Exam 2

Question 1

What are the four maxims that guide research participants’ interpretations when they are involved in an experiment?

Answer 1

1. Relation - want to make contribution to research, take into account context of questions
2. Quantity - will give only info researcher asks for, no more
3. Manner - contribution clear, researcher had a purpose in designing Qs
4. Quality - assume truthfulness, no deceit

Question 2

What were the key studies that prompted the development of ethical guidelines?

Answer 2

Milgram’s obedience study - extreme stress, psychological damage
Zimbardo’s prison study - extreme stress, psychological damage, danger
Micturation delay study (bathroom, personal space) - no consent
Humphrey’s study on gays - breach of privacy, no anonymity
*any deception is unethical - deontological position
*benefits must outweigh costs - utilitarian

Question 3

What is debriefing?

Answer 3

Educate participant, completely explain purpose
Identify deception and explain
Query participants about responses
Address concerns

Question 4

What is process debriefing?

Answer 4

More exact (ask them about their logical processes)
Major deceptions, unexpected behavior
Necessary for receipt of performance
May need to be iterative process

Question 5

What are the defining features of the correlational research method?

Answer 5

Measuring 2 or more variables

Change in 1 variable associated with another - one variable assumed to be cause (correlation does not imply causation)

Question 6

What are the different types of variables that can be tested using the correlational method?

Answer 6

Predictor: causal factor (like IV)
Criteria: outcome variable (like DV)

Question 7

What is the difference between a categorical/continuous variable and a discrete variable?

Answer 7

Continuous: can take on any value between two values (1, 1.25, 3.4444…) ex. intelligence
Discrete: only integers (1, 2, 3…) ex. gender

Question 8

What is the causal inference problem?

Answer 8

statistical relationship could reflect multiple possible causal relationships
motivation -> performance, motivation performance

Question 9

What is the third variable problem?

Answer 9

Another variable might be influencing your results
self-esteem -> performance (what else could be affecting it?)
ex. polio - thought to be caused by diet, really just more seasonal outbreaks

Question 10

What is the importance of looking for non-linear relationships among variables?

Answer 10

correlation only examines linear relationship - can miss out on different relationships
theory may posit another type
formulas you use to test for other relationships
curvilinear relationships (ex. stress and arousal)

Leary:

Question 11

What are the guidelines for interpreting the size of correlations? What factors should be taken into consideration?

Answer 11

|.1| = small
|.3| = medium
|.5| = large

take into account:
size predicted by theory
were vars assessed by different methods?
sample size
small correlations can be meaningful

Question 12

What is restriction of range?

Answer 12

Due to sample, one or both variables fail to show complete variation
ex. SAT & 1st year GPA - Clemson’s sample will only have medium to high range SAT scores based on acceptance

Question 13

What is the difference between a mediator and a moderator?

Answer 13

Mediation: what accounts for the relationship between 2 variables; “responsible for”
Moderation: relationship between 2 variables influenced by 3rd variable; “strength of relationship”

Question 14

What are the strengths of a longitudinal design?

Answer 14

Measure the same variables at two points in time; look at patterns of correlation

Question 15

What is the logic behind multiple regression?

Answer 15

use of 1+ variables to predict another variable

better prediction with predictors that account for unique variance (doesn’t share with other predictors)

Question 16

What are the four types of multiple regression?

Answer 16

1. Standard: all variables go in at once, 3 or 4 max
2. Stepwise: highest correlation goes in first (order, one-at-a-time, lots of variables)
3. Hierarchical: order based on theoretical relevance
4. Logistic: categorical (binary) outcome, focus on accuracy of predicting 2 groups (ex. graduated or not)

Question 17

What are the defining features of experimental research?

Answer 17

IV must be manipulated

Random assignment

Question 18

Why are control groups important?

Answer 18

Control group receives exact treatment as IV, but “zero level” of IV
Placebo effect: tendency for people to report a treatment has benefitted them regardless of whether or not treatment is present
Control group important so you have a baseline to compare experimental group to, placebo to see if effects are real or in their head

Question 19

Why are manipulation checks important?

Answer 19

increases validity
just because you manipulate the situation does not mean you are manipulating the IV
ensure manipulation of IV was effective
Usually come in the form of questions completed at the end of the study to assess effectiveness
(ex. to what extent were you thinking of yourself as a female during this imposter syndrome experiment”)

Question 20

What is error variance?

Answer 20

cannot be avoided

numerous influences on DV not related to TV (ex. mood, time of day, personality)

Question 21

What is a confound?

Answer 21

factor you unintentionally manipulate with your IV that may account for relationship between IV & DV
ex. time management training, control training -> how well you do in this class

Question 22

What is internal validity?

Answer 22

being confident that the differences in DV are because of IV

Question 23

What are some threats to internal validity?

Answer 23

1. history - historical event influences effect
2. differential attrition - different number of subjects in each group quit
3. demand characteristics - subjects know what you’re testing for and give a response that is expected
4. biased assignment - no random assignment
5. differential treatment of subjects

Question 24

What is external validity?

Answer 24

will the relationship between the IV and DV be found in the “real world”

Question 25

What are some problems with testing external validity?

Answer 25

effect size of tests in the lab and the field

Question 26

How do you describe a design involving more than one IV?

Answer 26

factorial design

levels in IV1*IV2 = # conditions

Question 27

What are the advantages and disadvantages of repeated measures?

Answer 27

\+ remove error of different people
\+ decreases # participants needed
- carryover effects: exposure affects responses to other levels
- fatigue
- habituation

Question 28

What are the two types of conditions involving people in experimental conditions?

Answer 28

within-subjects

between-subjects

Question 29

Why would a researcher want to measure the DV before manipulating the IV?

Answer 29

pre-test, post-test design, necessary when examining change

pretest might sensitize participants to purpose, shouldn’t immediately precede experiment

Question 30

What is matched random assignment?

Answer 30

divide subjects on attribute, randomly assign to conditions

Question 31

What is a mixed-model design?

Answer 31

When you measure one variable and manipulate one

useful if interested in how personality interacts with manipulation

Question 32

What are the two uses of an analysis of covariance?

Answer 32

Can be used to test why an IV is causing change in DV
ex. nature sounds high math performance than control (relaxation?)
Can be used to decrease error term in study - want your covariate to be related to DV, not IV
ex. stereotype threat effects on math performance, math SAT as covariate

Question 33

What is a quasi-experiment?

Answer 33

non-random assignment
manipulation of IV not directly controlled by researcher
overcome some limitations of correlational and experimental designs

Question 34

What are the three types of Q-E?

Answer 34

1. non-equivalent control group design - ex. target school, control group; can’t ensure comparison is the same
2. natural experiments - naturally occurring “manipulations” ex. hurricane, terrorist attack
3. time series designs - multiple pre- and post- measurements to study changes in trends, captures ongoing trends over time; ex. highly publicized suicides and single-car crashes

Question 35

What are some challenges of conducting Q-E research?

Answer 35

Balance of internal and external validity issues

often difficult to get data

Question 36

What are criticisms of single-case designs?

Answer 36

Results do not generalize to everyone, but to “group averages”
Psychologists often interested in predicting individual behavior
Effect must not be important if you can’t see it in an individual
Do not study variability within an individual person over time

Question 37

What are advantages of single-case designs?

Answer 37

Able to show effect of IV in each person examined

Can replicate finding within the study of one individual

Question 38

What are the types of single-case designs?

Answer 38

ABA: baseline, introduce IV, remove IV; record frequency
ABAB: replicate the study within an individual
AB1AB2: have two different levels of an IV

Question 39

What are the problems with single-case designs?

Answer 39

Question of generalization; cannot examine moderators

Involves inspection of patterns rather than statistical tests