Research Methods and Statistics Chapter 3, 6, 7, 8 and 10 (Different Research Claims) Flashcards

You may prefer our related Brainscape-certified flashcards:
1
Q

What are the three types of research claims

A
  1. Frequency claims (proportions of variable of population)
  2. Association claim (association between variables)8
  3. Causal claim (one variable causes another)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the 4 big validities

A
  1. External validity (can we generalize the research to other population and operationalizations)
  2. Construct validity (does the measure really measure what it is supposed to measure?)
  3. Internal validity (what is the causation –> only in experiments)
  4. Statistical validity (comparing the values from both conditions)
    Is there an effext?

–>

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

Whats a thematic apperception test

A

Letting a person write a story about a picture and valuing the emotions

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

What is the most ideal design for frequency claim

A

Surveys and also observational research

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

What’s the most ideal research design for association claims

A

Correlational research

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

What are the 6 types of probability sampling

A
  1. Simple random sample (everybody of population has same chance to participate) (very hard but most important)
  2. Cluster sample (everybody in a category like schools or organisations)
  3. Multistage sampling (sample random subjects of clusters)
  4. Stratford random sampling (sample according to percentages like blood types)
  5. Oversampling (sampling more of a specific minority)
  6. Systematic sampling (every nth person)

–> is a representative sample which can be generalised

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

What are the types of non probability sampling

A
  1. Convenience sampling (accessible samples)
  2. Purposive sampling (search for samples with specific requirements)
  3. Snowball sampling (ask subjects for other fitting subjects)
  4. Quota sampling (set a quota and fulfill them)

–> can not be generalised to population

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

Where is good sampling important

A

In frequency claims

It is not that important in causal and association claims

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

What are the 3 challenges in observational research

A
  1. Observer effect (observer affects subjects behaviour)
  2. Observer bias (your expectations affect your observations)
  3. Reactivity (subjects behave differently when they know that they are being observed)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are solutions against observer effect and observer bias

A
  1. Unambiguous codebook
  2. Multiple observers
  3. Masked design (observers are unaware of studies purpose)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are solutions to reactivity problem

A
  1. Blend in (making yourself less noticable)
  2. Wait it out (subjects will get used to presence after some time)
  3. Unobstrusive (study evidence for behaviour)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the challenge in correlational research

A

Correlation doesn’t say anything HOW the association works

  • A causes B
  • B causes A
  • C causes A and B
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are the three criterias for a causal claim

A
  1. Covariance (there is an effect)
  2. Temporal precedence (the causal came before the effect)
  3. Internal validity (there are no confounds)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is a bivarate correlation

A

A association that involves exactly 2 variables

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

How do you interrogate statistical validity

A
  1. Effect size: (How big is effect size)
  2. Measure statistical significance (is it surely not just by chance?)
  3. Measure potential outliers (are there any values affecting the results)
  4. Restriction of range (is the range not big enough?)
  5. Curvilinear (is the association maybe a curve?)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

How do you interrogate internal validity?

A

Did you maybe see the association as a causal effect?

17
Q

How do you interrogate external validity?

A

Is the sample really representative of the population?

18
Q

Why are surveys sometimes not valid

A
  1. The words in the question may Influence the answers

2. People want to make themselves look good

19
Q

Why are surveys sometimes not valid

A
  1. The words in the question may Influence the answers

2. People want to make themselves look good

20
Q

Whats the difference between observational and experimental research

A

In observational research you just measure the conditions (IV) nature produced and the variation (DV) from that.
In experimental research you produce the condition (IV) yourself to then see the variation (DV). Only here causal claims are possible.

21
Q

What is generalizability

A

When a theory is supported by both observational and experimental studies (Replication)

22
Q

What are the pros and cons of experimental and observational research

A

Experimental can be very hard, unethical and unnatural, but you have control and can achieve causality.
Observational is possible to have confounds and there is no direct causality, but it is easier to do and its more natural

23
Q

What are the four big things that can go wrong in an experimental design and which thread internal validity

A
  1. Design confounds (Your manipulation can cause multiple variations –> confounds)
  2. Selection effects (Systematic differences between groups (nonrandom or selection bias))
  3. Pseudoreplication (replication is not done right as subjects may come from same enviroment)
  4. Order effects (Systematic differences because you measured the conditions always the same –> solution is counterbalancing (mixing up the orders))
24
Q

Explain a between group design

A

A between group design (indepent) means different participants are used for each group and condition. It is more sure, but there may be selection effects

25
Q

Explain the two designs for between group experiments

A
  1. Post-test design (Assume no difference between groups and measure the difference in the dependent variable AFTERWARDS)
  2. Pretest/Posttest design (measure the difference in the dependent variable BEFORE and AFTERWARDS, and then measure the difference in the difference)
26
Q

Explain a within-groups design

A

A within-groups design has every participants test all the levels of independent variable
The advantage is that you need fewer participants, but there may be order effects and demand characteristics

27
Q

Explain the different within-groups designs

A
  1. Repeated measure design (measure the dependent variable in every participant after each exposure to the independent variable)
  2. Concurrent measure design (present both conditions and see which one is preferred (babies prefer warmth over food)