Please enable JavaScript.
Coggle requires JavaScript to display documents.
Research methods: Types of studies - Coggle Diagram
Research methods:
Types of studies
Correlations
Correlation
= Mathematical technique in which a researcher investigates an association between two variables - co-variables
Co-variable
= Variables investigated within a correlation - not the IV and DV because it doesn't show cause and effect
Positive
= As one co-variable increases so does the other
Negative
= As one co-variables increases the other decreases
Zero
= When there is no relationship between co-variables
Strengths of correlations:
Provides
precise and quantifiable measure
of how 2 variables are related - used as starting point to assess possible patterns before researchers commit to an experimental study
Quick and economical
- no need for controlled environment or manipulation of variables - data collected by others so less time consuming
Limitations of correlations:
Lack of manipulation and control means we don't know why variables are related
Can't demonstrate cause and effect between variables so unsure why a co-variable is causing the other to change
An extraneous variable may cause the relationships between co-variables
Correlations can be misused or misinterpreted
Questionnaires and interviews
Questionnaire
= A set of written questions used to assess a person's thoughts and experiences
S -
Cost-effective
- gather large amount of data quickly as it can be distributed to large numbers of people
S - Can be
completed without researcher present
so reduces effort
S - Data is
straightforward to analyse
and comparisons between groups of people can be made using graphs and charts
L - Responses may be
socially desirable
and show demand characteristics
L - Often produce
response bias
where they respond in same way
L -
Acquiescence bias
- always agreeing regardless
Structured interview
= Made up of pre-determined questions that are asked in a fixed order - happen in real time
Unstructured interview
= No set questions just an aim of topic and the interviewee is encouraged to expand and elaborate their answers
S - Straightforward to
replicate
due to standardised format
S -
Can't deviate from the topic
which limits data
U -
Flexibility
so can gain insight of the interviewee
U - Increased risk of
interviewer bias
and may be irrelevant info and drawing conclusions may be difficult
U - Risk that they may
lie b
ut a skilled interviewer should be able to establish sufficient rapport with ppts
Interview
= A live encounter where one person asks a set of questions to assess their thoughts and experiences
Types of experiments
Quasi-experiment
= They contain a naturally occurring IV which is a difference between people that already exist (gender and age) - then the researcher examines the effect of this variable on the DV
S - Often
controlled conditions
and can be replicated
L -
Cannot randomly allocate
ppts to conditions so may be confounding variable
L - The
IV is not deliberately changed
by researcher so cannot claim that the IV has caused an observed change
Natural experiment
= A naturally occurring IV that isn't manipulated and researcher still records fact of DV
S -
High external validity
- involves real world issues as they happen e.g. natural disasters and stress levels
L - Naturally occurring event can be
infrequent
- limits scope to
generalise
findings to other similar situations
L - Ppts may
not be randomly allocated
- unsure if IV affects DW
Lab experiment
= An experiment in a controlled environment within which the researcher manipulates the IV and records effects on DV while maintaining strict control of variables
S - High
control over CVs and EVs
- can ensure the effect of the DV is the result of manipulating the IV - high internal validity
S -
Replication
due to high level of control
L -
Lacks generalisability and real life application
- artificial and lack mundane realism - low ecological validity
L - Ppts are usually aware they are being observed -
demand characteristics
Field experiment
= An experiment in a natural setting within which the researcher manipulates the IV and records the effects on DV
S - Higher
mundane realism
than lab as it is more natural - produce authentic behaviour - high external validity
L -
Loss of control of CVs and EVs
- cause and effect may be more difficult to establish as exact replication is not possible
L -
Ethical issues
- if ppts are unaware they are being studied and cannot give consent to being studied - invasion of privacy
Observations
Naturalistic
= Watching and recording behaviour in the setting within which it would normally occur
S - High
external validity
as can be generalised to everyday life
L -
Lack of control
makes replication difficult - CVs and EVs may be a factor
Participant
= The researcher becomes a member of the group whose behaviour he is watching and recording
S - Researcher can experience situation as observers do so have an increased insight into their lives -
increase external validity
L - Researcher may
lose objectivity
and identify too strongly
Non-participant
= The researcher remains outside of the group whose behaviour he is watching and recording
S - Allows researcher to remain an
objective distance
L - May
lose insight
as they are too far removed from people and behaviour
Controlled
= Watching and recording behaviour within a structured environment
S - CVs and EVs are less of a factor so
replication
of observer is easier
L - May produce findings that cannot be
generalised
Covert
= Ppts behaviour is watched and recorded without their knowledge or consent
COVERTed
S - Ppts are unaware they are being watched so
reduces demand characteristics
and ensures behaviour is natural - increases internal validity
L -
Ethics
questioned as some people may not wish to have their behaviours noted down - consent/privacy
Overt
= Ppts behaviour is watched and recorded with their knowledge and consent
Open
S - More
ethically acceptable
as ppts have to give consent
L - May show
demand characteristics
as they know they are being observed
S - Captures what people do so gives an
insight into behaviour
L -
Observer bias
- observer's interpretations of a situation may be affected by their expectations
L -
Cannot demonstrate causal relationship
though may be used in experiments and help detect cause and effect relationships
Case studies
= In depth investigations of a person, group, event, or community and uses info from the person and also family and friends
Techniques such as interviews, psychological tests, observations and experiments are used
S - Provide
rich qualitative data
and have high levels of ecological validity
L - Difficult to
generalise
to other people as they have unique characteristics - unrepresentative