Unit 1 - Research methods Flashcards
1 - Independent variable (IV)
2 - Dependent variable (DV)
3 - What must all variables be? Give an example?
1 - An event that is directly manipulated by the experimenter in order to observe its effects on the DV
2 - Dependent on the IV
3 - Variables must be operationalised i.e. defined in a way that they can be tested.
E.G
Instead of DV ‘educational attainment’, an experimenter must specify a way to measure this such as GCSE grades
What is the aim of a study?
Aim of any study is a statement of what the researcher intends to investigate
Define a hypothesis
A precise and testable (operationalised) statement and the expected relationship between variables
1 - Directional hypothesis
2 - Non-directional hypothesis
3 - Null hypothesis
1 - Also known as ONE TAILED HYPOTHESIS. States direction of the relationship (trend/correlation) between the variables being investigated
2 - Also known as TWO TAILED HYPOTHESIS. Predicting that there will be a difference or relationship between the variables being investigated without stating the direction of the relationship
3 - Tends to state that there will be no difference relationship between the variables being investigated
Define experimental design and list the 3 possibilities
It’s a set of procedures used to control the influence of factors such as participant variables in an experiment
- Repeated measures
- Independent groups
- Matched pairs
Experimental design:
Repeated measures
+/- VEs
Some participants in every condition being tested
+ Good control for participant variables
+ Fewer participants needed
- Order effects (e.g. boredom, practice)
- Participants may guess the purpose of the experiment
Experimental design:
Independent groups
+/- VEs
Participants are allocated to 2 (or more) groups representing different experimental conditions
+ Avoids order effects and participants guessing the purpose of the experiment
- Needs more participants
- No control of participant variables (can use random allocation)
Experimental design:
Matched pairs
+/- VEs
Pairs of participants matched on key participant variables. 1 member of each pair is placed in the experimental group and the other in the control group
+ Avoid order effects
+ Participant variables partly controlled
- Matching is difficult and never totally successful
Counterbalancing. How is it used in experimental designs?
Used to deal with order effects by ensuring that each condition is tested fist or second in equal amounts
- Some participants receive condition A then B, others receive B then A
- Or ABBA - All participants receive A B then B A
What do these variables provide/ contain? (Experimental designs)
1 - Experimental condition
2 - Control condition
1 - Contains IV
2 - Provides a baseline measure of behaviour without the experimental treatment (IV), so that the effect of the experimental treatment may be assessed
Name the types of groups used in an experiment?
3
Independent groups design
Experimental group
Control group
How are behavioural categories separated? (2)
What should behavioural categories be? (3)
Observational design
1 - BEHAVIOURAL CHECKLIST
A list of component behaviours
2 - CODING SYSTEM
Individual behaviours are given a code for ease of recording
Behavioural categories should:
- Be OBJECTIVE = Observer shouldn’t have to make inferences about the behaviour
- Cover all possible component behaviours and avoid a ‘waste basket’ category
- Be MUTUALLY EXCLUSIVE = You shouldn’t have to mark 2 categories at 1 time
1 - Event sampling
2 - Time sampling
1 - Counting the number of times a certain behaviour (event) occurs in a target individual
2 - Recording behaviours at regular intervals e.g. every 30 seconds
1 - Participant observation
2 - Non - participant observation
1 - Observational study where the observer is also a participant in the activity being observed. This may effect the objectivity of their observations
2 - Observational study where the observer is not taking part in the activity being observed
1 - Overt observations
2 - Convert observations. Why?
1 - Observation technique where observations are ‘open’ i.e. participants are aware that they’re being observed
2 - Observing people without their knowledge e.g. using one way mirrors. This is done because participants are likely to change their behaviour is they know that they’re being observed
1 - Structured observation
2 - Uncontrolled observation
1 - An observer uses various ‘systems’ to organise observations, such as behavioural categories and sampling procedures
2 - An observer records all relevant behaviour but has no system. This technique may be chosen because the behaviour to be studied is largely unpredictable
What makes up a good question in a questionnaire? (4)
- Clear/easy to answer
- Unambiguous
- Not biased in any way (not leading)
- Not threatening
Questionnaires:
Closed questions?
+/- ve?
Have a good range of answers from which the participants select one
+ Produce quantitative data = easier to analyse
- Respondents may be forced to select answers that don’t represent their real thoughts or behaviour
Questionnaires:
Open questions?
+/- ve?
Invites respondents to provide their own answers rather than select one of those provided. Produces qualitative data
+ Can provide unexpected answers and rich detail, allowing researchers to gain new insights
- More difficult to summarise answers because there may be such as wide variety of responses. This then makes drawing conclusions difficult
Why are filler questions used in questionnaires/interviews?
To disguise the true aim of the questionnaire/interview so that respondents are more honest
How is reliability determined in experimental studies
Repetition
To improve reliability of extraneous variables should be controlled
How is reliability determined in observational studies
Inter-observer reliability = extent of which there is an agreement between 2 or more observers
ASSESS internal reliability- Correlate the observations of the 2 or more observers. IF:
total no’ agreements / total no’ observations is > 80 then the data has a high inter-observer reliability
Improve reliabilit = observers are trained to use behavioural categories
Self report technique to improve reliability?
Inter-interviewer reliability = extent to which 2 interviewers produce the same outcome from an interview
ASSESS internal reliability- Use split half method.
Scores/responses on both halves of a test should be constant
ASSESS external reliability - Use test-retest method. Same questionnaire/interview is repeated with the same respondent a few weeks apart
Improve reliability = remove questions which create inconsistency
Validity of experimental studies
INTERNAL =
The degree to which the observed affect was due to experimental manipulation rather than factors such as extraneous variables. It is also affected by mundane realism and experimental realism
EXTERNAL =
The representativeness of the sample affects the ability to generalise the findings to other people and situations i.e.
Population validity
Ecological validity
