Independent and dependent variables:
Independent variable (IV) - the variable that is manipulated by the experimenter to investigate what effect it has on the dependent variable.
Dependent variable (DV) - the variable that is measured by the experimenter.
Extraneous and confounding variables:
Extraneous variable - any unwanted variable other than the IV, that may potentially affect the DV and therefore, the results of the study.
Confounding variable - a factor in the experiment that was not controlled and had affected the research findings.
Correlational research and analysis:
Correlational research: to see if there is a relationship between two variables
Correlational analysis: a mathematical statistical formula used to analyse data from correlational research. The aim is to discover whether:
- there is a relationship between two variables
- the type of relationship
- how strong the relationship is
Correlational coefficient: a numerical value that describes the strength and type of relationship between two variables
- 1 being a perfect positive correlation - 0 being no correlation
- (-)1 being a perfect negative correlation
Evaluation of correlational research and analysis:
:) Ethically acceptable
:) Once a correlation has been established, this allows future predictions to be made which will be very useful for the government which can develop social policies.
:( a correlational analysis shows if there is a relationship between two variables but it does not mean that one variable causes the other because there may be other factors involved.
:( correlational analysis is only effective for linear relationships between two variables but not for curvilinear relationships.
Naturalistic observation: involves the researcher observing and collecting data on people's naturally occurring behaviour in their natural environment without interference or manipulation of variables.
:) Naturalistic observations have a high level of ecological validity because those being studied are unaware so they would behave as they usually would. This means that participant effects will be prevented and therefore, the findings will be high in validity.
:( In naturalistic observations, the researcher may be selective in what they want to see, they may unconsciously filter information, accepting only information that fits with their hypothesis. This may lead to the data being biased which will affect the validity of the findings.
:( in a naturalistic observation, e participant is not aware that they are being observed which raises ethical issues as to the invasion of privacy and lack of informed consent of those being observed.
Controlled observation: when the researcher deliberately manipulates or controls the environment in a particular way and observes the effects.
:) allows a higher level of control over possible extraneous variables that may influence the participants' behaviour.
:( participants are aware that they are being observed and this means that there couls be a high possibility of demand characteristics occurring which could lower the validity of the research findings.
Types of observation:
Covert/undisclosed observation: the researcher does not tell the participants that they are being observed and their real identity is hidden.
Overt/disclosed observation: the participants know they are being observed and usually the reason why.
- closed questions: produce quantitative data
- open questions: produce qualitative data
:) questionnaires are cheaper to administer which makes them cost effective and more time efficient the other research methods.
:) anonymous questionnaires allow the participants to be more honest as they will be more willing to answer more personal and sensitive answers than in a face to face interview.
:( respondents may not answer the questions in a truthful way such as lying or giving the easiest answer just to complete the questionnaire as quickly as possible. This can decrease the validity of the data.
:( those who do complete the questionnaire may not be representative of the population, because those people who do take the time to complete the questionnaire differ from the kind of people who don't meaning that the results won't be reliable.
- structured interview: includes pre-determined questions
- unstructured interview: introduces a number of topics into the discussion
:) allows the researcher to gain more detailed opinions and attitudes of the respondent which cannot be done with questionnaires.
:) interviews are more effective for sensitive subjects than a questionnaire, the respondents are more likely to give more truthful responses.
:( demand characteristics could affect the validity of the findings, the respondent may give answers which they believe the interviewer wishes to hear, or may give answers which portrays them in a positive light.
:( the interviewer may unintentionally bias the participants' responses. Certain gestures, the tone of voice as well as age and gender can influence the answers of the respondent.
:) case studies allow the researcher to provide rich and detailed information which provides a better insight into human behaviour, which can trigger further research and expand the current knowledge of human behaviour.
:) case studies can be used to prove or contradict existing theories. For example, the case study of the Czech twins who suffered severe deprivation but made a strong recovery challenged Bowlby's maternal deprivation theory that the lack of attachment bond can be permanently damaging to the child's social and cognitive development.
:( case studies involve an individual in a unique situation and therefore the results obtained from the study may not be representative of the rest of the population and cannot be generalised.
:( case studies often rely on the person's recollections of past events which may be prone to distortion giving unreliable results.
Independent group design:
Independent group design - the participants are assigned and tested in only one experimental condition.
:) avoids possibility of order effects.
:) reduces effect of demand characteristics because the participant takes part in one condition only meaning that they are less likely to guess the aim of the experiment.
:( individual difference may not be balanced out between the two conditions meaning that the results could be due to individual differences (such as intelligence, ethnicity, age etc.)
:( requires more participants – twice as many than a repeated measures design.
Repeated measures design:
Repeated measures design – the same participants take part in both experimental conditions.
:) eliminates the possibility of individual differences since the same people are used in both experimental conditions and therefore kept constant.
:) half as many participants are needed.
:( increases possibility of order effects where the participants may do better in the second condition because they have improved through practice or they may have done worse in the second condition due to fatigue or boredom. This can affect the results of the study.
:( increases possibility of demand characteristics, that they may guess the purpose of the study and this is likely to affect the results of the study.
Matched pairs design:
Matched pairs design – different participants are used for each experimental condition but he participants in both conditions are matched by similar characteristics.
:) reduces order effects and demand characteristics.
:) individual differences are minimised through pair matching so there is less chances of variation between conditions.
:( requires twice as many participants, which can be time-consuming.
:( can be extremely difficult to match all the variables between each pair of participants.
Order effect and demand characteristics:
Dealing with order effect and demand characteristics:
- counterbalancing can be used, where a randomly allocated half of the participants do condition A followed by condition B and the other half do condition B followed by condition A. (ABBA).
In a random sample every member of your target population would have an equal chance of being selected.
:( Time consuming
:) everyone has an equal chance
When volunteers have freely seleced themselves to be part of a sample through advertisements such as in newspapers and posters.
:) Quick and practical
:( Prone to volunteer bias.
When the researcher themselves approaches anyone who is available and willing to participate.
:) quick, cheap and practical.
:( prone to a bias sample.