PSYC 256 Final

Interrogate two aspects of external validity for an experiment (generalization to other populations and to other situations).

-Generalization to other populations: "how did the experimenters recruit their participants?" 1. Random assignment from population of interest? -Generalization to other situations: To decide whether an experiment's results can generalize to other situations, it is sometimes necessary to consider the results of other research.

Identify the following threats to internal validity: history, maturation, regression, attrition, testing, instrumentation, observer bias, demand characteristics, and placebo effects.

-History: some external or "historical" event affects most members of treatment group at same time as treatment. -Maturation: a change in behavior that emerges spontaneously over time. -Regression: extremely low or extremely high performance at time 1 is likely to be less extreme at time 2. -Attrition: systematic drop-outs from the study. -Testing: a change in participants as a result of experiencing the DV more than once. -Instrumentation: measuring instrument changes over time (ex: changing observation criteria). -Observer bias: observer's expectations influence dependent variables. -Demand characteristics: participants take cues from experimenter and behave in ways consistent with hypothesis. -Placebo effects: change in performance due to beliefs that treatment will work.

Interrogate the construct validity of the measured (dependent) variable in an experiment.

-How well was the DV measured? You can use past literature to make sure you have operationalized the variable well.

Describe interactions in terms of "it depends".

-Independent variable allows researchers to look for an interaction effect (or interaction)--whether the effect of the original independent variable (cell phone use) depends on the level of another independent variable (driver age); an interaction of two independent variables allows researchers to establish whether or not "it depends". They can now ask: Does the effect of cell phones depend on age?

Describe how the procedures for independent-groups and within-groups experiments are different. Explain the pros and cons of each type of design.

-Independent: different groups of participants are placed into different levels of the independent variable. This type of design is also called a between-subjects design or between-groups design. -Within: there is only one group of participants, and each person is presented with all levels of the independent variable. -Within-groups treat each participant as their own control, and require fewer participants than independent-groups designs. Within-groups designs also present the potential for order effects and demand characteristics.

Differentiate independent-groups, within-groups, and mixed factorial designs.

-Independent: different groups placed into different levels of the independent variable. -Within: one group experiences all levels of the independent variable. -Mixed: involves two or more independent variables, of which at least one is a within-subjects (repeated measures) factor and at least one is a between-groups factor. In the simplest case, there will be one between-groups factor and one within-subjects factor.

Identify a study's independent, dependent, and control variables.

-Independent: variables which are manipulated. -Dependent: variables that are measured. -Control: variables which are intentionally held constant.

Be able to identify and differentiate main effects and interactions.

-Interaction effects represent the combined effects of factors on the dependent measure. When an interaction effect is present, the impact of one factor depends on the level of the other factor; or part of the power of ANOVA is the ability to estimate and test interaction effects. -Main effect is the effect of just one of the independent variables on the dependent variable.

Give examples of questions you would ask about a small-N design to interrogate all four big validities.

-Internal: very high; intentional on making it carefully designed. 1. Are there alternative explanations for the result? -External: can combine results of one study with others; can specify the population to which they want to generalize, rarely intend to generalize to everyone. 1. How can results from one person generalize to everyone? -Construct: use multiple observers to check for interrater reliability. 1. Are the measurements used in the experiment valid? -Statistical: graphs provide enough quantitative evidence; look at effect size in these designs. 1. By what margin did client's behavior improve?

Explain what a meta-analysis does.

-It yields a quantitative summary of scientific literature; averaging the results of all the studies that have tested the same variables to see what conclusion that whole body of evidence supports.

Explain why large within-group variance can obscure a between-group difference.

-It's a statistical validity problem: The greater the overlap, the smaller the effect size, and the less likely the two group means will be statistically significant; that is, the less likely the study will detect covariance.

Understand and be able to identify and differentiate main effects from interactions.

***When a study shows both a main effect and an interaction, the INTERACTION is almost always more important. -Main effects: is there a sig difference between levels of one independent variable on the dependent variable, averaging over the levels of the other independent variable. In other words, a main effect is a simple difference (in a factorial design w/ 2 independent variables, there are 2 main effects). -Interactions: whether the effect of the original independent variable (cell phone use) depends on the level of another independent variable (driver age). 1. Show moderators which is an independent and dependent variable. 2. crossover: How much you like certain foods depends on the temperature at which they are served. It's equally correct to say that they temperature you prefer depends on which food you're eating. 3. spreading: My dog sits when I say "Sit," but only when I'm holding a treat.

Differentiate 2-way and 3-way interactions and be able to identify names of designs.

-2 way: 2x2=4 there are four different groups of participants in the experiment. -3 way: 2x2x2=8 cells ***If a three way interaction is significant, it means that the two way interaction between two of the independent variables depends on the level of the independent variable.

Us the three causal rules to analyze an experiment's ability to support a causal claim.

-3 rules: 1. Covariance. Do the results show that the causal variable is related to the effect variable? Are distinct levels of the independent variable associated with different levels of the dependent variable? 2. Temporal precedence. Does the study design ensure that the causal variable comes before the outcome variable in time? 3. Internal validity. Does the study design rule out alternative explanations for the results?

Identify and interpret data from a multiple regression table and explain, in a sentence, what each coefficient means (beta, significance).

-A beta value is similar to correlation, but it is within the context of the variable that you measured. A high beta value doesn't mean it is significant. Betas can alter depending on the other variables measured and change based on relative strength. There's one beta value for each predictor, and the sign of the beta tells you the direction of the relationship while the beta value tell you the strength of it (higher=stronger). -Significant beta values are determined by the p-value that corresponds with it.

Distinguish measured from manipulated variables in a study.

-A measured variable is one whose levels are simply observed and recorded. Some variables, such as height and and IQ, are measured using familiar tools (a ruler, a test). -In contrast, a manipulated variable is a variable a researcher controls, usually by assigning study participants to different levels of that variable. For example, a researcher might give some participants 10 milligrams of a medication, others 20 mg, and still others 30 mg.

Understand when to use and how to interpret one-way and N-way ANOVAs.

-ANOVA: analysis of variance. 1. one-way: compares the means between the groups you are interested in and determines whether any of those means are statistically significantly different from each other. Specifically, it tests the null hypothesis. 2. two-way: compares the mean differences between groups that have been split on two independent variables (called factors). The primary purpose of a two-way ANOVA is to understand if there is an interaction between the two independent variables on the dependent variable.

Explain the benefits and costs of using a small-N design.

-Advance of rare medical cases. -Lots of detail. -Can have high internal validity if carefully designed. -Costs: external validity & internal.

Describe the replication debate in psychology, including the notion of a "replication crisis".

-An ongoing (2019) methodological crisis primarily affecting parts of the social and life sciences in which scholars have found that the results of many scientific studies are difficult or impossible to replicate or reproduce on subsequent investigation, either by independent researchers or by the original researchers themselves. The crisis has long-standing roots; the phrase was coined in the early 2010s as part of a growing awareness of the problem. The replication crisis represents an important body of research in meta-science. -The announcement was alarming. Science writers dubbed the problem a "replication crisis," and in the months that followed, scientists began to analyze the situation. The replication crisis has been scrutinized in terms of problems with the replication attempt, with the original study, and with publication practices. The issues are summarized in Table 14.1.

Explain VanderStoep's main ideas regarding Christians' objections to research psychology.

-Challenges: 1. "The data don't lie." a. Reject psychology b. Work to gather psychological data that agree w/ Christian beliefs (e.g., positive effects of Christian life) c. Steer between these two extremes 2. "I don't believe it"/"I don't care" a. A Christian approach psychological research b. Data are descriptive, not prescriptive c. Question assumptions underlying research (why was it done; for what purpose) d. What about when Christianity and science seem to contradict? Choose the more desired outcome. i. Remember that science can't answer moral questions. e. Respect for science, but other beliefs (Christian beliefs) always override science. f. Belief bias effect g. Examples: i. Myers vs. Jones & Yarhouse ii. Cohabitation research 3. The importance challenge a. Christians accepting factuality of psychology's claims, but don't find them very helpful in their lives. i. Seeing psychology as adding nothing not already known through other disciplines. This is a low view of the value of psychology. ii. Psychological research has no direct relevance/application to their lives. b. This is a low view of the value of psychology. c. These objections aren't unique to Christians.

Identify effect size d and explain what it means for an experiment.

-Cohen's d is the size of the effect, tell you if there was a weak/moderate/strong effect.

Explain two reasons to conduct a factorial study.

-Factorial study: A study that has more than one independent variable is said to use a factorial design. A "factor" is another name for an independent variable. -WHY: 1. Show interactions between factors. 2. More like real life. 3. Allows you to compare IV's effect on subgroups of people. 4. Greater experimental control over extraneous variables. 5. Can be used to test theories. a. The best way to study how variables interact is to combine them in a factorial design and measure whether the results are consistent with the theory.

Explain how comparison groups, double-blind studies, and other design choices can help researchers avoid many of these threats to internal validity.

-Comparison groups: 1. history --> controls for the threat of "historical" changes. 2. maturation --> allow for subtraction of effect of maturation when interpreting results. 3. placebo --> to determine whether an effect is caused by a treatment or placebo. -!!! Many internal validity threats are likely to occur in the one-group pretest/posttest design, and these threats can often be examined simply by adding a comparison group. Doing so would result in a pretest/posttest design. The posttest-only design is another option (see Chapter 10). However, 3 more threats to internal validity--observer bias, demand characteristics, and placebo effects--might apply even for designs with a clear comparison group. -Double-blind: neither the participants nor the researchers who evaluate them know who is in the treatment group and who is in the comparison group --> to avoid observer bias and demand characteristics. -Placebo --> double-blind placebo control study.

Explain the difference between concurrent-measures and repeated measures designs.

-Concurrent measures: a type of within-groups design where participants are exposed to all the levels of an independent variable at the same time, and then indicate a preference for one level (the dependent variable). -Example: Harlow's monkeys being exposed to wire and cloth mother at the same time. -Repeated measures: a type of within-groups design in which participants are measured on a dependent variable after each exposure to an independent variable condition. -Rational example: Participants experience both levels, making it a within-groups design. The dependent variable was rating of the chocolate. It was a repeated-measures design because people rated the chocolate twice (i.e., repeatedly). -Establishes temporal precedence.

Interrogate quasi-experimental designs by asking about construct validity, external validity, and statistical validity.

-Construct: very important. -External: may be sacrificed. -Stat.: very important.

Explain why replication studies might fail.

-Contextually sensitive events 1. Failed due to altered context -Number of replication attempts 1. One-time attempts may fail themselves -Problems with the original study 1. Too small sample size 2. HARKing- Hypothesizing After Results are Known 3. p-hacking- Running the statistical test until you get the result you want, and then stopping.

Explain why control variables can help an experimenter eliminate design confounds.

-Control variables are essential in experiments. They allow researchers to separate one potential cause from another and thus eliminate alternative explanations for results. Control variables are therefore important for establishing internal validity. -What can we do about confounds? For a personal experience, it is hard to isolate variables. Think about the last time you had an upset stomach. Which of the many thing you ate that day made you sick? Or your allergies--which of the blossoming spring plants are you allergic to? In a research setting, though, scientists can use careful controls to be sure they are changing only one factor at a time.

Describe counterbalancing and its role in the internal validity of a within-groups design.

-Counterbalancing: Present levels of IV to different participants in different orders; With counterbalancing, any order effects should cancel each other out when all the data are collected. -Example: when you eat chocolate alone/with people: assign some subjects to eat alone first, and assign some to eat with other people first (assuming that there was a difference in your rating of chocolate based on if you ate it alone first then with someone, or ate it with someone first then alone). -Any order effects should cancel each other out if you use counterbalancing because you will randomly assign different sequences to all participants. -Order effects are when being exposed to one condition changes the way that they react to being exposed to the other one. They are a threat to internal validity, so we strive to avoid them. -Types of Counterbalancing 1. Full: all possible condition orders are represented. 2. Partial: only some of all possible condition orders are represented. a. present the conditions in a randomized order for every subject. b. Latin square, a formal system to ensure that every condition appears in each position at least once.

Identify three types of correlations in a longitudinal correlational design: cross-sectional correlations, autocorrelations, and cross-lag correlations.

-Cross-sectional correlations: We look at each time period and see if there is a correlation or relationship between the evaluation and the behavior (i.e. evaluation one and behavior one). -Autocorrelations: This is when we look at the one behavior over time and the one evaluation over time (i.e. evaluation one vs. evaluation two or behavior one vs. behavior two). -Cross-lag correlations: This is when the evaluation leads to a behavior and vice versa to see if one predicts another (i.e. does evaluation one predict behavior two? Does behavior one predict evaluation two?).

Review 3 threats to internal validity: design confounds, selection effects, and order effects.

-Design confounds: there is an alternative explanation because the experiment was poorly designed; another variable happened to vary systematically along with the intended independent variable. -Selection effects: confound exists because the different independent variable groups have systematically different types of participants. -Order effects: there is an alternative explanation because the outcome might be caused by the independent variable, but it might also be caused by the order in which the levels of the variable are presented. When there is an order effect, we do not know whether the independent variable is really having an effect, or whether the participants are just getting tired, bored, or well practiced.

Describe the differences among direct replication studies, conceptual replication studies, and replication-plus-extension studies.

-Direct Replication: 1. Same variables and operationalizations. a. A single failure doesn't fully discredit a finding. b. Downside- any flaws in the original study are repeated, 100% replication is impossible. -Conceptual Replication: 1. Same conceptual variables, different operationalizations. -Replication + Extension: 1. Adding one or two variables or operationalizations to the replication of the original study.

Explain why experiments are superior to multiple regression designs for controlling for third variables.

-Experiments have higher internal validity. -Multiple regression can't always establish temporal precedence.

Explain the differences between small-N and large-N experiments.

-Large-N 1. Participants are grouped. The data from an individual participant are not of interest in themselves; data from all participants in each group are combined and studied together. 2. Data are represented as group averages. -Small-N 1. Each participant is treated separately. Small-N designs are almost always repeated-measures designs, in which researchers observe how the person or animal responds to several systematically designed conditions. 2. Data for each individual are presented.

Explain how longitudinal designs are conducted.

-Longitudinal designs can allow us to see temporal precedence through looking at a person's life over time and seeing the relationship between the IV and DV change over time. -A longitudinal design can provide evidence for temporal precedence by measuring the same variables in the same people at several points in time. Longitudinal research is used in developmental psychology to study changes in a trait or an ability as a person grows older. In addition, this type of design can be adapted to test causal claims.

Estimate marginal means in a factorial design to look at main effects.

-Marginal means: arithmetic means for each level of an independent variable, averaging over levels of the other independent variable. Figure 12.13.

Articulate the difference between mediators, third variables, and moderating variables. (pg. 263 in book)

-Mediators ask "why?" Why is X related to Y? -Moderators ask "for whom?" or "when?" Under what circumstances? -Third variable links two other variables together. The third variable causes the relationship.

Explain how multiple-regression designs are conducted.

-More than two measured variables.

Describe three causes of within-group variance--measurement error, individual differences, and situation noise--and indicate how each might be reduced.

-Noise (error variance or unsystematic variance): too much unsystematic variability within each group. -Measurement error: a human or instrument factor that can inflate or deflate a person's true score on the dependent variable. 1. Solution: use reliable, precise tools; measure more instances (e.g., times, bigger sample). -Individual differences: people are just different. 1. Solution: add more participants; change the design. -Situation noise: external distractions (doing an experiment in the middle of the student union on campus).

Define the following quasi-experimental designs: nonequivalent control group design, interrupted time-series design, and nonequivalent groups interrupted time-series design.

-Nonequivalent: like independent-groups design, but participants not randomly assigned. -Interrupted time-series: measure participants repeatedly on a dependent variable before, during, and after the "interruption" caused by some event (a food break). -Nonequivalent interrupted time-series: combines nonequivalent and interrupted.

Describe at least two ways that a study might show inadequate variance between groups and indicate how researchers can identify such problems.

-Not enough variability between groups. This would be about having inadequate variation of the independent variable (simply the conditions into which people are assigned simply don't differ enough to bring about differences in the dependent variable). It could also be that the measurement is not sufficiently precise or sensitive to pick up on differences between groups or one could be dealing with floor effects (performance can't improve because people are already performing at a very high level).

Articulate the reasons that a study might result in null effects: not enough variance between groups, too much variance within groups, or a true null effect.

-Null effect: if independent variable did not make a difference in the dependent variable. -Not enough variance between groups can be due to: 1. Weak manipulations --> ask how the researchers operationalized the independent variable a. Effects of $ on mood: .10, .20, 1.00, vs. $20, $60, $100. 2. Insensitive measures --> When it comes to dependent measures, it's smart to use ones that have detailed, quantitative increments--not just two or three levels. 3. Ceiling & floor effects --> In a ceiling effect, all the scores are squeezed together at the high end. In a floor effect, all the scores cluster at the low end. a. Ceiling and floor effects can be the result of a problematic independent variable. For example, if the researcher really did manipulate his independent variable by giving people $0.00, $0.25, or $1.00, that would be a floor effect because these three amounts are all low--they're squeezed close to a floor of $0.00. b. Poorly designed dependent variables can also lead to ceiling and floor effects. Imagine if the logical reasoning test in the anxiety study was so difficult that nobody could solve the problems. That would cause a floor effect: The three anxiety groups would score the same, but only because the measure for the dependent variable results in low scores in all groups. 4. Reverse design confounds --> A study might be designed in such a way that a design confound actually counteracts, or reverses, some true effect of an independent variable.

How can larger sample sizes, open science, and preregistration help solve the replication crisis?

-Open science: the practice of sharing one's data and materials freely so others can collaborate, use, and verify the results. When data are open, psychologists provide their data set, so other researchers can conduct new analyses on it or reproduce the published results. -Preregistration: preregister a study's method, hypotheses, or stat. analyses online in advance of data collection. -Sample size: use a large sample size so that unusual cases have less chance of influencing a study's pattern.

How does external validity apply to both other participants and to other settings?

-Other participants: 1. Comes from how not how many --> randomly selected 200 participants = external validity, not haphazardly selecting 2,000 people. -Other settings: 1. Ecological validity: similarity to real-world contexts.

Explain the value of pattern and parsimony in research.

-Pattern means what is consistently showing up as a factor. -Parsimony means the simplest answer that still explains what's going on.

Define dependent variables and predictor variables in the context of multiple regression data.

-Predictor variables are the same as independent variables.

Identify posttest-only and pretest/posttest designs, and explain when researchers might use each one.

-Pretest/Posttest: type of quasi-experiment where you measure DV in subjects before and after exposure to the IV. You may use it when 1) Pre-existing conditions influence selection to the study 2) Random assignment may be ineffective 3) Participant mortality is a concern. - Pretest/posttest may make more sense in the case of ensuring equivalent groups at the start & studying improvement over time, as long as the pretest does not make the participants change their spontaneous behavior. -Posttest Only: type of quasi-experiment where participants are only tested after being exposed to independent variables, not before; one of the simplest independent-groups experiment design. You may use it when 1) time constraints are a concern 2) Pretest may sensitize subjects to what is being studied. -In some cases, its best to use posttest design --> van Kleef pasta study: ppl may have gotten too full to participate in the rest of the study, so researchers trusted in random assignment. -It's combo of random assignment and manipulation of a variable that leads to powerful conclusions. -This design satisfies ALL 3 criteria for causation 1. Covariance: detect differences in the dependent variable (having at least two groups). 2. Temporal: independent variable comes first in time. 3. Internal validity: when they are conducted well; when use appropriate control variables there should be NO design confounds; random assignment takes care of selection effects.

Explain how quasi-experiments can be independent-groups or within-groups designs.

-Quasi-experiment: might not be able to randomly assign participants to one level or the other; they are assigned by teachers, political regulations, acts of nature--or even by their own choice; researchers do not have full experimental control. -Independent: in which there are different participants at each level of the independent variable. This type of quasi-experimental design is typically called a nonequivalent control group design. It has at least one treatment group and one comparison groups, but unlike in a true experiment, participants have not been randomly assigned to the two groups. -Within-groups: as opposed to a true repeated-measures experiment, the researcher relies on an already-scheduled event, a new policy or regulation, or a chance occurrence that manipulates the independent variable.

Articulate the difference between random selection and random assignment and discuss how random selection relates to external validity and random assignment relates to internal validity.

-Random selection refers to how sample members (study participants) are selected from the population for inclusion in the study. 1. Participants: Population --> study -Random assignment is an aspect of experimental design in which study participants are assigned to the treatment or control group using a random procedure. 1. Participants: (in study) --> assigned to a group.

Explain the benefits and costs of using a quasi-experimental design.

-Real world opportunities. -Higher external validity. -Ethics. -Construct validity & stat. validity. -Costs 1. Internal validity is compromised / no random assignment.

Describe two techniques that researchers use to decide if a study's results are replicable: inferential statistics and replication studies.

-Replication: when a researchr performs a study again, it is known as a replication study. Even when the original investigation has a statistically significant result, researchers still have to conduct a replication study. -Inferential: use a random sample of data taken from a population to describe and make inferences about the population; valuable when examination of each member of an entire population is not convenient or possible.

Explain whether quasi-experimental studies avoid the following threats to internal validity: selection, maturation, history, regression, attrition, testing, instrumentation, observer bias, experimental demand, and placebo effects.

-Selection: not really, bc in the religious landmark study, they weren't able to randomly select who walked by which type of building. Maybe more conservative or spiritual people walked past the church leading to the results of ppl walking past churches to be more biased (pg. 396). -Maturation: occurs in a quasi-experimental design with pretest and posttest when an observed change could have emerged more or less spontaneously over time --> design of this quasi-experiment (cosmetic surgery, pg. 398) included a comparison group, and the results indicated that the comparison group did not improve over time; in fact, they got slightly worse on the same variables. Because of the design and the pattern of results, you can probably rule out maturation as an internal validity threat in this study. -History: occurs when an external, historical event happens for everyone in a study at the same time as the treatment --> When quasi-experiments include a comparison group, history threats to internal validity can usually be ruled out. -Regression: occurs when an extreme finding is caused by a combination of random factors that are unlikely to happen in the same combination again, so the extreme finding gets less extreme over time --> Regression is mainly a problem when a group is purposefully selected for its unusually low (or high) mean at pretest. Second, if regression to the mean was the explanation, the surgery group (cosmetic surgery study pg. 401) would have started out lower than the comparison group. -Attrition: becomes an internal validity threat when systematic kinds of people drop out of a study. In the cosmetic surgery study, for example, you might wonder whether people's self-image improved only because individuals who were disappointed with their surgery outcomes stopped responding to the study over time. -Testing: kind of order effect in which participants tend to change as a result of having been tested before. Repeated testing might cause ppl to improve, regardless of the treatment they received. Repeated testing might also cause performance to decline bc of fatigue or boredom. ***a comparison group helps rule out a testing threat to internal validity. -Instrumentation: a measuring instrument could change over repeated uses, and this change would threaten internal validity --> ex: using two versions of a test and one is harder than the other. -Observer bias: experimenters' expectations influence their interpretation of the results. -Experimental demand --> ask WHO measure the behaviors. -Placebo effects: when participants improve only bc they believe they are receiving an effective treatment --> ask whether design of study included a comparison group that received an inert treatment. -Demand characteristics: when participants guess what the study is about and change their behavior in the expected direction --> think about whether participants were able to detect the study's goals and respond accordingly.

Describe three small-N designs (stable-baseline designs, multiple-baseline designs, and reversal designs) and explain how each design addresses internal validity.

-Stable-baseline: observe behavior for an extended baseline period before beginning a treatment or other intervention. If behavior during the baseline is stable, the researcher is more certain of the treatment effectiveness. -Multiple-baseline: stagger introduction of an intervention across a variety of individuals, times, or situations to rule out alternative explanations (Tyner et al., 2016 children with autism and fear of dogs). 1. Internal validity: you can establish a causal claim with multiple baseline because you rule out alternative explanations with shown in 3 as opposed to 1 child, and each child began improvement after therapy was started. -Reversal designs: implement treatment and measure DV, remove treatment and measure DV (addresses maturation, history, and regression). 1. By observing how the behavior changes as the treatment is removed and reintroduced, the researcher can test for internal validity and make a causal statement: If the treatment is really working, behavior should improve only when the treatment is applied.

Review studies with one independent variable, which show a simple "difference."

-Strayer & Drews study on driving and being on the phone: The results showed that when drivers were simply talking on cell phones (not even texting or using apps), their reactions to road hazards were 18% slower. Drivers on cell phones also took longer to regain their speed after slowing down and got into more (virtual) accidents. People drove more poorly while using cell phones. Studies with one independent variable can demonstrate a difference between conditions. These two studies were analyzed with a simple difference score: placebo minus drunk conditions, or cell phone minus control.

Describe an interaction (i.e., as a "difference in differences").

-The mathematical way to describe an interaction of two independent variables is to say that there is a "difference in differences." In the driving example, the difference between the cell phone and control conditions (cell phone minus control) might be different for older drivers than younger drivers OR you like ice cream cold more than you like it hot, but you like pancakes cold less than you like the hot. -Studies with one independent variable can demonstrate a difference between conditions.

Given a factorial notation (e.g., 2x2), identify the number of independent variables, the number of levels of each variable, the number of cells in the design, and the number of main effects and interactions that will be relevant.

-The quantity of numbers indicates the number of independent variables (a 2x3 design is represented with two numbers, 2 and 3). The value of each of the numbers indicates how many levels there are for each independent variable (two levels for one and three levels for the other). When you multiply the two numbers, you get the total number of cells in the design. 1. 2x3 design --> This design has two independent variables (gender & cell phone condition), but one has two levels and the other has three levels (male/female; hands free/no phone/handheld) 2x3=6 cells.

Describe matching, explain its role in establishing internal validity, and explain situations in which matching may be preferred to random assignment.

-To create matched groups, participants are sorted from lowest to highest on some variable and grouped into sets of two. Individuals within each set are then assigned at random to the two experimental groups. -Example: Study on note taking operationalized by GPA; match students from highest to lowest GPA in pairs (starting with the two highest GPAS), randomly assign them to the notetaking conditions. -Successful random assignment spreads these differences out more evenly. It creates a situation in which the experimental groups will become virtually equal, on average, before the independent variable is applied. -The disadvantage is that the matching process requires an extra step; requires more time and often more resources than random assignment.

Interrogate the construct validity of a manipulated (independent) variable in an experiment, and explain the role of manipulation checks in establishing construct validity.

-To interrogate the construct validity of the independent variables, you would ask how well the researchers manipulated (or operationalized) them. In the Mueller and Oppenheimer study, this was straightforward: People were giver either a pen or a laptop. This operationalization clearly manipulated the intended independent variable. -Manipulation check: an extra dependent variable that researchers can insert into an experiment to convince them that their experimental manipulation worked. 1. More likely to be used when the intention is to make participants think or feel certain ways. 2. If you're measuring if students remember funny lectures better than serious ones, a manipulation check could be a survey asking students how funny they thought the "funny" lecture was to make sure that the "funny" lecture was actually funnier than the serious lecture. This is an extra DV that is used to make sure the operationalization worked even though they were interested in studying memory of the lecture rather than how funny it was.

Describe random assignment and explain its role in establishing internal validity.

-Used to avoid selection effects. -Random assignment may not usually create numbers that are perfectly even. However, random assignment almost always works. In fact, simulations have shown that random assignment creates similar groups up to 98% of the time (pg. 285). -Successful random assignment spreads differences out more evenly. It creates a situation in which the experimental groups will become virtually equal, on average, before the independent variable is applied.

Interpret different possible outcomes in cross-lag correlations, and make a causal inference from each pattern.

-When evaluating the relation between evaluations and behaviors, you look and see if the evaluation causes the behavior, or if the behavior causes the evaluation. To do this, compare the correlation coefficients. Whichever is stronger is said to be the primary cause. Both correlations can be significant. See pg. 241-242, figure 9.3.