Intro Flashcards
Population
the whole group of people of interest to the researchers
Sample
The participants being studied in the research pulled from the population
what makes a good sample
a sample that is representative of the populations which makes the results able to generalise. For the sample size to be big enough it must be 10% of pop
How big must the sample size be
10% of the pop
Characteristics of an experimental design
Random allocation, manipulation of IV, control of extraneous variables.
What does an experimental design give you
Cause and effect
Where can experiments be conducted
in a field or lab setting. Lab gives more control, field is more realistic
Three types of extraneous variables
Participant, situation and experimenter
Participant variable
pre-existing conditions (age, gender, sex)
Situation variable
Temp, wind, time of day, noise, brightness
Experimenter variable
clarity of instructions, behaviour towards participants, biases.
What is an extraneous variable
Any variable other than the IV and DV that may influence the results of the experiment
What is the difference between the experimental group and the control group
The only difference between the two should be the treatment
When is a quantitative observational design used
when it is not possible or ethical to use an experimental design
What does a quantitative observational do differently to an experimental
It does not show cause and effect as it does not manipulate the IV.
What does a quantitative observational show instead of a cause and effect
A correlation
Is there random allocation in quantitative observational?
No, there are pre-existing groups (married people, 17 years olds, people with blue eyes, etc).
Why doesn’t quantitative observational show cause and effect
Because we don’t manipulate the IV, therefore can not say that the change in DV was due to that and not other factors.
Qualitative design
Self-reporting data that does not seek to prove a specific hypothesis and could not prove it even if it did.
Focus groups
6-12 people
Group discussion
Lead by a researcher and discusses a topic of interest
A benefit of this is the snowballing effect
Delphi technique
A questionnaire is sent out to experts and cross-referenced to come to a consensus on the issue. Criticised for forcing an agreement.
How to we analyse qualitative data
Through content analysis
How do we analyse content
we short out answers into categories from which we can find the frequency of that answer
Why do we analyse content
to convert qualitative data into quantitative data.
Advantages of experimental design
- Cause and effect
- Maximum control
- Replicable
Disadvantages of experimental design
- Often artificial and not applicable
- Sometimes unethical
Advantages of quantitative design
Can study subjects that it would be unethical to experiment on
Disadvantages of quantitative design
does not allow for cause and effect
Advantages of qualitative design
In-depth responses
Avoid ethical problems
Can be used with illiterate people
Snowballing effect
Disadvantages of qualitative design
Does not show cause and effect
not useful for testing hypothesis
results can’t be generalised
social desirability
Quantitative data
Numerical measurements
Heart rate, reaction time, cm, mm, litres, behaviour counts, rating scale, time
Qualitative data
Non-numerical qualities, characteristics, images, descriptions
Objective data
can be directly observed and verified
Subjective data
Depends on perception, opinion or judgement. Cannot be directly observed or confirmed. Any type of self-report
Quantitative objective
heart rate, IQ, behavioural counts
Quantitve subjective
rating-scale personality test
Qualitative objective
does not exist
Qualitative subjective
Content analysis
Focus groups
Statements
Validity
whether the measurement tool (surveys, apparatuses for measurement, questionnaires, etc) actually measure what it is meant to.
Face validity
Whether a measure APPEARS as though it would measure what it is designed to measure
External validity
Can the findings be applied to the population? Are they correct for other situations other than a lab.
Reliability
How consistent the result of a measurement are. This is why we replicate.
Can a measure be reliable but not valid
Yes.
Social desirability
Is a participant variable
The tendency of some respondents to report an answer in a way they deem to be more socially acceptable than their true answer would be.
