Research methods

• Aim


  General statement of what the researcher intends to study
• Hypothesis


  A clear testable statement that states the relationship between investigated variables
• Hypothesis should always state the independent variable (IV) and dependent variable (DV)
• Directional hypothesis


  States exactly the difference between variables/conditions
• Directional hypotheses are used when there is back up information to support suggesting an outcome
• Non-directional hypothesis


  States there is a difference between variables/conditions, but does not state exactly the difference
• Independent variable (IV)


  Variable you change in an experiment, can be done by a researcher or naturally
• Dependent variable (DV)


  Variable that you measure in an experiment, any effect on the DV should be caused by changes to the IV
• Control variable


  Variable that is kept the same to ensure a fair test
• Operationalisation


  Clearly defining variables in ways they can be measured, can be assigning numbers to something
• Extraneous variable


  Any variable, other than the IV, that may have an effect on the DV if not controlled. Known as nuisance variables
• Researchers identify extraneous variables where possible to try to minimise them
• Extraneous variables do not vary systematically with the IV
• Extraneous variables make it difficult to detect results
• Confounding variable


  Any variable, other than the IV, that may have affected the DV so that we cannot be sure of the true source of changes to the DV
• Confounding variables vary systematically with the IV
• Confounding variables become one of the IVs
• Demand characteristics


  Any cue from a researcher that gives away the aim of an experiment to the participants. Can lead to the 'please U' or 'screw U' effect
• Investigator effects


  Any effect of the investigator's behaviour on the research outcome (DV). This includes any part of an experiment
• Investigator effects can be conscious or unconscious
• Randomisation


  Use of chance to control for the effects of bias
• Randomisation reduces the researcher's influence on the design of the investigation
• Randomisation minimises the effects of extraneous variables and confounding variables
• Randomisation is used to control investigator effects
• Standardisation


  Using the same procedures + instructions for all participants in a study
• Standardisation ensures the conditions are the same in any replications
• Independent groups design


  Participants are allocated to different groups with different experimental conditions (IV)
• In an independent groups design, the performance of both groups is compared, often by calculating a mean from the data
• Repeated measures design


  Participants experience both experimental conditions
• In a repeated measures design, data for each condition would be compared - 'like for like'
• Counterbalancing is used to attempt to control for the effects of order in a repeated measures design
• Matched pairs design


  Participants are matched based on similar variables that may affect the DV, then each participant is assigned to either condition 1 or condition 2
• Laboratory experiment


  Experiment conducted in a highly controlled environment with low mundane realism - wouldn't occur in an everyday scenario
• Field experiment


  Experiment that takes place in a natural setting with high mundane realism
• Natural experiment


  Experiments where the researcher takes advantage of pre-existing IVs between a group
• In a natural experiment, the IV is natural, not necessarily the setting
• Quasi experiment


  Study that is almost an experiment but lacks key ingredients. The IV has not been determined (what you change), however variables exist, e.g. being old or young, age, gender
• Population


  Group of participants who partake in an experiment - focus of researchers interest
• Sample


  Group of participants taken from a target population - presumed to be representative of the population
• Bias


  In the context of sampling, when a group may be over or under-represented within the sample selected, e.g. too many young people