Divided randomly into 2 groups + each does a different condition of IV
- + Each pts sees only ½ of study = harder for them to work out aim of study = reduces demand characteristics
- + Avoids practice & order effects = pts only does 1 condition = cannot be affected by boredom/practice
- – Each pts only provides 1 piece of data = more pts needed
- – Consider impact of individual differences i.e. other factors influencing IV
How can variables be controlled?
Randomisation: The use of chance in order to control for the effects of bias when designing materials and deciding the order of conditions
Standardisation: All procedures are standardised in order all pts are subject to the same environments
Demand characteristics: Features or cues in research which help participants work out what is expected of them. Participants may respond according to what they think is being investigated
Social desirability bias: Participants behave to present themselves in the best light. Researcher focuses on experimental realism, where task is engaging and participants forget they are being observed.
Investigator effects: Any effect of the investigators behaviour (conscious/unconscious) on the research outcome i.e. interaction with pts or leading questions
Pilot study: Small scale trial run of the actual investigation/experiment. This allows researcher to identify any potential issues and to modify the design or procedure, saving time and money in the long term.
Sampling techniques:
A sample is taken from a target population. It is suggested that a sample should be representative and generalizable to the wider population.
Random sample:
Each person in the sampling frame has an equal chance of selection e.g. drawing names from a hat or computer generator
- + Unbiased selection
- + Laws of probability says the researcher will normally get a representative sample
- – Chance that the sample is not representative = can’t generalise
Systematic sample
Taking every nth person in sampling frame and selecting them for the sample. E.g. every 5th person
- + Avoids bias as no control over who is selected
- + Laws of probability says the researcher will normally get a representative sample
- – Chance that the sample is not representative = can’t generalise
- – Not as objective as random sampling because research may decide on how people are listed before selection and the nth number used
Stratified sample
Sampling frame has been divided into groups that the research wants to make sure are represented in final sample. A certain number of pts are selected from these groups (usually randomly) so that they are proportionately represented in the sample
- + Ensures the sample is representative
- + Relatively objective because once the sampling has been stratified – normally left to chance (random sample) who is selected
- – Time consuming than other techniques
- – Researcher may not identify all the key characteristics for stratification meaning the sample is not representative
Opportunity sample
Made up of participants that have been selected because they are convenient and available
- + Easy and convenient
- + Least time consuming
- – Biased because the target population is so small
- – Biased because only certain types of people will volunteer to be chosen e.g. free time or interested in research
- – Researcher may show bias when selecting the pts
Volunteer sample
Participants volunteer to do research generally through response to adverts e.g. newspapers/poster
- + Gives access to wider population
- – Volunteer bias = particular kinds of people tend to volunteer e.g. highly motivated with spare time