Research Methods
EXPERIMENTAL METHOD
Aims are general statements that describe the purpose of an investigation
• Developed from theories
Hypothesis is a statement made at the start of the study that clearly states the relationship between
variables.
• Directional: States direction of the difference or relationship e.g. faster, lower, more, less
o Used when we are given previous research findings that suggested an outcome
RESEARCH ISSUES
Extraneous Variables (EV) should be identified at the start of the study so their influence can be
reduced
• Nuisance Variables: do not vary systematically with the IV
o E.g. age of participants, lighting in a lab
Confounding Variables: something found after the study that affected the DV
Demand Characteristics are conscious/unconscious cues which tell the participants the aim of the
experiment or how to behave
• They may change their behaviour (caused by participant reactivity)
o 'please-U effect': over perform to please experimenter or act in the way they think is
expected
o 'screw-U effect' deliberately underperform to sabotage the results
Investigator Effects are any unwanted influence of the investigator on the research outcome
• Includes: expectancy effects, unconscious cues (e.g. smiling, tone of voice), leading questions,
actions of the researcher related to the study's design (e.g. selection of participants, material,
instructions)
Randomisation is the use of chance to reduce researcher's influence on the design of investigation
• Controls investigator effects
Standardisation means all participants are subject to the same environment, information and
experience
EXPERIMENTAL DESIGN
Experimental Design: the way participants are used in experiments
Independent Groups
Independent Group Design: when two separate groups of participants experience two different
conditions of the experiment
One group is part of the experimental condition and the other is the control condition and the results
are compared
Example: a drug trial (one group has drug and other has placebo)
+ Order effects are not a problem
+ Increased external validity (more pps used)
— Pps in each group are not the same (results could be due to participant variables)
o Solution: random allocation
— Less economical than repeated measures (pps only used once)
Repeated Measures
All pps experience both conditions (experimental & control) of the experiment and then results are
compared to see if there is a difference
Example:
+ Guarantees you’re comparing ‘like with like’
+ Participant variables are controlled
+ Less pps needed
, — Order effects
o Pps have to do both tasks
o Repetition could create boredom/fatigue affecting results
o Repetition could result in pps improving due to practice
o Solution: counterbalancing
— Demand Characteristics: More likely pps will work out the aim of the study
Matched Pairs
Participants are paired together with someone who has similar characteristics which are relevant to
the experiment
Then one participant from each pair would be allocated a different condition
Example: in a memory test, pps with similar IQs may be paired together
+ Order effects & demand characteristics are less of a problem
— Pps can never be matched exactly
— Matching can be time-consuming & expensive
TYPES OF EXPERIMENT
Laboratory Experiments
They are conducted in highly controlled environments (not always a lab)
Example: Milgram’s study on obedience
+ High control over extraneous variables (EV)
o Researcher can ensure that any effect on the dependent variable (DV) is due to the
independent variable (IV) → high internal validity
+ Replication is more possible
o Due to high levels of control so new EVs are not introduced
o Replication is vital to check findings and see if it is valid
— May lack generalisability
o Lab not like everyday life so pps may not behave normally
o Leading to low external validity
— Demand characteristics
— Low mundane realism (tasks may not be like real life experiences)
Field Experiments
The IV is manipulated in a natural, everyday setting
Example: Hofling’s study on obedience (nurses following ‘doctor’ orders)
+ Higher mundane realism
+ May produce behaviour which is more valid and authentic
+ High external validity
— Loss of control of extraneous variables
— Replication often not possible
— Ethics: pps unaware they’re being studied, can’t consent to being studied
Natural Experiments
When researcher takes advantage of a pre-existing IV
• Natural as IV would have changed even if researcher wasn’t there
• Natural IV not always natural setting
Example: Studies of institutionalised Romanian orphans
+ Opportunity for research which may not be done due to practicality/ethics
+ High external validity: involve studying real life issues as they happen
— Naturally occurring event may only happen very rarely
o Less opportunity for research
o Limit generalising findings
— Pps may not be randomly allocated to experimental conditions
EXPERIMENTAL METHOD
Aims are general statements that describe the purpose of an investigation
• Developed from theories
Hypothesis is a statement made at the start of the study that clearly states the relationship between
variables.
• Directional: States direction of the difference or relationship e.g. faster, lower, more, less
o Used when we are given previous research findings that suggested an outcome
RESEARCH ISSUES
Extraneous Variables (EV) should be identified at the start of the study so their influence can be
reduced
• Nuisance Variables: do not vary systematically with the IV
o E.g. age of participants, lighting in a lab
Confounding Variables: something found after the study that affected the DV
Demand Characteristics are conscious/unconscious cues which tell the participants the aim of the
experiment or how to behave
• They may change their behaviour (caused by participant reactivity)
o 'please-U effect': over perform to please experimenter or act in the way they think is
expected
o 'screw-U effect' deliberately underperform to sabotage the results
Investigator Effects are any unwanted influence of the investigator on the research outcome
• Includes: expectancy effects, unconscious cues (e.g. smiling, tone of voice), leading questions,
actions of the researcher related to the study's design (e.g. selection of participants, material,
instructions)
Randomisation is the use of chance to reduce researcher's influence on the design of investigation
• Controls investigator effects
Standardisation means all participants are subject to the same environment, information and
experience
EXPERIMENTAL DESIGN
Experimental Design: the way participants are used in experiments
Independent Groups
Independent Group Design: when two separate groups of participants experience two different
conditions of the experiment
One group is part of the experimental condition and the other is the control condition and the results
are compared
Example: a drug trial (one group has drug and other has placebo)
+ Order effects are not a problem
+ Increased external validity (more pps used)
— Pps in each group are not the same (results could be due to participant variables)
o Solution: random allocation
— Less economical than repeated measures (pps only used once)
Repeated Measures
All pps experience both conditions (experimental & control) of the experiment and then results are
compared to see if there is a difference
Example:
+ Guarantees you’re comparing ‘like with like’
+ Participant variables are controlled
+ Less pps needed
, — Order effects
o Pps have to do both tasks
o Repetition could create boredom/fatigue affecting results
o Repetition could result in pps improving due to practice
o Solution: counterbalancing
— Demand Characteristics: More likely pps will work out the aim of the study
Matched Pairs
Participants are paired together with someone who has similar characteristics which are relevant to
the experiment
Then one participant from each pair would be allocated a different condition
Example: in a memory test, pps with similar IQs may be paired together
+ Order effects & demand characteristics are less of a problem
— Pps can never be matched exactly
— Matching can be time-consuming & expensive
TYPES OF EXPERIMENT
Laboratory Experiments
They are conducted in highly controlled environments (not always a lab)
Example: Milgram’s study on obedience
+ High control over extraneous variables (EV)
o Researcher can ensure that any effect on the dependent variable (DV) is due to the
independent variable (IV) → high internal validity
+ Replication is more possible
o Due to high levels of control so new EVs are not introduced
o Replication is vital to check findings and see if it is valid
— May lack generalisability
o Lab not like everyday life so pps may not behave normally
o Leading to low external validity
— Demand characteristics
— Low mundane realism (tasks may not be like real life experiences)
Field Experiments
The IV is manipulated in a natural, everyday setting
Example: Hofling’s study on obedience (nurses following ‘doctor’ orders)
+ Higher mundane realism
+ May produce behaviour which is more valid and authentic
+ High external validity
— Loss of control of extraneous variables
— Replication often not possible
— Ethics: pps unaware they’re being studied, can’t consent to being studied
Natural Experiments
When researcher takes advantage of a pre-existing IV
• Natural as IV would have changed even if researcher wasn’t there
• Natural IV not always natural setting
Example: Studies of institutionalised Romanian orphans
+ Opportunity for research which may not be done due to practicality/ethics
+ High external validity: involve studying real life issues as they happen
— Naturally occurring event may only happen very rarely
o Less opportunity for research
o Limit generalising findings
— Pps may not be randomly allocated to experimental conditions
