Week 2 - Research Design I Flashcards
What are the 3 key features of the experimental method?
- MANIPULATING the independent variable
- CONTROLLING extraneous variables
- MEASURING the dependent variable
What are the following types of independent variable: situational, task, instructional, control?
Manipulating the IV attempts to establish cause-and-effect
(A) Situational: describing/characterising a social situation (eg. number of bystanders in a social study)
(B) Task: the materials/procedure manipulation (eg. divided into groups, then given different difficulties of maths problems)
(C) Instructional: the way we communicate (eg. given the instruction to either memorise using visual imagery OR by no instruction at all)
What is the benefit of random participant assignment?
Rules out the possibility there are systematic differences (eg. intelligence, personality, belief in luck etc.) between these two groups
is STRICTLY NON-SYSTEMATIC
What is a manipulation check?
Part of the method (eg. a question in a survey) that ensures that the manipulation has had the desired effect on the groups
What is sample representativeness?
Correspondence between the sample and the population to which the research is to be generalised on dimensions RELEVANT to the research processes
can research be generalised to other populations in a similar relevant context
What is indirect manipulation?
Researcher manipulates a variable that is not the primary variable of interest - but is related to or influences the variable of interest
What is an extraneous variable? How is it different to a confounding variable?
Extraneous: Any variable NOT OF IMMEDIATE INTEREST to a researcher which may THREATEN VALIDITY because it compromises the INTERPRETATION OF RESEARCH FINDINGS
Confounding: ACCIDENTAL MANIPULATION of an EXTRANEOUS VARIABLE that occurs because that variable is associated with an IV in an experiment
- It’s effect on the DV ay be mistaken for the effect of the primary IV
What may a pilot study help to identify?
Ceiling Effect: If task is too easy - all scores are very high
Floor Effect: If task is too hard - all scores are very low
Measuring the DV issues: outline ‘practical restraints’ and ‘relevance-sensitivity trade off’
Practical Restraints: ethical and moral issues (eg. research into drink driving - you can’t give people alcohol and let them drive)
Relevance-Sensitivity Trade Off: the more sensitive a DV is to changes in the IV, the less relevant it may be in the real-world phenomena in which one is interested –> “proxy” measures may not be similar enough to the variable they are attempting to imitate
What are quasi experiments?
Differences on the IV already exist -they are NOT manipulated by a researcher (eg. age, gender)
- Cannot be manipulated
- But can select people for each condition based on these characteristics
Compare experimental and quasi-experimental studies?
Experimental:
- EVs are controlled for
- Causal Inference can be made
- Can conclude that changes in IV cause changes in DV
Quasi-Experimental:
- EVs cannot be controlled for
- Cannot establish causal inference
- Can only say different groups performed differently