Week 6 Flashcards

(24 cards)

1
Q

What is a confound?

A

An extraneous variable not considered in the study that can provide an alternative explanation for the results, and would have worked for the research hypothesis.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is a counterconfound?

A

A extraneous variable not considered in the study that can provide an alternative explanation for the results, and would have worked against the research hypothesis (explains results that deviate from the predicted result)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is the difference between a confound and a mediator?

A

A mediator is part of the mechanism/explanation, whereas a confound is not on the causal path, it explains why A seemed to have an effect on X without help from A

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Lets say researchers find that owning a sports car is associated with speeding, and comes up with the hypothesis that buying a sports car causes speeding. What is a potential mediator, and a potential confound?

A

Mediator - driving enjoyment

Confound - need to impress

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Lets say researchers find that owning a sports car is associated with speeding, and comes up with the hypothesis that buying a sports car causes speeding. Is owning a sports car a PAV IV?

A

Yes - owning a sports care is an attribute of the participants that they bring into the experiment situation.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is the core problem of person variable confounds?

A

Groups or conditions should only differ in the variable of interest, and be equal in terms of all other extraneous variables that could influence the results.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is attrition?

A

Loss of data due to withdrawal of participants (or exclusion of participants)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Is attrition a potential confound?

A

No - it is an external validity problem

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is differential attrition?

A

If data loss is greater in one group or condition than another.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Is differential attrition a potential confound?

A

Yes - it can act as a potential confound or counter confound - especially is these differences are substantial and make a substantial difference to the participant numbers in each group

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

If there is high attrition in the condition that was predicted to perform better, is the differential attrition a confound?

A

Yes

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

If there is high attrition in a condition that should perform worse, is the differential attrition a confound?

A

Potential counter-confound

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

If there is high attrition in all conditions, is the differential attrition a confound?

A

No - possible lack of sensitivity or limitation of external validity

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Can regression to the mean act as a confound or counter confound?

A

Yes - depending on whether the results are in line with the results (confound) or not (counter-confound)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What causes regression to the mean?

A

Selecting participants on the basis of an attribute that is later measured, and having less than perfect measurements which skews the results towards people being better or worse than their true performance or characteristics.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is regression to the mean?

A

The phenomenon where if one sample of a random variable is extreme, the next sampling of the same random variable is likely to be closer to its mean.

17
Q

How can regression to the mean be prevented?

A

Avoiding selecting participants on a characteristic of their performance at the outset and avoiding interventions that are directly related to performance

If those are both necessary, then using multiple pre-tests and different kinds of selection tests can increase reliability

18
Q

What is a stimulus/materials confound?

A

An extraneous variable introduced in the stimulus materials used by the researcher to test a research question, that can provide an alternative explanation for the results

19
Q

How can stimuli confounds be prevented?

A

Identifying all possible confounds that could be associated with stimulus materials, and identifying all possible factors that can affect DV, as well as controlling all possible confounds

20
Q

What are history confounds?

A

Time and place dependant changes that occur during study outside of the participants and provide an alternative explanation for the results

21
Q

How can history confounds be prevented>

A

Using a time lagged design to seperate out the effects of aging/development from history factors

22
Q

What is a maturation confound?

A

Time-dependant changes within the individual that occur during the study and provide an alternative explanation for the results

23
Q

How can maturation confounds be prevented (short-term)?

A

Counterbalancing time of testing, or hold time of testing constant

24
Q

True or False: Regression to the mean, stimulus confounds, history confounds, and maturation confounds are all very likely to be construct validity problems

A

True - occurred in the planning of the study, operationalising constructs