T--Methodology

Question 1

Validity

Definition of construct validity/internal validity/external validity

Answer 1

• Construct validity: whether the variables are reliable, objective measure of DV
• Internal validity: the methodological quality of the experiment—when confounding variables are controlled.
• External validity: the generalisability of the finding sin the experiment .
- Population validity—whether the result can be generalised from the sample to the target population. (representativeness)
- Ecological validity—whether the findings can be generalised to other settings

Ways to enhance validity:
Operationalise the variables
• Construct: theoretically defined variable, construct based on theory
(e.g. violence, love, anxiety, memory)
Operationalization: express the construct in terms of observable behavior

Question 2

Experimental studies:

Answer 2

• includes independent variable(IV)manipulated by the researcher
and dependent variable(DV)change as the IV changes
• a change in IV caused a change in DV
• cause-and-effect inferences

Question 3

Correlational studies

Answer 3

• variables are measured and the relationship between them is quantified
• correlate two variables using a formula
• “co-relation”–one variable changes as the other one changes
• When data are collected to show a relationship between two variables
• When one variable changes, another variable changes as well

Limitation:
• No cause-and-effect relationship
• No IV is manipulated
• Bidirectional ambiguity: when the relationship between the variables is not clear, there might be another factor to influence the result

Question 4

Descriptive studies:

Answer 4

the variables are approached separately, such as a public opinion survey
• statistics to analyze data

Question 5

Quasi-experiment

Answer 5

• When participants are grouped based on a trait or behaviour
• IV: gender, culture and age
• No random allocation
• Natural experiments
- IV is manipulated by nature, not by the researcher
- Allocation based on pre-existing intergroup differences/ characteristics of interest
Large-scale
• IV : environmental in nature and outside of the control of the researcher

Strengths:
• Show indirect causal relationship between an IV and DV
Limitations:
• Do not show direct causation
• Low internal validity—could not control the confounding variables

Question 6

True (lab) experiments

Answer 6

• Experiment researchers conduct and experiment and lab and manipulate an independent variable to examine its effects on dependent variable, this allows them to establish a cause and effect relationship between the two variables

IV: the variable that causes changes
DV: the variable that is measured after the manipulation of IV
CV: (control variable) the variable to ensure that all the variables stay the same except the manipulation of IV
Extraneous variable: the variable that is not controlled
• Random Allocation
• Variables must be operationalised—clear and precise
• Experiments are standardised—detailed procedures that are replicable
• IV is the only difference between groups

Strengths:
• Establish cause-and-effect relationship
• Confounding variables are controlled—increase internal validity
• Allows for strict control over variables, ensures there are no extraneous variables which may be affecting the results
• Lab experiments are easy to manipulate, which means easy to replicate the experiment

Limitations:
• Cannot control demand characteristics -> participants guessing the aim of the study, trying to act according to aim
• Low ecological validity due to artificial environment
 May not be able to be generalized

Question 7

Independent sample design

Answer 7

Characteristics:
• IV is manipulated by random allocation (potential confounding variables can cancel out)

Strengths:
• Have multiple groups
• No order effect–participants only take part in one group
• Difficult for the participants to figure out the true aim of the study

Limitations:
• Participants variability–random allocation, the ability are not the same

Ways to overcome:
• Large sample size for random allocation–individual differences will be cancelled out

Question 8

Matched pairs design

Answer 8

Characteristics:
• Decide the matching variable (age, gender)
• Rank the participants according to the matching variable
• Allocate randomly according to the ranks

Strengths:
• Useful when the researcher want to keep the confounding variable constant in all groups
• Useful for small sample size
• (random allocation might cause individual differences)

Limitations:
• Difficult to implement–matching variables need to be measured first
• Theory-driven: the researcher need to know the confounding variable

Ways to overcome:
• Keep the experiment simple (one matching variable and two groups)

Question 9

Repeated measures design

Answer 9

Characteristics:
• Participants are compared to themselves–the same group of participants is exposed to two or more conditions

Strengths:
• No participant variability–they are compared to themselves
• Smaller sample size

Limitations:
Order effect –the results of the second trial are affected by the fact of participation in the first trial

Ways to overcome:
Could be overcame by counterbalancing