Research Methods Flashcards
Confounding variables
> A variable that is not the IV but which varies systematically with the IV.
‘Confound’ means cause confusion - changes in DV may be due to the confounding variable rather than the IV.
Extraneous variables
> Does not act as an alternative IV, but may have an effect on the DV.
Mundane realism
> Refers to how an experiment mirrors the real world.
Generalisation
> To what extent can I generalise these findings to everyday life
Internal validity
> The degree to which an effect was due to the experimental manipulation rather than other factors
External validity
> The degree to which research can be generalised to other settings - to other settings (ecological), to other groups of people (population), or over time (historical)
Repeated measures design - Explanation
> All participants receive all levels of the IV
Repeated measures design - Limitations
> Order effects
When participants do the second test they may guess the purpose of the experiment, which may effect their behaviour
Repeated measures design - Solutions to limitations
> Counterbalancing - AB or BA< ABBA
A cover story can be presented about the purpose of the test
Independent group design - Explanation
> Participants placed in separate groups - each group does one level of the IV
Independent group design - Limitations
> Researcher cant control the effects of participant variables (abilities or characteristics) - becomes a confounding variable
Independent group design - Solutions to limitations
> Randomly allocate participants to conditions which distribute participant variables evenly
Matched pairs design - Explanations
> Match participants on key characteristics believed to affect performance on the DV
Matched pairs design - Limitations
> Very time-consuming and difficult to match participants on key variables
Not possible to control all participant variables because you can only match known to be relevant, but other could be important.
Matched pair design - Solutions to limitations
> Restrict the number of variables to match to make it easier
Conduct a pilot study to consider variables that might be important when matching
Lab experiments
> Controlled setting
Lab experiments - Strength
> High internal validity - good control over all variables is possible - confident that ant any change in DV is due to the IV
Lab experiments - Weakness
> Low ecological validity - aware they are being studied and the tasks involved tend to be more artificial - may change their behaviour
Field experiment - Explanation
> Controlled outside a laboratory
Field experiment - Strength
> Not likely to be aware that their behaviour is being studied - therefore behaviour may be more ‘natural’ and relaxed
Field experiment - Limitation
> Low internal validity - more difficult to control extraneous variables
Natural experiment
> Experimenter has not manipulated the IV directly - it varies ‘naturally’
Quasi experiment
IV is actually not something that varies at all - it’s a condition that exists
Investigator effect
> Direct - consequence of the investigator interacting with the participant
Indirect - consequence of the investigator designing the study
Opportunity sample
> People who are most easily available at the time of the study
Easiest method - takes less time
Biased - drawn from a small part of the population
Random sample
> Random technique
Unbiased - equal chance of being selected
Time consuming - contact all of those selected
Stratified sample
> Subgroups within a population are identified - selected randomly from subgroups
More representative
Time consuming
Systematic sample
> Use a predetermined system to select participants
Unbiased
Not truly unbiased unless you select a number using a random method and start with this
Volunteer sample
> Newspaper, noticeboard, internet
More representative and less bias
Volunteer bias - people may be more motivated to be helpful, or may need the money offered
Informed consent
> Participants must be given info concerning the nature and purpose of the research and their role in it
Presumptive consent - asking a group similar to the participant whether they would take part
Deception
> Participant is not told the true aims of the study
Fully debriefed after study -informed of true nature and allowed to withhold data (form of retrospective informed consent)
Right to withdraw
> Participants can stop if they are uncomfortable in any way
Informed at the beginning of a study
Protection from harm
> Participants should not experience negative physical or psychological effects
Stop the study if harm is suspected
Confidentiality
> Trust that personal information will be protected
Numbers or false names to represent participants
Privacy
> Right to control the information shared about themselves
Don’t study anyone without consent unless public place and behaviour
Unstructured observations
> Records all relevant behaviour but has no system
Structured observation
> Various systems to organise observations
Behavioural categories
> Dividing a target behaviour into a subset of specific and operationalised behaviours
Sampling
> Event sampling - counting the number of times a certain behaviour occurs
Time sampling - recording behaviours in a given time frame
