Midterm #2 - Experimental Designs (I and II) Flashcards
1
Q
between groups design
A
- each participant tested in only one condition/level
- ensures all conditions are independent of each other
- can be costly in time and effort
2
Q
strategies to reduce bias
A
- random assignment
- setting that allows control over relevant variable
- standardized protocol
3
Q
experimental control
A
- methods used to counter threats to validity
- provides comparison for experimental condition
- reduces sources of variability
4
Q
setting the stage
A
- provide informed context information
- explain why experiment is being conducted
5
Q
staged manipulation
A
- uses confederates
- event manipulation
- creates a psychological state
- stimulates real world situations
6
Q
strategies for reducing variability
A
- explicitly include nuisance variables
- isolate effects
- statistical control
- match participants on variables known to effect DV
7
Q
within group/subjects design
A
- compare same people in all conditions
- can take a lot longer
- each participant experiences every condition
8
Q
advantages of within-subjects
A
- study change/differences in one person
- reduces variability
9
Q
disadvantages of within-subjects
A
- logistically more challenging
- instrumentation
- maturation
10
Q
counterbalancing
A
- with 2 conditions:
- half sample gets A then B
- half sample gets B then A
11
Q
Latin square
A
- situations when complete counterbalancing not possible
- each condition occurs in each position in sequence
12
Q
temporal precedence
A
- when changes in the suspected cause occur before changes in the effect
13
Q
mundane realism
A
- the degree to which a study parallels everyday situation in the real world
14
Q
independence
A
- the assumption that each participant represents a unique and individual data point
15
Q
matched-pair design
A
- one creates a set of two participants who are highly similar on a key trait
- randomly assigns individuals in the pair to different groups
16
Q
t-test for independent means
A
- compares groups’ means to see if the groups differ to a degree that could not have happened by chance
17
Q
effect size
A
- measure of the magnitude of the difference between groups
18
Q
null hypothesis
A
- hypothesis of no difference
- usually what the researcher is trying to statistically reject
19
Q
multiple independent variables
A
- could be used to explain single or multiple DVs
- can determine if effect of one IV depends on the level of another IV
20
Q
factorial designs
A
- when there’s more than one independent variable
- each IV is known as a factor
- each level of one factor combines with each level of another factor
21
Q
2x2 study
A
- one main effect for the row (A), one main effect for the column (B), and one interaction term (AxB)
22
Q
there is an _______ when lines are no longer ________
A
- interaction
- parallel
23
Q
synergistic effect
A
- 2 variables combine to produce an outcome that’s greater than what each individual variable contributes
24
Q
suppression effect
A
- an effect where 2 variables combine to produce and outcome that’s smaller than what each individuals variable contributes
25
Q
benefits of factorial designs
A
- establish cause and effect
- conduct multiple experiments at once
- examine how a combo of IVs affects the DV
26
Q
mixed design
A
- one or more IVs are between subjects factor
AND - one or more IVs are within subjects factors