A. Results

B. Reference

C. Method

D. Introduction

A. an explanation of a phenonema.

B. cannot be tested with the scientific method.

C. the same as a prediction.

D. all of the above.

A. survey

B. archival

C. systematic

D. naturalistic

A. the theories are too unusual.

B. the theories do not specify causes for behavior.

C. the theories are not the simplest explanations for behavior.

D. the theories are difficult to falsify.

A. Applied; basic

B. External; internal

C. Internal; external

D. Basic; applied

A. parsimony.

B. construct validity.

C. inter-rater reliability.

D. test-retest validity.

A. inter-rater reliability.

B. parsimony.

C. construct validity.

D. test-retest validity.

A. reliability.

B. an independent variable.

C. maturation.

D. an operational definition.

A. nominal

B. ordinal

C. interval

D. ratio

A. a dependent variable.

B. an independent variable.

C. a confounding variable.

D. a subject variable.

A. stratified random sample

B. simple random sample

C. volunteer sample

D. none of the above (all are equivalent in terms of sampling error)

True

False

What scale of measurement is the independent variable?

A. ordinal

B. nominal

C. ratio

D. interval

The independent variable in this study is _________, and the dependent variable is __________.

A. 20 min; the study list

B. activity group; memory

C. memory; activity group

D. the study list; 20 min

A. none of the participants were willing to shock the confederate.

B. most participants quit the study before it concluded.

C. most of the participants were willing to “shock” the confederate at the highest level.

D. all of the participants were willing to “shock” the confederate at the highest level.

True

False

A. All data must be collected anonymously (no identifying information is gathered).

B. The study must be designed to minimize harm to the participant.

C. The benefit of the research must outweigh the risks.

D. (b) and (c) only

E. all of the above

A. use of monkeys

B. use of untrained personnel

C. release of the animals into the wild at the completion of the study

D. both (b) and (c)

E. all of the above

A. a review board at each institution where research is conducted (IRB).

B. a committee that is part of the federal government.

C. a group of judges.

D. just the researchers themselves.

True

False

A. main effects.

B. non-significant results.

C. interaction effects.

A. ANOVA.

B. interaction effect.

C. main effect.

D. dependent variable.

A. two

B. four

C. one

D. three

A. predictive

B. descriptive

C. causal

A. non-psychological/psychological

B. “naturally”-occurring/researcher-implemented

C. psychological/non-psychological

D. researcher-implemented/”naturally”-occurring

A. include groups that do not take the pretest.

B. include a randomly assigned control group.

C. include groups that do not take the posttest.

D. compare a pattern of scores over time before and after the treatment.

A. Quasi-experiments are more internally valid than experiments.

B. Some independent variables cannot be manipulated due to ethical concerns.

C. Age is their variable of interest.

D. Both (a) and (b).

E. Both (b) and (c).

B. Some independent variables cannot be manipulated due to ethical concerns.

C. Age is their variable of interest.

True

False

A. cross-sectional

B. cohort-sequential

C. longitudinal

D. experimental

A. nonresponse error

B. coverage error

C. social desirability bias

D. testing effects

E. all of the above

A. intuition.

B. authority figures.

C. logic.

D. observations.

A. nominal scales have numerical response categories and ordinal scales do not.

B. responses on ordinal scales can be rank ordered and responses on nominal scales cannot be rank ordered.

C. nominal scales include zero as the lowest possible score and ordinal scales do not.

D. both (a) and (b).

IV A Level 1 IV A Level 2

IV B Level 1 50 50

IV B Level 2 75 75

A. main effect of IV A only.

B. main effect of IV B only.

C. interaction effect only.

D. all of the above effects appear to be present.

A. “naturally”-occurring/researcher-implemented

B. non-psychological/psychological

C. psychological/non-psychological

D. researcher-implemented/”naturally”-occurring

A. Exercise mediates the relationship between fidgeting and obesity

B. Fidgeting and obesity mediate the effects of exercise

C. People who don’t exercise should try fidgeting to lose weight

A. case study

B. correlational

C. experimental

D. observational

A. correlational research.

B. manipulated variables.

C. main effects of humor enjoyment.

D. an operational definition of laughter.

A. multiple t-tests.

B. a single-factor design.

C. five conditions.

D. repeated measures.

A. a time series design.

B. a quasi-experimental variable.

C. a within-subjects design.

D. a cross-sectional design.

A. your measurements correlate with one another.

B. your operational definitions relate to the underlying concepts you are trying to measure.

C. your statistical tests help you answer your research questionss.

D. your manipulation results in a change in the outcome.

A. between-group variance … total variance

B. between subject variance … error effects

C. between group variance … within group variance

D. between subject variance … within subject variance

A. quota sample.

B. convenience sample

C. stratified sample.

D. systematic sample.

A. literature searches

B. independent variables

C. hypothetical constructs

D. operational definitions

A. aspirational goals.

B. principles of responsiblity

C. ethical standards.

D. ethico-legal principles.

A. between group variance … within group variance

B. between subject variance … error effects

C. between-group variance … total variance

D. between subject variance … within subject variance

A. post-hoc tests.

B. regression.

C. correlation.

D. multiple t-tests.

A. objective.

B. intuitive.

C. data driven.

D. predicted.

A. manipulated variable.

B. criterion variable.

C. confirmatory varible.

D. predictor variable.

A. Stretching prevents injuries

B. Stretching makes injuries worse

C. Having an injury makes people want to stretch more

D. Stretching can predict one quarter of the variance in running injuries

A. ensure that all responses are anonymous and confidential.

B. let respondents know from the very beginning that once they begin their participation, they need to continue with the project.

C. remember that if the researcher makes a big point of assuring confidentiality and anonymity, it may needlessly arouse suspicious among resondents.

D. avoid asking questions of a sensitive nature.

A. dividing the population into subgroups and randomly selecting from each subgroup.

B. randomly selecting participants from the names of everybody in your population.

C. creating clusters of people in the population and selecting everybody from randomly chosen clusters.

D. using chain-referral sampling.

A. stratified sample.

B. convenience sample

C. quota sample.

D. systematic sample.

A. cross-sectional design.

B. cohort-sequential design.

C. multiple baseline design.

D. longitudinal design.

A. a closed-ended question.

B. an open-ended question.

C. a ratio question.

D. a Likert question.

A. quasi-experiments.

B. experiments.

C. observational research.

D. correlational research.

A. hypothetical constructs

B. independent variables

C. literature searches

D. operational definitions

A. between-subjects

B. single-subjects

C. within-subjects

D. matched groups

A. They can become confounding variables and they can increase the variability.

B. Individual differences are not a problem in a within-subjects design.

C. They can become confounding variables.

D. They can increase the variability.

A. covariation

B. internal validity

C. temporal precedence

D. random assignment to groups

internal validity is about the causal link. while all 3: temporal precedence, internal validity and covariation are all necessary for causation, this specific concern is internal validity.

A. placebo effect.

B. experimenter bias.

C. Hawthorne effect.

D. external invalidity.

A. Students’ auditory sensitivity

B. Students’ GPA

C. Students’ music preferences

A. order effects are not properly controlled

B. it’s hard to find a matching variable

C. less power than with simple random order

D. too many groups may be needed

A. Matched subjects

B. Repeated measures

C. Independent groups

D. Ex post facto design

A. between-groups design.

B. cross-sectional design.

C. within-subjects design.

D. nonequivalent groups design.

A. internal validity.

B. external validity.

C. statistical validity.

A. your operational definitions relate to the underlying concepts you are trying to measure.

B. your measurements correlate with one another.

C. your statistical tests help you answer your research questionss.

D. your manipulation results in a change in the outcome.

A. instrumentation

B. history

C. regression to the mean

D. maturation

A. Diffusion of treatment

B. Different attrition rates

C. Possible regression effects

A. You don’t test subjects more than once

B. They can be eliminated statistically

C. There’s no opportunity for them to occur

D. The effects should be the same for all groups

A. your statistical tests help you answer your research questionss.

B. your operational definitions relate to the underlying concepts you are trying to measure.

C. your measurements correlate with one another.

D. your manipulation results in a change in the outcome.

A. 1

B. 2

C. 4

D. 5

E. 3

F. 6

A. random order

B. Latin square design

C. counterbalancing

D. switching to a between subjects design

E. increasing sample size

A. 1

B. 6

C. 5

D. 3

E. 2

F. 4

A. 10

B. 20

C. 30

D. 40

E. 50

F. 60

A. single-factor design

B. two-factor design

C. three-factor design

D. factorial design

A. is never a manipulated variable.

B. can have any number of levels.

C. has at most two levels.

D. is a subject variable.

A. extraneous variables.

B. dependent variables.

C. manipulated variables.

D. factorial variables.

A. information about the statistical tests used to analyze the data.

B. a statement about the research hypotheses.

C. the number and types of participants.

D. an integration of the data with theory.

A. an extraneous variable

B. a dependent variable

C. a quasi-independent variable

D. a confounding variable

A. confounding

B. dependent

C. independent

D. extraneous

A. a time series design.

B. a quasi-experimental variable.

C. a within-subjects design.

D. a cross-sectional design.

A. a correlational design.

B. a one-group pretest-posttest design.

C. a nonequivalent group control design.

D. a noninterrupted time series design

A. selection.

B. history.

C. regression to the mean.

D. maturation.

a. Identify the likely dependent variable, and a way of operationalizing that dependent variable. Be specific.

b. Identify the independent variable and the most likely levels of that independent variable

c. What kinds of variables are these (discrete vs. continuous, and scales of measurement)

d. What kind of research methodology is this?

A psychologist was interested in studying the effects of the dependent variable of caffeine on hours of sleep, and he used an interval scale to measure sleep.

a. Do you believe that all students must complete two semesters of English composition, regardless of their writing skills?

b. How often do you get drunk?

(a) A child’s understanding of other children’s feelings

(b) Teachers’ ratings of a child’s social adjustment

(c) A child’s score on a test of social adjustment

(a) Stretching prevents injuries

(b) Stretching makes injuries worse

(c) Having an injury makes people want to stretch more

(d) Stretching can predict one quarter of the variance in running injuries

(a) Exercise mediates the relationship between fidgeting and obesity

(b) Fidgeting and obesity mediate the effects of exercise

(c) People who don’t exercise should try fidgeting to lose weight

(a) Excessive binge drinking contributes to poorer academic performance

(b) Binge drinking is a common reaction to poor academic performance

(c) Both are OK

(d) Neither is OK

(a) Better academic counseling would be an effective way to reduce binge drinking

(b) The students most likely to engage in binge drinking are those doing poorly in school

(c) Both are OK

(d) Neither is OK

(a) zero

(b) 50%

(c) 100%

(d) more than 50%

(a) Statistical validity

(b) Internal validity

(c) External validity

(a) Possible regression effects

(b) Diffusion of treatment

(c) Different attrition rates

(a) history

(b) maturation

(c) regression to the mean

(d) instrumentation

(a) internal validity.

(b) external validity.

(c) statistical validity.

(d) internal, external, and statistical validity

(a) control for order effects

(b) control participants’ expectations

(c) increase the reliability of her attitude measurement

(a) Possible subject and experimenter bias

(b) There was no control group

(c) The sample size was too small

(a) Use of an ad hoc sample

(b) Failure to use random selection

(c) Failure to use random assignment

(a) Students’ GPA

(b) Students’ auditory sensitivity

(c) Students’ music preferences

(a) between subject variance … within subject variance

(b) between subject variance … error effects

(c) between group variance … within group variance

(d) between-group variance … total variance

(a) Independent groups

(b) Matched subjects

(c) Repeated measures

(d) Ex post facto design

(a) It’s not a repeated measures design

(b) Regression effects are random error

(c) There would be no regression to the mean

(d) Randomization equates any regression effects

(a) single-subjects

(b) between-subjects

(c) within-subjects

(d) matched groups

(a) They can become confounding variables.

(b) They can increase the variability.

(c) They can become confounding variables and they can increase the variability.

(d) Individual differences are not a problem in a within-subjects design.

(a) less power than with simple randomizing

(b) it’s hard to find a matching variable

(c) order effects are not properly controlled

(d) too many groups may be needed

(a) They can be eliminated statistically

(b) There’s no opportunity for them to occur

(c) You don’t test subjects more than once

(d) The effects should be the same for all groups

(a) single-factor design

(b) two-factor design

(c) three-factor design

(d) factorial design

< shape graph x-axis (1day/1week) y-axis (imagery/no-imagery) What effects did Oscar find in his analysis? (a) An interaction only (b) Two main effects only (c) Two main effects and an interaction

X shaped graph

x-axis (gender) y-axis (pol. party)

(a) A main effect for party

(b) A main effect for sex

(c) An interaction of sex and party