deck_761476

Question 1

Atminimum, howmany variables are there in an association claim?

Answer 1

.An association that involves exactly two variables.

Question 2

What characteristic of a study’s variablesmakes a study correlational?

Answer 2

They are measured, not manipulated.

Question 3

Sketch three bar graphs: one that would show a positive correlation, one that would show a negativecorrelation, and one that would show a zero correlation.

Answer 3

.

Question 4

When do researcherstypically use a bar graph, as opposed to a scatterplot,to display correlationaldata?

Answer 4

. can guess, maybe ask. most likely if one of the variables is categorical. most likely not to use it if both variables quantitative

Question 5

In one ortwo briefsentences, explain how you would interrogate the construct validity of a bivariatecorrelation.

Answer 5

.Does the measure have good reliability?-Test/Retest, Internal Reliability, Interrater Reliability.Measuring what it intends? What is the evidence for its face validity, its concurrent validity, its discriminant and convergent validity?-Face/Content Validity-Predictive/Concurrent Validity(e.g. Do mothers’ answers to this question correlate with their actual employment history? for maternal employment)-Convergent Validity-Discriminant Validity

Question 6

What are five questions you can ask aboutthe statistical validity of a bivariate correlation?Do all ofthestatistical validity questions apply the same way when bivariate correlations are represented as bargraphs?

Answer 6

.What is the effect size?.Is it statistically significant?.Subgroups within the sample? Is the relationship spurious? Is there a third variable?.Are there outliers?.Is the relationship curvilinear? If slope of pattern is not just a straight line, r does not describe pattern well.

Question 7

Which ofthe three rules of causation is almost alwaysmet by a bivariate correlation? Which two rulesmight not bemet by a correlationalstudy?

Answer 7

.Covariance.Temporal precedence or internal validity

Question 8

Give examples ofsome questions you can ask to evaluate the external validity of a correlationalstudy.

Answer 8

.Can the association generalize to other people, places, and times? Must consider who the participants were and how they were selected. The size of the sample does not matter as much as the way the sample was selected from its population

Question 9

Why can’t a simple bivariate correlationalstudymeet allthree rulesfor establishing causation?

Answer 9

.No time difference between measures!

Question 10

Explain how longitudinal designs are conducted. Why is a longitudinal design called amultivariatedesign?

Answer 10

.Because each measure of one variable at different times is a different variable right.Like, TvViolence2001, TvViolence2011AND, TIME is a THIRD variableSo no matter what you do, it will always be multivariate

Question 11

Identify the three types of correlations in a longitudinal correlational design: cross‐sectionalcorrelations, autocorrelations, and cross‐lag correlations.

Answer 11

.Cross-Sectional: TvViolence2001 & Aggression2001.Autocorrelations: TvViolence2001 & TvViolence2011.Cross-lag: TvViolence2001 & Aggression2011

Question 12

Interpret different possible outcomesin cross‐lag correlations, andmake a causal inference fromeachpattern.

Answer 12

.ASK

Question 13

Explain howmultiple‐regression designs are conducted.Describe in your own words whatitmeanstosay thatsome variable “was controlled for” in amultivariate study.

Answer 13

.LOOK IN TEXT.Control for: Holding p aotential third variable steady while investigating the association between two other variables. Researchers are asking whether, after they take the relationship between the third variable and the outcome (effect) into account, there is still a portion of variability in the outcome (effect) that is attributable to the predictor(cause)

Question 14

Define dependent variables and predictor variablesin the context ofmultiple‐regression data.Howmany dependent variables are there in amultiple‐regression analysis?Howmany predictor variables?

Answer 14

.Criterion: Researchers most interested in understanding or predicting (also called DV in this case).Predictor: Used to explain variance in the dependent/criterion variable (also called IV in this case..only ONE criterion/dependent variable.unlimited predictor/independent variables i assume

Question 15

Identify and interpret data fromamultiple‐regression table and explain, in a sentence, what eachcoefficientmeans. What does a significant betamean? What does a nonsignificant betamean?

Answer 15

When you have only one predictor variable in your model, then beta is equivalent to the correlation coefficient between the predictor and the criterion variable. This SPSS for Psychologists – Chapter Seven 209 equivalence makes sense, as this situation is a correlation between two variables. When you have more than one predictor variable, you cannot compare the contribution of each predictor variable by simply comparing the correlation coefficients. The beta regression coefficient is computed to allow you to make such comparisons and to assess the strength of the relationship between each predictor variable to the criterion variable.

Question 16

Give atleastthree phrasesthatindicate that a study used amultiple regression analysis.

Answer 16

.rl between x & y is negative, even when z IS CONTROLLED FOR.rl between x & y is negative, INDEPENDENT OF the proportion of z.rl between x & y is negative, even when z IS HELD CONSTANT.rl between x & y is negative, and is NOT ATTRIBUTABLE TO THE THIRD VARIABLE OF z, because it holds even when the proportion of z is held constant

Question 17

What are two reasonsthatmultiple regression designs cannot completely establish causation? Explainwhy experiments are superiortomultiple‐regression designsfor controlling forthird variables.

Answer 17

1. Even though multivariate designs analyzed with regression statistics can control for third variables they cannot establish temporal variables, they cannot establish temporal precedence.2. Researchers cannot control for variables that they do not measure.A well-run exp yy erimental study is ultimately more convincing than a correlational study.  The power of random assignment would make the groups likely to be equal on any possible third variable.  A rand i d i t i till th ld domized experiment is still the gold standard for determining causation. Multiple regression allows researchers to control forpotential third variables, but only those that they choose to measure

Question 18

Explain the value of pattern and parsimony in research.

Answer 18

.An approach which allows researchers to investigate causality by using a variety of correlational studies that all point in a single, causal direction. -pattern of results best explained by parsimonious causal explanation-parsimony: simplest explanation of a pattern of data-several diverse predictions are tied back to one central principle = parsimony-does not work for a single study

Question 19

Consider why journalistsmight preferto reportsingle studies,ratherthan parsimonious patterns ofdata. What problemsresultsfromthistendency?

Answer 19

.Trying to find news, and flashy headlines.They usually only report the latest finding. They selectively present only a part of thescientific process.

Question 20

Identify amediation hypothesis and sketch a diagramofthe hypothesized relationship.Describe thestepsfortesting amediation hypothesis.

Answer 20

TESTING FOR A MEDIATING VARIABLEKenny (2008):1.Test for relationship c. 2.Test forrelationship a.3.Test for relationship b. 4.Finally, run a regression test, using both the predictor and mediator variables to predict the criterion, to see whether relationship c goes awayORtest for relationship c, then a, then b-run regression test-relationship btw IV and DV should drop significantly or become zero when mediator is controlled forMULTIVARIATE CORRELATIONAL RESEARCH (look up and understand more if time)

Question 21

Articulate the difference betweenmediators,third variables, andmoderating variables.

Answer 21

.med: “why are these two variables linked?”mod: “are these two variables linked the same way for everyone, or in every situation?”THIRD VARIABLEinternal validity rule, when you can come up with an alternative explanation for the association between two variables, that alternative explanation is the third variable

Question 22

Give an example of a question you would ask to interrogate each ofthe four validitiesfor amultivariatestudy.

Answer 22

.Longitudinal designs help establish temporal precedence, and multivariate provide evidence for internal validity  Should interrogate the construct validity (i.e., how well each variable was measured) external measured), external validity (i.e., how well the results generalize), and the statistical conclusion validity (i e the and the statistical conclusion validity (i.e., the effect size and statistical significance).

Question 23

What are theminimumrequirementsfor a study to be an experiment?

Answer 23

.A study in which one variable is manipulated and the other is measured.

Question 24

In your own words, define the termsindependent variable, dependent variable, and control variable.

Answer 24

.IV = Manipulated in an experiment.DV = Measured.Control = Potential variable experimenter holds constant on purpose

Question 25

How do experimentssatisfy the three causalrules?

Answer 25

.Temporal Precedence: control which variable comes first

Question 26

How are design confounds and control variablesrelated?

Answer 26

Design confounds threaten internal validity and vary systematically with the independent variable; control variables establish internal validity and do not vary at all. If you can identify a potential design confound and eliminate it by keep that factor constant instead (turning it into a control variable) then you would have more confidence that your independent variable actually caused the difference in your dependent variable.

Question 27

Describematching, explain itsrole in establishing internal validity, and explain situationsin whichmatchingmay be preferred to randomassignment.

Answer 27

Matched-subjects design, participants matched into blocks on the basis of a variable the researcher believes relevant to the experiment. Helps eliminate selection effects, or one condition varying systematically in a way tha is different from the other condition

Question 28

Describe how the proceduresfor between‐subjects and within‐subjects experiments are different.Explain the pros and cons of each type of design.

Answer 28

The principal advantage of a within-groups design is that it ensures that the participants in the two treatment groups will be equivalent. As a result, the only difference between the two groups should be attributable to the independent variable, not to individual or personal variables. also INCREASED POWER (ability to detect stat sig effect)

Question 29

Describe how posttest‐only and pretest/posttest designs are both between‐subjects designs. Explainhow they differ, and when a researchermay use each one.

Answer 29

.With random assignment (posttest only), any preexistingdifferences between participants should be distributed evenly across both groups, and their effect canceled out. In some cases, participants might become suspicious if they are asked to complete the same thing twice.  The pretesting step is useful if researchers want to be extra sure that groups are equivalent at the outset

Question 30

What are the two simple forms of within‐subjects designs?

Answer 30

.concurrent-measures design: An experiment usi i hi ing awithin-groups d i i hi h design in which participants are exposed to all the levels of an independent variable at roughly the same time, and a single attitudinal or behavioral preference is the dependent variable. (taste coke taste pepsi, choose favorite)Repeated-measures designs: An experiment with a within-groups design in which participants respond to a dependent variable more than once, after exposure to each level of the independent variable.

Question 31

Describe counterbalancing, and explain itsrole in the internal validity of a within‐subjects design.

Answer 31

.Counterbalancing: Presenting the levels of the independent variable to participants in different orders to control for order effects.

Question 32

How domanipulation checks provide evidence forthe construct validity of an experiment? Why doestheorymatter as you evaluate construct validity?

Answer 32

.ASK

Question 33

Explain why experimenters usually prioritize internal validity over external validity when itis difficulttoachieve both.

Answer 33

.b/c without internal validity, your results are meaningless regardless of wethere or not your experiment is externally valid

Question 34

Cohen’s D equivalents to r

Answer 34

d = strength = r.20 = weak/small = .10.50 = moderate/medium = .30.80 = strong/large = .50

Question 35

Summarize the three threatsto internal validity thatthissection has covered.

Answer 35

design confounds, selection effects, order effects

Question 36

Review three threatsto internal validity: design confounds,selection effects, and order effects. Whatparticular problems do these threats pose?

Answer 36

.

Question 37

Whatis a one‐group, pretest/posttest design, and which threatsto internal validity are especiallyapplicable to this design?

Answer 37

.One-group, pretest/posttest design: A study in which a researcher recruits one group of pp p p articipants; measures them on a pretest; exposes them to a treatment, intervention, or change; and then measures them on a posttest. Threats to internal validity that especially apply to this design:  Maturation, history, regression, attrition, testing, and instrumentation.

Question 38

Indicate which ofthe threatsto internal validity would be relevant even to a two‐group, posttest‐onlydesign.

Answer 38

Observer bias, demand characteristics, placebo effect

Question 39

Explain how comparison groups, double‐blind studies, and other design choices can help researchersavoidmany ofthese threatsto internal validity.

Answer 39

 Double-blind study: A study in which neither the participants nor the researchers who evaluate them know who is in the treatment group and who is in the comparison group. When a double-blind study is not possible a blind study is not possible, a variation might be an acceptable alternative. K i g b bli d t diti i Keeping observers blind to condition is evenmore important when they are rating behaviors th t diffi lt t d that are more difficult to code.

Question 40

Articulate the reasonsthat a studymightresultin null effects: not enough variance between groups,toomuch variance within groups, or a true null effect.

Answer 40

 The independent variable really does not affect the dependent variable. The study was not designed well enough. Some obscuring factor in the study prevented the researchers from detecting the covariance.Not enuf b/t groups variance: Weak manipulations, insensitive measures, and reverse confounds might prevent an experiment from detecting a true difference that exists between 2 or more experimental groups.  Important to ask about construct validity: Was the independent variable manipulation strong enough to cause a difference between groups? Was the dependent variable measure sensitive enough to detect that difference?

Question 41

Describe atleasttwo waysthat a studymightshow inadequate variance between groups, and indicatehow researchers can identify such problems.How can a studymaximize variability betweenindependent variable groups? (There are four ways.)

Answer 41

Everything you have here is related to the issue of between-group differences, but these are really ways of identifying problems with the manipulation, rather than manimizing the variability between groups.The more unsystematic variability there is within each group, the more the scores in the two groups overlap with each other. And the more they overlap, the less apparent the average difference is. Most researchers prefer to keep within-group variability to a minimum, so that they can more easily detect between-group differences.To maximize variability between groups you could:- use measures and manipulations with excellent reliability and validity. Using manipulation checks (as you suggested) can help to determine the validity of your manipulations (e.g., make sure the manipulation is strong enough); using measures with good construct validity (while eliminating ceiling and floor effects) will help to detect differences between groups.- control for within-group differences by using a within-subjects or matched design- add more participants (reduces the impact of individual differences and helps reduce the impact of measurement error)- control the external situation to eliminate situation noise—-.Floor/Ceiling effects.Noisy dataWeak manipulations, insensitive measures, and reverse confounds might prevent an experiment from detecting a true difference that exists between 2 or more experimental groups.  Important to ask about construct validity: Was the independent variable manipulation strong enough to cause a difference between groups? Was the dependent variable measure sensitive enough to detect that difference?

Question 42

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

Answer 42

.TOO MUCH NOISE! measurement error?

Question 43

Describe three causes of within‐group variance— measurement error, individual differences, andsituation noise.How can a studyminimize variability within groups? (There are three ways.)

Answer 43

.meas error: use reliable measurements, measure more instances.indiv diff: change design, use either within-groups or matched-groups designadd more participants.sit noise: control irrelevant events, sounds, distractions

Question 44

In your own words, describe why Wansink’sstudy on price and package size was a factorial design.

Answer 44

.Two IVs with 2 levels, creates 4 conditions, it’s a 2x2 factorial design, DV measured in each condition

Question 45

Review studies with one independent variable, which show a simple “difference.”Describe aninteraction as a “difference in differences.”

Answer 45

a / b—–c / deach are values of the DV in that condition, a 2x2 factorial designtake values a & c, get differencetake values b & d, get differencenow compare those two values. if they are significantly different, you have an interaction

Question 46

Describe interactions in terms of “it depends.”

Answer 46

.ASK

Question 47

How can you detectmain effects and an interaction froma table ofmeans? Froma line graph? Fromabar graph?

Answer 47

Table of Means-ME = difference between means/avgs of all DVs in each condition of an IV-Int = Difference between difference of DVs in either condition…Line Graph: Parallel slopes (ME), Diff slopes (INT)Bar Graph Same… same.

Question 48

Describe how the same 2 × 2 designmight be conducted as a between‐subjectsfactorial, a within‐subjectsfactorial, or amixed factorial design.

Answer 48

between = 4 diff groupswithin = 1 participant for each 4 conditionsmixed = could have two groups, and they each experience the second IV’s two conditions

Question 49

Indicate how the different designs change the number of participantsrequired: Which design requiresthemost? Which requiresthe fewest?

Answer 49

.Matched factorial design has largest requirement. if 3x2, there are 6 conditions. there must be 6 people in each condition. so that would be 36, minimum, other designs don’t suffer from this requirement.

Question 50

Given a factorial notation (e.g., 2 × 2), identify the number ofindependent variables,the number oflevels of each variable,the number of cellsin the design, and the number ofmain effects andinteractionsthat will be relevant

Answer 50

2 X 3: There are 2 independent variables. The first one has 2 levels and the second one has 3. There are 6 cells. There are 2 main effects and one 2-way interaction.3 X 2 X 4: There are 3 independent variables. The first one has 3 levels, the second has 2, and the third has 4. There are 24 cells. There are 3 main effects and three 2-way interactions as well as one 3-way interaction. ORa x b x ca main effectb main effectc main effecta-b interactiona-c interactionb-c interactiona-b-c interaction

Question 51

Why is amain effect better called an “overall effect”?

Answer 51

.DUNNO

Question 52

Explain the basic logic ofthree‐way factorial designs.

Answer 52

• for some research questions, researchers find it necessary to have three (or even more) independent variables in a crossed factorial design.- the variables can be manipulated either as between-subjects or within-subjects.- When a factorial design has three independent variables, the number of differences to be investigated increases dramatically. In a three-way design, we will be looking at three main effects (one for each independent variable), plus three separate two-way interactions and a three-way interaction.

Question 53

How can you determine,froma graph, whether a study shows a three‐way interaction

Answer 53

.YESIf it is significant, means that the two-way interaction between two of the independent variables depends on the level of the third independent variable.Remember, light traffic, the interaction was present (age & cell use). heavy traffic, it was not.

Question 54

Explain how quasi‐experiments can be either between‐subjects designs or within‐subjects designs.

Answer 54

.

Question 55

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

Answer 55

Nonequivalent control group design: A quasiexperiment that has at least one treatment group and one comparison group, but participants have not been randomly assigned to the two groups. Interrupted time-series design: A quasiexperiment in which people are measured repeatedly on a dependent variable before, during, and after the “interruption” caused by some event.Nonequivalent groups interrupted time-series design: A quasi-experiment with two or more groups in which (1) participants have not been randomly assigned to groups; (2) participants are measured repeatedly on a dependent variable before, during, and after the “interruption interruption caused by some event; and (3) ” caused by some event; and (3) the presence or timing of the interrupting event differs among the groups.

Question 56

How is a nonequivalent control groups design differentfroma true between‐subjects experiment?

Answer 56

.No random assignment, dude

Question 57

How are interrupted time‐series designs and nonequivalent control groupsinterrupted time‐seriesdesigns differentfromtrue within‐subjects experiments?

Answer 57

.

Question 58

Explain whether quasi‐experimentalstudies avoid the following threatsto internal validity:selection,maturation, history,regression, attrition,testing, instrumentation, observer bias, experimental demand,and placebo effects.

Answer 58

.

Question 59

Describe why both the design and the results of a study are importantfor assessing a quasi‐experiment’sinternal validity.

Answer 59

For question #6 your response is also incorrect. Quasi-experiments can take a variety of designs, and the support that a quasi-experiment provides for a causal claim depends partly on its design and partly on the results a researcher obtains. Both of these contribute to our ability to rule out alternative explanations (and thus establish internal validity), but the way they do so depends on the design. You should be able to tell me how the design and the results would rule out various internal validity threats for each type of design (as we discussed in class).

Question 60

What are three reasonsthat a researchermight conduct a quasi‐experiment,ratherthan a trueexperiment,to study a research question? Explain the trade‐offs(i.e.,sacrifices or disadvantages) ofusing a quasi‐experimental design.

Answer 60

.1. Quasi-experiments enable researchers to take advantage of real-world opportunities to study interesting phenomena and events.2. These designs can enhance external validity: the likelihood that the patterns observed will generalize to other settings and to other individuals.3. Many questions of interest to researchers would be unethical to study in a true experiment

Question 61

Interrogate quasi‐experimental designs by asking about construct validity, external validity, andstatistical validity.

Answer 61

Often, quasi-experiments show excellent construct validity for the independent variable.  Also need to ask how well the dependent variables were measured.  Statistical validity: We would ask how large the group differences were (the effect size) and whether the results were statistically significant. These designs can enhance external validity: the likelihood that the patterns observed will generalize to other settings and to other individuals.

Question 62

Explain three differences between small‐Nand large‐Nexperiments.

Answer 62

.Large-N vs Small N Participants are grouped. The data from an individual  Each participant is treated as a separate experiment. Small-N participant are not of interest in themselves; data from all participants in each group are bi d d t di d designs are almost always repeated-measures designs, in which researchers observe how combined and studied th i l d t together. Data are represented as group gthe person or animal responds toseveral systematically designed conditions.averages. I di id l ’ d t td Researchers decide whether a result is replicable by doing a t t f t ti ti l ig ifi Individuals’ data are presented. Researchers decide whether a result is replicable by repeating th i t test of statistical significance. the experiment on a newparticipant.

Question 63

Describe three small‐Ndesigns(stable‐baseline designs,multiple‐baseline designs, and reversal designs)and explain how each design addressesinternal validity.

Answer 63

Stable-baseline design: A study in which a researcher observes 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’s effectiveness. Multiple Multiple-baseline design: A small-N design in which researchers stagger their introduction of an intervention across a variety of contexts, times, or situations. Reversal design: A study in which a researcher observes a problem behavior both before and during treatment and then discontinues the treatment for a while to see if t he problem behavior returns.

Question 64

Give examples of questions you would ask about a small‐Ndesign to interrogate allfour big validities

Answer 64

 Internal validity? Careful, within-subject experiments that allowed them to draw causal conclusions.  Usually measured behaviors repeatedly both before measured behaviors repeatedly, both before and after some intervention or manipulation. External validity? Can triangulate by combining the results of small-Nstudies with other studies on animals or on larger groups. Researchers are able to specify the population to which they want to generalize.  Sometimes researchers do not care about generalizing Construct validity?  Is fairly straightforward when researchers are recording what people drew, what objects they picked up, what they said or how said, or how many words or numbers people remembered.  Trickier for observations.  Statistical validity?  Do not typically use traditional inferential statistics.  A graph may provide enough quantitative evidence. Can replicate the study.  Can think about effect sizes in terms of margin of improvement.

Question 65

Explain the trade‐offs of using a small‐Ndesign.

Answer 65

.One problem is that a few participants may not represent the human population very well. External validity issue.

Question 66

How do inferentialstatistics help researchers estimate whethertheirstudies are replicable?

Answer 66

.Inferential statistics: A set of techniques that uses chance and probability to help researchers make decisions about what their data mean and what i f th k f th inferences they can make from them.« If p 05 h l i i i ll i ifi Th .05, the result is not statistically significant. Theresearcher cannot rule out the possibility that the result is a chance occurrence from a p poulation in which there is no relationship��

Question 67

Describe how the three types ofreplication studies are similar and different.

Answer 67

1. Direct replication (or exact replication): A replication study in which researchers repeat the original study as closely as possible to see whether the original effect shows up in the newly collected data. ´ E.g., Bargh, Chen, and Burrows (1996): Do ste eotypes o soc a g oups c a ge peop e s reotypes of social groups change people’sbehavior?�2. Conceptual replication: A replication study in which researchers examine the same research question (the same concepts) but use different procedures for operationalizing the variables.  E.g., Elliot and colleagues’ (2007): Does the color red a ect sc oo pe o a ce affect school performance?3.. Replication Replication-plus-extension: A replication study in which researchers replicate their original study but add variables to test additional questions. Eg .., Strayer Strayer and Drews (2004): Does talking on a (2004): Does talking on a cell phone influence driving performance?

Question 68

In your own words, describe the steps a researcherfollowsin ameta‐analysis. What can ameta‐analysistell us?

Answer 68

Meta-analysis: A way of mathematically averaging the results of all the studies that have tested the same variables to see what conclusion that whole body of evidence supports.  Summarize the literature in a mathematical way

Question 69

Give examples of how external validity applies both to other participants and to othersettings

Answer 69

 When researchers test their questions using slightly different methods, different kinds of participants, or different situations, or when they extend their research to study new variables, they are demonstrating how their results generalize to other populations and settings.1.  If a study is intended to generalize to some population, the researchers must draw a probability sample from that population. Remember it’s a population, not thepopulation. External validity comes from how, not how many2.  Conceptual replications illustrate this aspect of external validity very well.  Sometimes we want to know whether a laboratory situation created for a study generalizes to real-world settings world settings. Ecological validity (or mundane realism): The extent to which the tasks and manipulations of a study are similar to real-world contexts.

Question 70

In your own words, describe the difference between generalizationmode and theory‐testingmode.

Answer 70

 Theory-testing mode: The testing of association claims or causal claims to investigate support for a theory. In theory-testing mode, external validity matters much less than internal validity. Example: Harlow’s (1958) classic study of attachment in infant monkeys Generalization mode: The intent of researchers to generalize the findings from the samples and p y pp rocedures in their study to other populations or contexts. Applied research tends to be done in generalization mode, and basic research tends to be done in theory-testing mode. Survey research that is intended to support frequency g claims is done in generalization mode

Question 71

Which ofthe three types of claims(frequency, association, or causal)is almost always conducted ingeneralizationmode? Which ofthe three claims are usually conducted in theory‐testingmode?

Answer 71

. Most of the time, association and causal claims are conducted in theory-testing mode.  But researchers sometimes conduct them in generalization mode, too. E g T ti g h th E.g., Testing whether a th ‘ ff ti therapy’s effectivenessgeneralizes to other populations. FREQUENCY in generalization?

Question 72

Explain why researchers who are operating in theory‐testingmodemight not attemptto use a randomsample in theirresearch. What validity are they prioritizing? What aspects oftheirresearch are theyemphasizing (for now)?

Answer 72

.Internal Validity!

Question 73

Summarize the goal of cultural psychology. What doesthisfield suggest about working in theory‐testingand generalizationmodes?

Answer 73

Cultural psychologists have frequently questioned the universality of results obtained by researchers who operate exclusively in theory-testing mode. While they understand why theory-testing mode focuses on internal validity, and that research conducted in this mode does not necessarily assume generalizability (and sometimes generalizability doesn’t matter), cultural psychologists point out that a theory that has been supported by a study in one human sample will not necessarily hold true for human beings in general. In contrast, cultural psychologists have shown that many theories may be supported in some cultural contexts but not in others. Indeed, cultural psychologists have collected dozens of examples of theories that were supported by data in one cultural context but not in any other cultural context. Sometimes cultural psychologists work in the generalization mode, but most combine the generalization mode with theory-testing mode - to test a theory in multiple cultures. .Not looking for huge external validity… because they’re looking at the differences between cultures!

Question 74

Reevaluate two common assumptionsfromthe perspectives of generalizationmode and theory‐testingmode:thatimportantstudies use diverse,randomsamples and thatimportantstudiestake place in real‐world settings.

Answer 74

.Only if external validity is a seriously huge super big priority.Theory-testing mode:

Question 75

Strengths of r

Answer 75

+/- .10 = small or weak+/- .30 = Medium, or moderate+/- .50 = Large, or strong

Question 76

Point-biserial correlation

Answer 76

A statistical test used for evaluating the association between one categorical variable and one quantitative variable.

Question 77

Phi coefficient:

Answer 77

A statistical test designed to evaluate the association between two categorical variables

Question 78

describe random assignment and its role in establishing internal validity

Answer 78

With random assig , yp g nment, any preexistingdifferences between participants should be distributed evenly across both groups, and their effect canceled out.

Question 79

In your own words,summarize all ofthe advantages and disadvantages of within‐subjects designs(hint:there are 3 of each).

Answer 79

.disadv:1. The potential for order effects.2. Demand characteristics: Cues that lead participants to guess a study participants to guess a study s hypotheses or ‘s hypotheses or goals.3. A within-groups design might be impossible..adv:1. Need less participants2. Easier to find a significant effect (greater power).3. ensures participant in each treatment group is equivalentThe principal advantage of a within-groups design is that it ensures that the participants in the two treatment groups will be equivalentPOWER, easier to detect stat sig restults

Question 80

Television/Larceny Study (Quasi and Small-N Designs)

Answer 80

In the early days of television in the United States, individual cities had to apply for a license to transmit television signals. After issuing licenses up to 1949, the Federal Communications Commission (FCC) stopped issuing broadcasting licenses for 3 years (from 1949 to 1952); therefore, in the early 1950s, some U.S. cities had access to television, but others did not. Years later, some clever researchers (Hennigan et aI., 1982) took advantage of this situation to study crime rates in cities with and without television. Specifically, they measured whether rates of larceny rose in a city in the months after television became available. This quasi-experiment has an independent variable (television exposure) and a dependent variable (larceny rates). The researchers measured larceny rates both before and after the introduction of television. This independent variable (the introduction of television) was not controlled by the researchers but instead was a historical event. The lack of full experimenter control is what made the study a quasi-experiment. In this study, the researchers also compared larceny rates in cities that had television with rates in cities that did not- an independent-groups comparison. This independent-groups manipulation of the independent variable was not controlled by the researchers, either: Cities were not randomly assigned to have access to television or not; instead, the FCC had inadvertently assigned cities to these two groups by imposing the freeze on new television licenses. Therefore, the comparison groups in the independent-groups part of the study were also quasi-experimental. The results of this analysis are shown in this figure. Notice that larceny rates rose right after 1951, but only in cities that had access to television. After 1955, however, larceny rates showed a similar increase only in those cities that had just acquired television.

Question 81

Do quasi-experiments = correlational studies?

Answer 81

 When a quasi-experiment uses a between-groups design, the groups in the study can look similar to those in correlational studies. Quasi-experiments and experiments and correlational correlational designs also designs also have similar internal validity concerns.  Whereas correlational researchers p y rimarilymeasure variables in a sample and analyze their relationships, quasi-experimental researchers more actively select groups for an independent variable so they can achieve a greater degree of internal validity.