define reliability
the extent to which a study can be replicated and produce the same results.
What are the two ways to assess reliability and describe each one
1) Test-retest: involves giving the same test/. questionnaire to the same group of ppl on different occasions. If the test is reliable, the results would be similar/same. Wait some time between each occasion so can’t remember their answers, but not too long that their characteristics have changed.
2) Inter-observer reliability: involves multiple researchers observing a study so the subjective view of one researcher isn’t the only interpretation. if reliable, two or more observers findings will produce similar results.
What is done at the end of a study to see if its reliable
the reliability is measured using correlational analysis. If the correlation coefficient is +0.8 then its reliable.
What are the four ways to improve reliability
1) Questionnaires: replace open ended questions with close ended questions.
2) Interviews: use structured interviews e.g. standardised questions. Ensure all pps are asked the same questions in the same order.
3) Experiments: standardised procedures - same conditions for all pps.
4) Observations: operationalise all behavioural categories. The observers should all use the same clear, non-overlapping categories.
Define validity
the extent to which an observed effect is genuine.
What are the two types of validity
1) Internal validity: whether the effects observed are due to the manipulation of the independent variable and not another factor.
2) External validity: the extent to which findings can be generalised beyond the research setting.
What are the two types of external validity?
1) ecological validity: the extent to which the research findings can be generalised to real-world settings.
2) Temporal validity: the extent to which the findings can be generalised across different historical periods.
What are the two ways to assess validity
1) face validity: does the test look as if it’s measuring what the researcher intended to measure.
2) Concurrent validity: this s when they compare the performance with a previously established test of the same topic. If there’s a close agreement (0.8 or higher) between the two tests, then high concurrent validity.
What are the 4 ways to improve validity
1) Questionnaires: use a lie scale to check response consistency and reduce social desirability bias. Ensure anonymity so respondents feel comfortable giving truthful answers.
2) Qualitative methods: use triangulation- when multiple sources/ methods are used to check findings. Include direct quotes to include pps own words.
3) Experiments: use a control group, standardised procedures, and single/ double blind procedures.
4) Observations: behavioural categories shouldn’t be too broad, overlapping or ambiguous. Use a covert observation to reduce the effects of demand characteristics.
Features of science: objectivity
features of science: empirical methods
features of science: replicability
features of science: falsifiability
features of science: theory construction
features of science: paradigm and paradigm shifts
what is a lab experiment
this is where the researcher has control over the variables in the study. The experimenter uses standardised procedures and controls environmental factors.
Only the IV should change when the researcher manipulates it in order to see the effects on the DV.
Lab experiment evaluation
Strengths: as all the variables are controlled, researchers can be confident that a cause and effect relationship has been established.
High internal validity and can be replicated due to the use of standardised procedures.
Weaknesses: lack external validity as lab setting isn’t like real life so low ecological validity.
Lacks mundane realism as tasks done in studies often not similar to the ones done in real life.
pps are aware they’re being studied so they’re behaviour may change as they respond to DCs.
What is a field experiment?
the study is conducted in a real world setting. the IV is changed by the researcher between the different conditions of the experiment and the researcher measures the effects on the DV.
Evaluation of field experiments
Strengths: high external validity so pps more likely to behave naturally.
Increased mundane realism as tasks more likely to replicate everyday tasks.
Less likely to respond to DCs.
Weaknesses: lack of control over extraneous variables.
Low internal validity.
What is a natural experiment
the levels of the IV have already occurred naturally in the real world and the researcher just measures the change in the DV.
The IV is not changed by the researcher. Other possible variables that could change the DV are not controlled.
Evaluation of Natural Experiments
Strengths: allows research into areas that could not have been investigated otherwise due to ethical reasons or cost.
High external validity as the change is happening naturally in real life so changes in behaviour are not affected by DCs.
Weaknesses: researcher has no control over the experiment which means no extraneous variables are controlled.
Cannot be replicated as they’re extremely rare.
What is a quasi experiment?
this is where pps cannot be randomly allocated to different levels of the IV as the groups already exist e.g. when investigating age or gender.
All variables other than the IV that could affect the DV are controlled. Changes in DV are measured.
Evaluation of quasi experiment
Strength: this is the only way to experimentally study these factors that are pre-existing characteristics of the pps.
Weaknesses: there may be other factors related to the levels of the IV that cannot be controlled since they change systematically with the levels of the IV and alter the measurements of the DV: confounding variables.
define observation
when the researcher watches and records behaviour as it happens.