research methods Flashcards
aim
a general statement of what the researcher intends to study
hypothesis
a prediction of what the researcher thinks will happen in their study
directional hypothesis
states the direction of the difference or relationship
non-directional
does not state the direction of the difference or relationship.
the researcher says there will be a difference but doesn’t elaborate further.
null hypothesis
states there will be no difference in the direction or relationship
operationalisation
clearly defining variables in terms of how they are measured.
extraneous variables
any other variables apart from the IV that might have an effect on the DV.
types of EV
participant variable eg age
situational variable eg noise
experimenter variable eg appearance
confounding variable
any other variables apart from the IV that does have an effect on your DV
laboratory experiments
conducted in highly controlled environment. researcher has high levels of control over the IV and DV.
strengths of laboratory experiments
high control over all variables - allows cause + effect relationship to be established.
easily replicable which allows you to determine whether your results are reliable as it uses standardised procedures
limitations of lab experiments
artificial environment so lack of ecological validity - cannot be generalised to everyday life.
demand characteristics - when a participant changes their behaviour because they know they are part of research .
Field experiments
Real life setting.
IV is manipulated and effect on DV is measured
Strengths of field experiments
Real life environment so high levels of ecological validity
Lower levels of demand characteristics - higher validity
Limitations of field experiments
Less control over EVs so difficult to establish cause and effect relationship
Hard to replicate due to lack of standardised procedures
Ethical issues - participants unaware they’re part of study so lack of informed consent
Natural experiments
Real life settings
IV changes naturally and effect it has on DV is measured
Strengths of natural experiments
Often able to study events that would not be ethically or practically possible
Limitations of natural experiments
Some experiments are rare so difficult to replicate. This lowers reliability
Lees control over EVs makes it difficult to establish cause + effect relationship
Quasi experiments
In a controlled setting
IV hasn’t been chosen by researcher. It is fixed and cannot be manipulated
Eg. You can’t change a persons age
Strengths of Quasi experiments
high control over all variables - allows cause + effect relationship to be established.
easily replicable which allows you to determine whether your results are reliable as it uses standardised procedures
Limitations of quasi experiments
artificial environment so lack of ecological validity - cannot be generalised to everyday life.
demand characteristics - when a participant changes their behaviour because they know they are part of research .
Target population
A large group of people the researcher is interested in studying
Representative
A sample that reflects the target population
Generalisation
The extent to which findings can be broadly applied to the population
Opportunity sampling
Recruit people who are most available to use. Eg people in street
Produces an unrepresentative sample
Strengths of opportunity sampling
Convenient - little time spent gathering sample
Cost effective
Limitations of opportunity sampling
Researcher bias
Bias- when/were you collect sample may affect representativeness
Random sampling
Each member of target population has equal chance of being chosen
Produces representative sample
‘Lottery method’
Strengths of random sampling
No researcher bias
Limitations of random sampling
Time consuming
‘Freak sample’ - you could still end up with unrepresentative sample
Stratified sampling
Subgroups within a population are selected eg boys and girls
Need to identify strata that make up target population
Strengths of stratified sampling
No researcher bias
Limitations of stratified sampling
Sometimes impossible- not all identified strata within population can be represented in sample
Systematic sampling
Use a predetermined system to select participants eg every nth participant
Strengths of systematic sampling
No researcher bias
Limitations of systematic sampling
‘Freak sample’
Volunteer sampling
Participants select themselves to take part in study
Ad in newspaper
Strengths of volunteer sampling
Easy sample for researcher
Cost effective
Limitations of volunteer sampling
Volunteer bias
No sample - no one might respond to ad
Independent groups
Participant only takes part in 1 condition
Strengths of independent groups
Not affected by order effects
Not affected by demand characteristics - less chance they will guess aim / change behaviour
Limitations of independent groups
More participants - time consuming
Individual differences of participants
Repeated measures
Participant takes part in both conditions
Strengths of repeated measures
No individual differences
Fewer participants
Limitations of repeated measures
Order effects
Demand characteristics
Matched pairs
Matched in terms of age, IQ etc
Participant A does condition 1, B does condition 2
Strengths of matched pairs
No order effects
Lees likely to be affected by demand characteristics
Less individual differences
Limitations of matched pairs
More participants needed - time consuming
Matching people is difficult
How to overcome issues with experimental designs
Random allocation - tries to control individual differences in participants. Each P has equal chance of being allocated either condition
Names on paper and pulled out hat
Counter balancing - controls order effects. Half do condition 1 first other half do other
