exam 3 Flashcards
1
Q
Which variable is manipulated?
A
Independent variable
2
Q
Which variable is measured?
A
Dependent variable
3
Q
Any variable that an experimenter holds constant
A
Control variable
4
Q
T/F Everything should be held constant except what is being manipulated.
A
True
5
Q
Why Experiments Support Causal Claims?
A
They Establish:
1. covariance
2. temporal precedence
3. internal validity
6
Q
What group has no treatment condition?
A
Control group
7
Q
What group has one or more treatment condition?
A
Treatment group
8
Q
placebo control group is called
A
Placebo group
9
Q
The group with the comparison condition is
A
Comparison group
10
Q
What is a design confound?
A
accidental second variable is an alternative explanation for the results. Systemic variability is the problem.
11
Q
Which variability has levels of variables that coincide in some ways causing confounds?
A
Systematic Variability
12
Q
Unsystematic Variability
A
Levels of variables fluctuate independently leading to variability
13
Q
When participants at one level are systematically different than those from the other level which effect is this and what does it affect?
A
Selection effect; Internal Validity
14
Q
Random Assignment
A
random method to assign participants
15
Q
Define matched groups
A
participants who are similar are grouped together
16
Q
Independent groups design
A
different groups are exposed to different levels of the independent variable
17
Q
Within-groups design
A
each participant is exposed to all levels of the IV
18
Q
participants are tested on the dependent variable only once.
A
Posttest-only design
19
Q
participants are tested on the dependent variable twice (once before and once after exposure to independent variable)
A
Pretest/Posttest Design
20
Q
Taking an exam as a group, and then taking the test individually would be problematic to which design?
A
pretest-postest design
21
Q
How is construct validity established in dependent variables?
A
By how well the variables are measured
22
Q
How is construct validity established in independent variables?
A
By how well the variables are manipulated
23
Q
How can you test how well an independent variable was manipulated?
A
1.Manipulation Checks
2. Pilot studies
24
Q
an extra dependent variable that researchers can include to determine how well a manipulation worked
A
Manipulation checks
25
What is a pilot study?
a study before (or sometimes after) to test effectiveness of manipulations..
26
participants are measured on a dependent variable more than once, after exposure to each level of the independent variable.
Repeated Measures Design
27
participants are exposed to all the levels of an independent variable at the same time
Concurrent- measures design
28
Name 2 advantages of within-groups design
1. Participants in your groups are equivalent
2. requires fewer participants than other designs
29
How does counterbalancing avoid order effects?
they present the levels of the independent variable to participants in different sequences
30
threat to internal validity where people change overtime just by random happenings
Maturation threat
31
Ex: 1st grade teacher measures words at the beginning of the school year in students vs words they know at the end of the school year. The increase in words could be from the curriculum or could simply just be from their brains growing. What type of threat is this?
Maturation threat
32
How can maturation threats be solved?
By adding a control group
33
An experimental group changes over time because of an external factor that affects all or most members of the group
History threat
34
How can history threats be solved?
Adding a control group
35
any extreme finding is likely to be closer to its own typical, or mean level the next time it is measured (with or without the experimental treatment or intervention).
regression threat
36
TRUE OR FALSE
regression to the mean (regression threat) is likely to be a threat ONLY when there is an extreme score
TRUE
37
threat to internal validity that occurs when a systematic type of participant drops out of the study before it ends.
attrition threat
38
In which 3 types of studies can attrition threats occur?
pretest/posttest, repeated measures, & quasi-experimental studies
39
TRUE OR FALSE
Attrition is more of a problem when participants are dropping out for random reasons rather than for all of the same reasons
FALSE, it is more of a problem when participants are dropping out for all of the same reasons
40
a threat to internal validity that occurs when participant scores change overtime due to taking a test more than once
testing threat
41
a threat to internal validity when the measuring instrument changes overtime in a study.
instrumentation threat
42
how can instrumentation threats be prevented?
1. design
2. standardize scores/z-score (to compare more extreme scores)
43
An outside event or factor systematically affects participants at one level of the IV.
Selection-history threat
44
Participants in only one experimental group experience attrition.
Selection-attrition threat
45
Three Potential Internal Validity Threats in Any Study
1. observer bias
2. demand characteristics
3. placebo effects
46
2 things Controlling for observer bias and demand characteristics
1. double-blind study
2. masked study
47
A cue that leads participants to guess a study’s hypotheses or goals; a threat to internal validity. Also called experimental demand.
demand characteristics
48
1. Perhaps there is not enough between-groups difference.
2. Perhaps within-groups variability obscured the group differences.
3. Perhaps there really is no difference.
These are all things to consider when interrogating which effect when the Independent variable does not make a difference?
Null effect
49
TRUE OR FALSE
When you see a null effect it is because a study wasn't designed well and it could be designed better to manipulate the dependent variable
TRUE
50
Insensitive measures are typically a problem with which variable?
Dependent variable
51
TRUE OR FALSE
continuous dependent measures are always less sensitive than categorical dependent measures.
FALSE, they are always MORE sensitive
52
TRUE OR FALSE
the more sensitive the measure is the bigger effect it can actually detect
FALSE, the more sensitive the measure is the smaller effect it can actually detect
53
What effect is this an example of?
A professor makes his students take an exam at an early time, 6am for example instead of the regular time, but the test he is giving is on a 5th grade level, so all of the scores fall at the higher end of the scale.
Ceiling effect
54
What effect is this an example of?
A professor makes his students take an exam at an early time, 6am for example instead of the regular time, and the test he is giving is on a higher grade level than what the students are capable of, so all of the test scores fall at the lower end of the scale.
Floor effect
55
independent variable groups score almost the same on a dependent variable, such that all scores fall at the high end of their possible distribution.
ceiling effect
56
independent variable groups score almost the same on a dependent variable, such that all scores fall at the low end of their possible distribution
floor effect
57
an extra dependent variable researchers can include to determine how well a manipulation worked.
manipulation check
58
TRUE OR FALSE
Although confounds usually threaten internal validity, they can apply to null effects.
TRUE
59
1.Using reliable, precise measurements
2. Measuring more instances
these are both solutions for reducing what?
measurement error
60
TRUE OR FALSE
SMALL area of within groups variability = LARGE area of between groups variability, leading to a BIG F-value.
LARGE area of within groups variability = SMALL area of between groups variability, leading to a SMALL F-value.
TRUE
61
Individual differences _______ out scores within each group.
Spread
62
2 solutions for individual differences
1. Change the design to a within-groups or matched-groups design.
2. Add more participants.
63
any kind of external distraction that could cause variability within groups that obscures between-groups differences.
situation noise
64
Situation noise can be ___________ by controlling the surroundings of an experiment.
minimized
65
the likelihood that a study will yield a statistically significant result when the IV really has an effect.
power
66
TRUE OR FALSE
If a study provides strong evidence that there’s probably no real effect, scientists should report that result transparently.
TRUE
67
The main effect is
A. the most important effect.
B. found only in studies with one independent variable.
C. the overall effect of one independent variable at a time.
C. the overall effect of one independent variable at a time.
68
An interaction can occur in an experiment with
A. one independent variable.
B. two independent variables.
C. two dependent variables.
B. two independent variables.
69
In a factorial design, a participant variable is treated like a(n)
A. independent variable.
B. dependent variable.
C. design confound.
B. dependent variable.
70
A factorial design with two independent variables, one with two levels and the other with three levels, would be represented in a factorial design as
A. 2 x 3.
B. 2 x 2 x 3.
C. 2 x 2 x 2.
D. 2 x 2.
A. 2 x 3
71
Which of the following phrases is a factorial design clue often found in a journal article?
A. “controlled for”
B. “taking into account”
C. “it depends”
C. “it depends”
72
How many IVS, main effects, conditions, and lvls are in this factorial design?
2 X 2 X 3
IVS: 3
ME: 3
Lvls: 2 IV w/ 2 lvls, 1 Iv w/ 3 lvls
Conditions: 12
73
When the effect of one IV depends on the level of the other IV
Interaction effect
74
Factorial Design
A study with 2 or more IV or factors
75
Consider this 2 x 2 design, determine the independent variables and their levels, dependent variable, and whether or not there is an interaction.
People high in bilateral facial symmetry are more attractive than people who are low in it. It does not matter whether they are male or female.
IV: bilateral facial symmetry, sex
levels: bilateral facial symmetry (high or low facial symmetry), sex (male or female)
DV: attractiveness
interaction: no interaction
76
A variable whose levels are selected (measured), not manipulated (age, gender, ethnicity)
Participant Variable
77
Define main effects
overall effect of one IV on the DV in factorial designs
78
Consider this 2 x 2 design, determine the independent variables and their levels, dependent variable, and whether or not there is an interaction.
Alcohol slows reaction time equally for young and old people, and being older slows reaction time equally for both sober and drunk people.
IV: sobriety, age
levels: sobriety (sober or drunk), age (young or old)
DV: reaction time
interaction: no interaction (keyword: equally)
79
arithmetic means for each level of an IV
marginal means
80
If the interaction is signifcant, DONT trust main effects (T/F)
TRUE
81
Are positive attitudes (such as forgiveness) in a relationship healthy? It depends on how serious the problems are. When problems are minor, positive attitudes (rather than negative ones) are healthy for a relationship. But when problems are major, such as abuse or drug dependence, positive attitudes are unhealthy for a relationship because it prevents the couple from addressing their relationship problems.
Consider the 2x2 design and identify the Independent variables and their levels, dependent variable, and if there is an interaction or not.
IV: Atittude and Problem
Levels: (positive, negative), (major, minor)
DV: Relationship health
Interaction: Yes (Positive attitudes are healthy for a relationship but only when problems are minor)
82
83
Are taller (versus shorter) people more attractive? It depends on their sex. Women perceive taller men as more attractive, but women women's height does not matter to men when it comes to attractiveness.
Consider the 2x2 design and identify the Independent variables and their levels, dependent variable, and if there is an interaction or not.
IV: Height and Sex
Levels: (Tall, short), (male, female)
DV: Attractiveness
Interaction: Yes (being tall makes people more attractive but only if they are male)
