Research methods

• Experimental methods

  The manipulation of independent variable (IV) to measure the effect on the dependent variable (DV)
• Aim

  A general statement of what the researcher intends to investigate (the purpose of the study)
• Hypotheses

  A clear, testable statement that states the relationship between the variables
• Directional hypotheses

  States the direction of the difference or relationship
• Non-directional hypotheses

  Does not state the direction or relationship
• Variables

  Anything that can vary or change within the investigation
• Independent variable

  Manipulated by the researcher, or changes naturally so the effect on the DV can be measured
• Dependent variable

  The variable which is measured, only effect should be caused by the IV
• Operationalisation

  Clearly defining variables in terms of how they can be measured
• Extraneous variables

  Any other variable which can effect the DV if not controlled
• Confounding variable

  Varies systematically with the IV, can’t tell which one changed the DV
• Demand characteristics

  Participants behaving a certain way to please the researcher
• Investigator effects

  Conscious or unconscious behaviour which may affect the DV e.g., design of the study, interaction, participants
• Randomisation

  ‘Chance’ methods to control effects of bias
• Standardisation

  Using the same instructions for all participants
• Experimental design

  Different ways participants can be organised in relation to the experimental conditions
• Independent group design

  Participants are allocated to different groups where each group represents one experimental condition
• Repeated measures

  All participants take part in all conditions of the experiment
• Matched pairs

  Pairs are first matched on some variable(s) that may affect the DV. Pairs are then randomly assigned to either a control or experimental group
• Random allocation

  An attempt to control for participant variables in independent groups, ensures everyone has the same chance of being in one condition as any other
• Counterbalancing

  An attempt to control for the effects of order in a repeated measures design e.g., half of the participants experience conditions in one order, then the other half in the opposite order
• Laboratory experiments

  Conducted in highly controlled environments, they are not always in a lab, they could be, as well as, a classroom where conditions are well controlled
• Lab experiments

  + High control over confounding and extraneous variables ensures changes to the DV is likely due to the IV (high internal validity)

  + Replication is more possible due to high level of control, vital to whether finding is valid

  - May lack generalisability, the environment may seem artificial (not everyday real-life) participants may behave in unusual ways (low external validity)

  - Participants are usually aware of being tested (demand characteristic)

  - Low mundane realism, doesn’t replicate everyday real life
• Field experiments

  IV is manipulated in a natural, more everyday setting. The researcher goes to the participants usual environment
• Field experiments

  + Higher mundane realism than lab experiments because the environment is more natural. May produce behaviour which is more natural and authentic, especially if they are unaware of being studied

  + High external validity

  - Ethical issues are a problem if the participant is unaware of being studied they cannot consent, which may cause an invasion of privacy

  - Increased realism causes a loss of control over CVs and EVs, harder to tell if the changes to the DV were caused by the IV

  - Exact replication may be difficult
• Natural experiments

  An experiment where research is unable to manipulate the IV, researcher examines the naturally occurring changes on the DV they decided on
• Natural experiments

  + Provides opportunities for research that may have not happened otherwise for practical and ethical issues

  + High external validity because it involved a study of the real-world issues and problems as they happen e.g., effects of a natural disaster on stress levels

  - Natural events may happen rarely, reducing opportunities for research

  - Lack of control, there is no control over EVs and the environment. Cannot always accurately investigate the effects of the IV on the DV
• Quasi-experiments

  A study which is almost an experiment but lacks key ingredient. The IV has not been determined by anyone. The variables simply exist e.g., being old or young. Not an experiment
• Quasi-experiments

  + Often carried out under controlled conditions so it shared some strengths with lab experiments (e.g., replication)

  - Like natural experiments, cannot randomly allocate participants to conditions. may be CVs

  - May be CVs as you cannot claim the IV caused any change
• Population

  A group of people who are the focus of the researchers interest from which a smaller sample is drawn
• Sampling techniques

  The method used to select people from the population
• Generalisation

  The extent to which findings and conclusions from a particular investigation can be broadly applied to the population. This is possible if the sample of participants is representative of the target population
• Random sample

  All members of the target population have an equal chance of being selected. Firstly, obtain a list of all members from a target population. Secondly, all names are given a number. Finally, use a lottery methods e.g., picking numbers from a hat
• Random sample

  + Potentially unbiased, EVs and CVs should be equally divided between different groups (internal validity)

  - Difficult and time-consuming

  - A complete list of a target population may be difficult to obtain
• Systematic sample

  Every nth member is selected from the target population e.g., every 3rd house in a street or every 5th pupil on a school register
• Systematic sample

  + One the system is established, the researcher has no control over who is chosen (esp. if random)

  - Time-consuming, participants may refuse to take part, resulting in a volunteer sample
• Stratified sample

  A method of sampling from a population which can be partitioned into subpopulations e.g., football club fans
• Stratified sample

  + Representative sample because it is designed to accurately reflect the composition of the population, generalisation is possible

  - Identified strata cannot reflect all the ways that people are different, complete representation isn’t possible
• Opportunity sample

  Select anyone who happens to be willing and available, ask whoever is around at the time of the study e.g., in the street
• Opportunity sample

  + Convenient as the people who could participate are there

  + Less costly in terms of time and money

  - Bias as it’s unrepresentative of the target population as they are drawn from a specific area

  - Researcher has compete control over participants, may avoid people they don’t like the look of (researcher bias)