certain other factors constant on purpose. This kind of variable is called a(n) control variable.
Joaquin is investigating how teenagers (ages 13-17) and adults (ages 18 and up) respond to two different types of messages (direct versus subtle) designed to increase condom use. After Joaquin gives each participant one of the messages, he asks them to rate how likely they are to use condoms in the future using a percentage out of 100. Select the table that best represents an interaction in Joaquin's data.
answer in image
Place each term on the graph that best represents it.
answer in image
Select the figures that depict a nonequivalent control group interrupted time-series design.
answer in image
Select the graph that shows data with high within-groups variability.
answer in image
Yan and Sengupta (2011) examined the effects of price, attractiveness, and consumer type on the perceived tastiness of and rated satisfaction with a dish of fried rice. The study had a between-groups design and included varying levels of price (inexpensive or expensive), attractiveness of picture (attractive or unattractive), and type of consumer (self or classmate). Select the table that depicts the design of the study.
answer in image
Label each relationship diagram with the type of variable it best represents.
answer in image. - third variable: having lenient parent = viewing violent TV and aggressive behavior - moderator: hours of exposure= is related to viewing violent TV and aggressive behavior - mediator: becoming desensitized to violence = viewing violent TV and aggressive behavior
Bruno is testing a new diet plan to see if it is effective in reducing the frequency of eating cancer-causing foods. Bruno creates two groups of people—one that will receive his new diet plan and one that will receive a traditional diet plan. Bruno knows that culture influences food choices and wants to ensure that each group has an equal representation of different ethnicities. He puts the names of all of the participants from one ethnicity into a hat and draws out names, placing half of them in one group and half in the other. He does the same for each of the ethnic groups represented in his participant pool. Bruno then gives the two groups their different diet plans and measures participants' eating habits 3 months later. Which of the following descriptions are applicable to Bruno's experiment?
applicable: - matched-groups design - posttest-only design - independent-groups design - random assignment not applicable: - pretest/posttest design - within-groups design
Gokhan wants to examine whether coffee increases productivity. He creates two conditions in his study—2 cups of coffee per day and 2 cups of water per day—and asks his participants to sign up for the condition they prefer. In the morning, participants drink either 2 cups of coffee or 2 cups of water. At the end of the day, participants rate their level of productivity on a scale of 1 ("not productive at all") to 10 ("extremely productive"). Which of the following descriptions are applicable to Gokhan's experiment?
applicable: - selection effect - independent-groups design - posttest-only design not applicable: - within-groups design - random assignment - pretest-posttest design
Match each threat to internal validity to the appropriate description.
attrition threat: Participants leave a study in a systematic way. placebo effects: The thought of treatment, rather than the treatment itself, causes participants to report changes. testing threats: Participants change their responses based on past assessment. maturation threat: Participants show spontaneous change. selection effects: Groups vary systematically on traits other than the levels of the independent variable. history threat: An external event, rather than the independent variable, changes scores of the dependent variable.
Some threats to internal validity can be addressed simply by including a comparison group, whereas other threats to internal validity can occur even in studies with a comparison group. The inclusion of a comparison group would help to avoid which of the following threats to internal validity?
avoided threats: - history threat - maturation threat - regression to the mean not avoided threats: - observer bias - demand characteristics
Antonio is studying how different pamphlets promoting a local charity might increase volunteer behavior in high school students. He creates one pamphlet that shows students having fun and being social while volunteering, and another that discusses the benefits volunteering has for college applications and future careers. Antonio has participants read one pamphlet or the other and then fill out a questionnaire about their intentions for volunteering in the future. Antonio's questionnaire asks participants to rate how likely they are to volunteer in the future on a scale of 1 ("I will not volunteer at all") to 5 ("I will likely volunteer in the future"). Antonio finds that both groups score an average of 4.8 on his measure. What problem is most likely causing a null effect in Antonio's study?
ceiling effect
Zion is investigating the effectiveness of his summer math tutoring program. He randomly assigns elementary school students to a tutoring group, which receives the math tutoring program 3 days a week during the entire break, or a self-study group, which receives a sample of math materials without a tutor. At the end of the summer, all of the students take the same math test with a possible score of 0 to 100. The students in the tutoring group are proctored by a strict and intimidating teacher, w
design confounds acting in reverse
Professor Horvat designs a study to assess the work satisfaction and home-life satisfaction of a group of graduate students. She administers the same measures of work and home-life satisfaction on two occasions, 1 year apart. Suppose she finds that home-life satisfaction at the first time point is strongly correlated with job satisfaction at the second time point, but there is no correlation between job satisfaction at the first time point and home-life satisfaction at the second time point. Which of the following three criteria for causation are established in Professor Horvat's study?
established: - covariance - temporal precedence not established: - internal validity
Label each example with the correct mode. Labels can be used more than once.
generalization mode: - A researcher is recreating a previous study from liberal arts colleges at large public universities. - Two researchers are attempting to replicate a finding from the United States in Japan. theory-testing mode: - Researchers design a study to understand what, specifically, compels people to help others in emergency situations. - A lab is conducting a series of studies to understand the effects of emotion on the written word.
A city in California has asked Professor Rodriguez to conduct an experiment on earthquake preparedness. Professor Rodriguez will assess the preparedness of a random sample of residents in the city, and then the city will mail out an annual brochure on earthquake safety. Then, 2 weeks later, he will again assess the preparedness of those residents. Right after the brochures are mailed, a large earthquake is reported in Japan. Which threat to internal validity is present in Professor Rodriguez's experiment?
history threat
On the first exam in an Introductory Psychology class, the grades are lower than Professor Mutola expected. She suspects that multitasking is to blame. She bans computers and smart phones from her class between the first and second exams. When she compares the two sets of exam scores, she finds a significant improvement on the second exam. Match each threat to internal validity to the corresponding scenario that might happen in Professor Mutola's study.
instrumentation threat: Professor Mutola looks back over the second exam and discovers it was an easier exam. maturation threat: Professor Mutola notes that every semester students always do better on the second exam because they are more used to the class. attrition threat: When rechecking her data, Professor Mutola finds that the five students with the lowest scores on the first exam dropped the class.
Amir is conducting a study in which women and men watch one of three television commercials (charity, political, or control) in order to see which combination of commercial and gender lead to the most helping behavior. Identify the number of main effects and interactions Amir is likely to find in his study. Not all items will have a match.
interaction(s): one main effect(s): two
What is the reason that researchers sometimes rely on pattern and parsimony to investigate causality?
it may not be ethical or practical to manipulate certain variables
Sammy is interested in studying behavior problems. Identify the multivariate technique that Sammy should use to investigate each of her research goals. Labels can be used more than once.
longitudinal study: - Sammy wants to find out whether self-esteem in elementary school predicts behavior problems in middle school. - Sammy wants to find out whether self-esteem and behavior problems have a mutually reinforcing relationship. multiple regression: - Sammy wants to find out whether parenting style explains the association between self-esteem and behavior problems. - Sammy wants to find out whether there is an association between self-esteem and behavior problems even after adjusting for experience with bullying.
Label each example with the type of variable that best represents it. Labels can be used more than once.
mediator: - A negative parenting style is the reason that marital violence is linked with childhood aggression. - Friendship explains why social media use and happiness are related. moderator: - Stress is associated with negative health outcomes only when the stress is viewed negatively. - third variable: - The correlation between weight and vocabulary is actually a function of age, not a true association. - Warm temperatures cause ice cream sales to be associated with crime rates, though they otherwise would not be associated.
All else being equal, which of the following are methods that can help increase power in a study?
methods: - increasing sample size - using a within-groups design not methods: - using an independent-groups design - adding situation noise
Which of the following strategies are methods for addressing criticisms about external validity in small-N studies?
methods: - combine the results of single-N studies with those of other studies - specify a limited population to generalize to not methods: - set up a comparison group - present the data in a graph - check the operationalization of the variables
Match each design to the correct example.
multiple-baseline design: Teachers introduce four different third-grade classrooms to longer recess periods starting at different time points, to find out whether longer recess will help decrease classroom misbehavior. reversal design: Therapists introduce a patient with antisocial personality disorder to an intervention involving the reinforcement of positive behavior; then, the therapists remove it several weeks later to see how it affects the patient's behavior. stable-baseline design: A therapist studies a patient with obsessive-compulsive disorder for several weeks before initiating treatment.
Match each design to the appropriate description.
nonequivalent control group pretest/posttest design: a quasi-experiment with a treatment and a control group that measures the dependent variable before and after the treatment nonequivalent control group interrupted time-series design: a quasi-experiment with two groups that are measured repeatedly before, during, and after some event interrupted time-series design: a quasi-experiment with a single group of participants that is measured repeatedly before, during, and after some event nonequivalent control group posttest-only design: a quasi-experiment with one treatment and one control group that measures the dependent variable only once
Which of the following are obscuring factors that can be detected with a manipulation check?
obscuring factors: - weak manipulations - ceiling effects - floor effects not obscuring factors: - individual differences - situation noise
Mohamad hypothesizes that lack of sleep before the age of 7 results in substance abuse later in life. He realizes that it would be unethical to conduct an experiment depriving children of sleep and that a correlational study could not establish temporal precedence. Mohamad decides to conduct several different studies to establish multiple association claims that point to his hypothesis. What is Mohamad's approach called?
pattern and parsimony
Which of the following scenarios are examples of questionable research practices?
questionable research practices: - Researchers create new hypotheses after collecting the data. - Researchers add more participants to their study after discovering a result that is not significant. not questionable research practices: - Researchers freely share the data and materials from their study online. - Researchers conduct a study with a large sample.
Match each type of replication study to the correct description.
replication-plus-extension: A researcher is recreating an experiment on study habits and adding in ethnicity as a new factor to see if there are any differences. conceptual replication: A scientist attempts to replicate the better-than-average effect with niche talents such as playing musical instruments, rather than in the classroom. direct replication: A team of researchers recreates a previous experiment on persuasion exactly as it was written in the original publication.
Samira finds these results in her study on binge-watching TV and relationship quality: d = −0.13, 95% CI [−.30, .40]. Her variables had good construct validity and she had an adequate sample size. What should Samira do based on the results of her study?
samira should conclude that there truly is no significant effect and revise her theory
Timur has collected some longitudinal data on self-esteem and social media use at two time points 1 year apart. He finds these correlations. What is the best interpretation of Timur's results on the relationship between social media use and self-esteem? (Note: * = p < .05)
students who have used more social media are more likely to have high self-esteem over time
Label each example with the type of variability it best represents. Labels can be used more than once.
systematic variability: - Shilpa wants to examine whether time of day affects grocery shoppers' moods. She finds that people who shop for groceries earlier in the day are happier than people who shop later in the evening. After Shilpa collects her data, the manager tells her that the store usually has more items in stock in the morning. - Travis is comparing the effects of music type on productivity. His research assistants tell him they really enjoy the upbeat music condition. unsystematic variability: - Imani and her three research assistants are doing a study on sociability in college students, with participants either in one-on-one or in small groups. She later finds out that one of her research assistants is much chattier than the others in both the one-on-one and small group conditions. - Marcos is testing how video game performance affects aggression. He randomly assigns participants to play either an easy video game or a difficult video game. Some of his participants have never played video games before.
Match each threat to internal validity to the corresponding scenario.
testing threat: On Monday, an instructor has his class sit in chairs for 2 minutes before completing a reading quiz. On Wednesday, he has the same class do 2 minutes of jumping jacks before completing the same reading quiz that they took on Monday. observer bias: A graduate student predicts that people eating sweets will be friendlier than people eating healthy foods. She has one group of participants eat donuts and interact with one another. She has another group of participants eat carrot sticks and interact with one another. She codes each participant's level of friendliness. instrumentation threat: Initially, raters are quite strict in their ratings of prosocial behavior in videotapes of a preschool class, but after 3 hours of rating, their criteria become more lenient.
There are several threats that specifically apply to one-group, pretest/posttest experiments. Match each threat to the example that best represents it.
testing threat: Participants change their answers on a racism scale after seeing it a second time. regression threat: Participants show very high stress scores on the pretest and returned to average on the posttest. maturation threat: Students in a study on grade performance naturally improve their grades during the study. history threat: A large clearance sale takes place during a study on shopping behavior. instrumentation threat: Observers code social behavior as less friendly over time. attrition threat: The three healthiest participants withdraw from a study on metabolic syndrome.
Jonide comes across a newspaper article with the headline, "Bigger Weddings Lead to Happier Marriages." She reads that researchers recruited 418 married couples from a local shopping center and collected their responses to a variety of survey questions, including some asking about the number of guests at their wedding and their relationship happiness (measured with questions about spousal satisfaction). This table presents the results of the study. A skeptic of this research says that the only reason that couples with larger weddings have happier marriages is that rich people can afford large weddings and rich people are happier. Which statement is the correct response to this critic?
the critic is incorrect because the number of guests at the wedding is associated with relationship happiness even after the researchers controlled for personal income.
Professor Horvat designs a study to assess the work satisfaction and home-life satisfaction of a group of graduate students. She administers the same measures of work and home-life satisfaction on two occasions, 1 year apart. Suppose she finds that home-life satisfaction at the first time point is strongly correlated with job satisfaction at the second time point, but that there is no correlation between job satisfaction at the first time point and home-life satisfaction at the second time point. Which statement explains why Professor Horvat can't conclude that home-life satisfaction causes job satisfaction?
there are potential third variables that might explain the relationship
Gloria is designing an experiment to understand whether the amount of stress someone is experiencing (high versus low) changes which types of medications for depression (SSRI, NDRI, or placebo) will be effective. Gloria also plans to account for the differences in people with major depressive disorder and people with persistent depressive disorder. Identify the number of two-way interactions, three-way interactions, and main effects Gloria is likely to find in her experiment.
three: - two-way interactions - main effects one: - three-way interactions
Yan and Sengupta (2011) examined the effects of price, attractiveness, and consumer type on the perceived tastiness of and rated satisfaction with a dish of fried rice. The study had a between-groups design and included varying levels of price (inexpensive or expensive), attractiveness of picture (attractive or unattractive), and type of consumer (self or classmate). Identify the true and false statements about this study.
true statement(s): - there are eight cells in this study - there are two dependent variables in this study false statement(s): - the researchers could have examined two possible two-way interactions in this study - this study is a 2 x 3 factorial design
Jared wants to examine whether mindfulness training can increase concentration. He begins with a concentration task and finds that on average his participants can concentrate for only 30 seconds. He then gives the participants mindfulness training over the course of 2 weeks and finds that their average score improves significantly to 30 minutes on the same concentration task. Identify the true and false statements about Jared's study.
true statements: - - false statements: - -
Identify the true and false statements about multivariate designs and causation.
true statements: - Association claims are often used as a step toward establishing a causal relationship. - Multivariate correlational designs are often used when it is impossible to conduct an experiment. false statements: - Multivariate designs cannot be used to improve the case for causation. - Multivariate designs can handle no more than four variables at a time.
Feliciano is using a pretest/posttest design to conduct an experiment on improving children's handwriting, employing two different techniques of improving handwriting and a control condition. In the results, the two groups who receive the treatment don't show any difference from each other. Feliciano believes that there is a difference but that his 3-point assessment scale of handwriting cannot detect it. Identify the true and false statements about Feliciano's study.
true statements: - Feliciano is most concerned about using an insensitive measure. - To address his concern, Feliciano should use a scale with more levels for his dependent variable. false statements: - To address his concern, Feliciano should increase his sample size. - Feliciano is most concerned about measurement error. - To address his concern, Feliciano should use a manipulation check for his independent variable.
Identify the true and false statements about threats to internal validity in one-group, pretest/posttest designs.
true statements: - If participants withdraw from a study in an unsystematic way, there is likely no attrition threat. - A regression threat can produce a significant result that does not actually exist in the population. false statements: - To prevent a history threat, the comparison group should be studied at a different time or in a different location than the treatment group. - A study typically has only one threat to internal validity.
Identify the true and false statements about null effects.
true statements: - If there is not enough between-groups difference, it can result in a null effect. - Null effects can occur in any experiment. false statements: - Researchers rarely find null effects in experiments. - Decreases in within-groups variability can lead to a null effect.
Grimstvedt and colleagues (2010) examined the effect of placing signs encouraging the use of stairs near elevators. Based on their design, Liu Wei designs a study for his campus. He selects four buildings and starts by measuring elevator and stair use in those buildings for a month. He then posts signs encouraging the use of stairs near the elevators and measures elevator and stair use in the buildings for another month. Identify the true and false statements about Liu Wei's study.
true statements: - Liu Wei is utilizing a stable-baseline design. - Liu Wei's study involves a within-groups design. false statements: - Liu Wei's study design has high external validity. - Liu Wei's study is a quasi-experiment.
Identify the true and false statements about the difference between beta and r.
true statements: - Unlike r, beta reflects the independent contribution of the predictor variable, controlling for the other predictor variables. - Unlike r, betas can only be compared within the same regression table. false statements: - Unlike r, a beta of zero reflects a statistically significant relationship between the predictor variable and the criterion variable. - Unlike r, beta cannot be negative.
Identify the true and false statements about replicating studies.
true statements: - A study that has been replicated is more credible than a study that has not been replicated. false statements: - A direct replication reproduces every single detail of the original study. - Conceptual replications are less useful than direct replications in assuring that a finding is reliable. - If a study gets significant results, it does not need to be replicated.
Identify the true and false statements about quasi-experiments.
true statements: - Many quasi-experiments would be unethical if treated as true experiments. - Quasi-experiments allow scientists to study real-world phenomena in real time. false statements: - Correlational studies and quasi-experiments are identical designs. - Researchers conducting quasi-experiments are not trying to make causal claims.
Horselenberg and colleagues (2003) conducted an experiment based on Kassin and Kieche (1996) in which participants were falsely accused of striking a computer key that caused important data to be deleted. The first study showed that 69% of the participants were willing to sign a confession that they had struck the key. In the later study, researchers changed the procedure so that in addition to signing the confession, participants were asked to give up part of their compensation for participatin
true statements: - The original study was conducted in the United States. If they wanted to strengthen external validity, the researchers could have conducted their replication study in the Netherlands. - If they wanted to increase experimental realism, the researchers could have made the lab situation closely parallel false confessions of a crime. false statements: - If they wanted to strengthen external validity, the researchers could have increased the number of participants in the study. - If they wanted to strengthen construct validity, the researchers could have conducted several different replication studies.
Match each threat to the appropriate prevention method.
use a comparison group: - history threat - regression threat - maturation threat remove participant scores from the pretest: - attrition threat use a posttest-only design: - instrumentation threat
Professor Zhao wants to test the effectiveness of review sessions on test performance. He randomly assigns the students in his 50-student Introduction to Psychology class to one of two review sessions, each being taught with a different technique. Identify the problem that is most likely causing a null effect in each scenario that might happen in Professor Zhao's study.
weak manipulation: The review sessions are different in that one is held in-person and the other is held through video conferencing, although they both cover the same content. floor effect: All 50 students get all 10 test questions incorrect, regardless of the review session they are in. ceiling effect: All 50 students get all 10 test questions correct, regardless of the review session they are in. insensitive measure: Professor Zhao measures the effectiveness of the review sessions with pass/fail categories. He finds that there is no difference between the students in the two review sessions.
Match each type of factorial design to the correct definition.
within-groups factorial design: each participant experiences all combinations of the independent variables independent-groups factorial design: each cell of each of the independent variables has unique subjects mixed factorial design: all participants experience all levels of one independent variable but only one level of another independent variable
