Research methods Flashcards
Types of validity
face
concurrent
ecological
temporal
Face validity
where a behaviour appears at first sight (on the face of It ) to represent what is being measured
Concurrent validity
Comparing a new test with an existing test of the same nature to see if they produce similar results
Ecological validity
Where a measure of behaviour accurately reflects the way in which the behaviour would occur in normal circumstances
the extent to which the results and conclusions are generalisable to real life.
Temporal validity
Where findings from research that took place at a certain point in time accurately reflect the way that behaviour would occur at a different point in time
Types of experiments
Laboratory
Natural
Quasi
Field
What is validity?
the extent to which findings or conclusions of a study are actually measuring what they claim to be measuring
Internal validity
the measure of the experimenter’s measurement of the dependent variable.
Internal validity - stopwatch example
measuring the reaction times of a person with a stopwatch.
Can you see an problem with this measurement?
The problem is that the person with the stopwatch has to also react. So, we would expect that this measurement is invalid.
use a video camera.
external validity
the extent to which findings can be generalised
Why is it important to have high external validity?
Important to have high levels of external validity because this directly affects the usefulness of the results and conclusions of the study
Population validity
the extent to which the sample can be generalised to similar and wider populations.
Why is population validity important?
This type of validity is important because without it the research becomes low in usefulness
Aim
a statement which describes the overall purpose of the research
Hypothesis
Statements or predictions about what the researcher expects to find.
Predictions might be based on prior research or existing theories
Method
How the research is carried out
When are directional hypotheses chosen?
if research is a replication of previous research
If a particular result has been found in the past, it is more likely that the same thing will be found again.
Operationalisation of variables
Process of avoiding ambiguity and maintaining internal validity by making variables and hypotheses clear and measurable.
Example of a null hypothesis
Breaking the rules about school uniform is not affected by gender and any difference is DUE TO CHANCE
Directional hypothesis
gives a direction in which the difference goes (i.e. higher, smaller)
Non-directional hypothesis
states that there will be a difference.
random sampling
gives every member of a target an equal chance of selecition
systemic sampling
every nth person is selected
Stratified sampling
groups of pp’s are selected in proportion to their frequency in their population to obtain a representative sample
Opportunity sampling
PP’s who are in the right place at the right time
most easily available at the time of study
Volunteer sampling
Ask people whether they are interested in taking part via an advertisement
pilot studies
a small-scale trial run of a research before doing the real thing
covert
concealed, hidden, done in secret.
Repeated measures
each pp takes part in all conditions
Independent groups
each pp only takes part in one condition
Matched pairs
where different but similar participants are used in each condition of the experiment.
matched on characteristics such as age or ability.
independent variable
variable that is manipulated by the researcher to measure its effect on the dependent variable.
Dependent variable
what is measured
Confounding variable
things that might affect research findings other than the IV.
Extraneous variable
Any variable, other than the IV, that may have an effect on the DV
Should be controlled at the start of the study
Confounding variable
any variable, other than the IV, that has affected the DV
Counterbalancing
a technique used to deal with order effects when using a repeated measures design
E.g. first 10 pp’s complete condition A then B
remaining 10 pp’s complete condition B then A
randomisation
the use of chance in order to control for the effects of bias when designing materials
suitable in an experiment with may diff lvls of IV
Lab experiment
controlled experiment
conducted in an artificial setting
participants know they’re being studied
demand characteristics
Occur when pp’s try to make sense of the experiment and act accordingly to support aim of research
Natural experiment
DONT affect the IV by yourself bc highly unethical
British psychology society’s code of ethics
Document which details general principles that apply to use of human pp’s in all research contexts
overt
in the open, not concealed/ hidden
participants are aware that they are being observed
test-retest reliability
A way of assessing the external reliability of a research tool
testing and testing again on a diff occasion using exact same conditions and pp’s
non-participant observation
when the researcher remains separate from the group they are studying
objectivity
means research isn’t affected by personal feelings of the researcher
falsifiability
Principle that a theory only considered scientific IF it was possible to establish it as false
theory construct
theory - a proposed explanation for causes of behaviour
theory needs to be a logically organised set of propositions that:
defines events
describes relationships among events
explains and predicts occurrence of events
should offer a testable hypothesis that can be rigorously tested
paradigm
A framework containing commonly accepted view about a subject
paradigm shift
A fundamental change in approach or underlying assumptions
matched pairs - disadvantage
difficult to carry out - hard to match pp’s on certain criteria
Quantitative data
numerical
can be analysed statistically
correlation coefficient
measures the strength of a correction
-1.0 = perfect negative
+1.0 = perfect positive
qualitative data
Expressed though detailed descriptions/words
Concerned with the quality of behaviour of an experience; feelings and emotions.
Thematic analysis
1) convert qualitative date into quantitative
2) data reviewed repeatedly so researcher can identify trends
3) themes re-analysed so become more defined
4) The themes identified can be used to support of challenge existing theories
Type 2 error
think results weren’t significant but are
peer review - purpose
make it more scientific for objectivity
person carrying out research is impartial to results
Why peer review?
decide on future Gov funding
improve credibility of the field
representative
a smile that accurately represents the population being studied
e.g. stratified sampling
naturalistic observations
watching and recording behaviour in the setting within which it would normally occur
controlled observation
watching and recording behaviour within a structured environment i.e where some variables are managed
e.g. Ainsworth strange situation
positive correlation
as one co-variable increases, so does the other
e.g. amount of people in a room and noise
negative correlation
as one co-variable increases, the other decreases
correlation
assess the strength and direction of an association between 2 variables
structured interview
pre-determined list of behaviours to quantify observations
e..g behavioural categories
unstructured interview
researcher records everything they see
producing accounts of behaviour in rich detail
investigator effects
Researcher (consciously/unconsciously) acts in a way to support their prediction
primary data
obtained first-hand by researcher
secondary data
already exists before investigation, someone else has collected the info
more convenient than gathering primary data
zero correlation
No relation between 2 co-variables
What are the 4 major principles of BPS Code of Ethics?
Respect
Competence
Responsibility
Integrity
Why are demand characteristics an issue?
Participants may behave in a way to support the hypothesis (please-you effect)
Makes results much less valid
Conversely, pp’s may try to disrupt results (screw-you effect)
Empirical method
The use of an objective, quantitative observation in a systemically controlled, replicable situation to test/refine a theory
Content analysis
1) Researchers establish aim and hypothesis
2) familiarise self with data so coding system can develop
3) researcher systematically re-analysis data to identify example of each code
disadvantage = themes are subjective, lack objectivity
type 1 error
think results were significant, but weren’t
generalisation
Application of results from a study, to the wide target population.
Findings from original sample will be the same for everyone else in the target population
peer review - process
Before publication, paper/book sent to other academics of same field
Suggest improvements
Can be improved or rejected
pilot study
a small-scale study of the real study
inter-rater reliability
The extent to which two or more observers are observing and recording behaviour in the same way
behavioural categories
Breaking down the target behaviour (e.g. aggression) into components that can be observed and measured (e.g. hitting, kicking)
time sampling
Observer records behaviour at prescribed time intervals
e.g. every 15 mins
Questionnaire: open questions
don’t have fixed responses, pp’s aren’t restricted on answers
generates qualitative data
Questionnaire: closed questions
Restricts pp to a predetermined set of responses
generates quantitative data
Quasi experiment
Contains a naturally occurring IV
E.g. looking at effect of gender or intelligence
natural experiment
dont affect IV yourself, bc highly unethical
field experiment
controlled experiment
conducted in an ordinary setting
pp’s unaware they’re being tested
objectivity
Not affected by personal feelings of the researcher
standardisation
procedures used in research are kept the same
Participant observation
research is directly involved in experiment
Participant observation
research is directly involved in experiment
What is reliability?
refers to the consistency of research study; whether it can be repeated and produce the same results
