Experimental Research Methods Flashcards
What is meant by a ‘dependent variable’?
The variable that the experimenter measures
What is meant by an ‘independent variable’?
The variable that the experimenter manipulates
List the research methods in experimental psychology
Laboratory Study
Field Study
Natural Experiment
Quasi Experiment
Outline and evaluate Laboratory Studies
- An experiment conducted in an environment where the variables are carefully controlled
- IV manipulated by the researcher
Pros:
- Internal validity
- Less likelihood of extraneous variables
- Easily replicated
Cons:
- Artificial
- Demand Characteristics
- Low ecological validity
Outline and evaluate Field Studies
- An experiment conducted in natural settings
- IV manipulated by researcher
Pros:
-Ecological validity (behaviour is more realistic)
Cons:
- Less control over extraneous variables in the real world, therefore less internal validity
- Potentially time consuming and expensive
- Not easily replicated
Outline and evaluate Natural Experiments
- An experiment that is conducted when the IV can not be (practically or ethically) manipulated
- Therefore, it is said that the IV occurs naturally
- DV may be tested in a lab
Pros:
- Reduced Demand Characteristics
- Good method for sensitive ethical issues
- High ecological validity
Cons:
- Difficult to show cause-and-effect (IV + DV)
- Researcher doesn’t control IV or environment
Outline and evaluate Quasi Experiments
- An experiment measuring the difference between people (e.g. gender, age, height), therefore the IV is naturally occurring
- DV may be tested in a lab
Pros:
-Allow for comparisons between different types of people
Cons:
-Participants may be aware of being studied, ultimately affecting the internal validity
List the designs used in experimental psychology
Independent Groups Design
Repeated Measures Design
Matched Participants Design
Outline and evaluate the Independent Groups Design
-One group for each condition
Pros:
- No practice effects
- Less likely to show demand characteristics
Cons:
- No control of individual differences between participants
- Twice as many participants are needed (potentially), therefore less economical
Outline and evaluate the Repeated Measures Design
-All groups do all conditions
Pros:
- Participant variables are controlled as the same participants are used in each condition
- More economical (fewer participants needed)
Cons:
- Practice effects
- Demand characteristics
Outline and evaluate the Matched Pairs Design
-Participants are matched by similar traits (e.g. age, gender, intelligence)
Pros:
- Attempts to tackle participant variables
- No order effects
Cons:
- Matching is difficult/expensive/time consuming
- Matching is never totally successful
Define ‘extraneous’ and ‘confounding’ variables
Extraneous Variables: variables other than the IV affecting the DV
Confounding Variables: if the EV is not removed, it becomes a confounding variable
Define ‘counterbalancing’?
All participants doing all conditions (ABBA)
What is meant by ‘investigator effects’?
How the investigator looks, speaks and acts. As the investigator could unintentionally convey how participants should behave
What is meant by ‘social desirability bias’?
The tendency for participants (typically in questionnaires and interviews) to answer questions in a manner which they feel will be favoured by others
What is meant by ‘face validity’?
Whether the experiment appears to test what it claims to
What is meant by ‘concurrent validity’
Comparing the outcome of a new study with the results of a similar, pre-existing study
Outline the ways to improve internal reliability
Split-half method; questions on a test are split in half. If reliable, the answers for the questions highlighted should be the same for any individual
Outline the ways to improve external reliability
Test-retest method; the ability to replicate the results of the study
Replication; the ability to replicate the results of the study with different participants
List the sampling methods used in experimental psychology
Random Sampling Opportunity Sampling Systematic Sampling Stratified Sampling Volunteer Sampling
What is meant by ‘Random Sampling’?
Each individual has an equal opportunity of being selected
What is meant by ‘Opportunity Sampling’?
Using people who are available to participate
What is meant by ‘Systematic Sampling’?
Taking every nth person from a list to create a sample
What is meant by ‘Stratified Sampling’?
Small scale reproduction of a population, and the individuals within each category are random. (e.g. if 12% of the population are black, 12% of participants in the study should be black)
What is meant by ‘Volunteer Sampling’?
Using people who offer to take part in a study
Evaluate Random Sampling
Pros: Best chance of getting a representative sample
Cons: Often difficult and expensive
Evaluate Opportunity Sampling
Pros: Can be the easiest method to organise, as participants are readily available
Cons: Researcher’s choice may be biased
Evaluate Systematic Sampling
Pros: No bias in selection of participants
Cons: Unbiased selection does not mean and unbiased sample (e.g. the participants may be all female)
Evaluate Stratified Sampling
Pros: Representative of sub-groups within a population
Cons: Time-consuming; dividing into different categories and then randomly selecting participants takes time
Evaluate Volunteer Sampling
Pros: Very convenient
Cons: Usually biased, as the participants are all the same/similar (highly motivated, and/or too much free time)
Evaluate using a Mean as a measure of Central Tendency
Pros: Most accurate measure
Cons: Less useful for anomalous data
Evaluate using a Median as a measure of Central Tendency
Pros: It can be used with original data
Cons: Can be unrepresentative if you’re not given much data
Evaluate using a Mode as a measure of Central Tendency
Pros: It is useful when data is in categories
Cons: There can be more than one mode
Evaluate using a Range as a measure of Dispersion
Pros: It’s easy to calculate
Cons: Can be distorted by extreme values
Evaluate using the Standard Deviation as a measure of Dispersion
Pros: A more sensitive dispersion measure
Cons: May hide some of the characteristics of the data (e.g. extreme values)
How to calculate a percentage?
Divide the result by the total and then multiply by 100
e.g. 17/45 x 100 = 37.7%
