Research Methods
Experimental Method:
Experimental Method
Aim ~ a general expression of what the researcher intends to
investigate. E.g., To investigate whether drinking energy drinks makes Control of variables/Research issues
people more talkative. Experimental design
Hypothesis ~ a statement of what the researcher believes to be true
of the relationship between the independent and dependent variables. Types of experiment
- Directional hypothesis – predicts which if the two conditions Sampling
will result in a greater change in the dependent variable. E.g.,
Ethical issues and ways of dealing with
There will be significantly more cones knocked over by those
who have drunk 3 pints of beer compared to those who them
have not. Pilot studies
- Non-directional hypothesis – the experimenter thinks the
independent variable will affect the dependent variable but Observational techniques
not sure in what direction. E.g., There will be a significant Observational design
difference in the number of cones knocked over between
Self-report techniques
those who have drunk 3 pints of beer and those who have
not. Self-report design
- Null hypothesis – contradicts the experimental hypothesis. Correlations
E.g., There will be no significant difference in the number of
cones knocked over by people who have drunk 3 pints of Types of data
beer than those who haven’t. Any results are due to chance. Measures of central tendency and
- The independent variable is the variable that the
experimenter manipulates, and the dependent variable is the dispersion
variable that the experimenter measures. Graphs
Operationalisation IV – alcohol or no IV – whether Peer review and psychological research
~ clearly defining alcohol participants receive
variable in terms of 50ml of alcohol or and the economy
how they can be no alcohol Case studies and content analysis
measured. E.g., table DV – memory DV – result in a
Reliability
memory test
Types of validity
Control of Variables/ Research Issues:
Choosing a statistical test
Extraneous variables ~ Any variable other than the independent
variable that may affect the dependent variable if it is not Probability and significance
controlled e.g., time of day, order effects, investigator effects, age, Mann-whitney and Wilcoxon
gender
Confounding variables ~ any variable other than the independent Unrelated and related t-tests
variable that affects the dependent variable so we cannot be sure Spearman’s and pearsons
of the true source of changes to the dependent variable e.g., years of
Chi-squared test
driving experience
Demand characteristics ~ any cue from the researcher or from the Reporting psychological investigations
research situation that may be interpreted by the participants as Features of science
revealing the purpose of the investigation. This may lead to the
participant changing their behaviour within the research situation.
- This can be reduced by using different participants in each condition, so they are less likely to
realise the aims of the study
- Single blind experiment where the participant doesn’t know which side of the experiment they are
assigned to.
, Investigator Effects ~ any effects of the investigator’s behaviour on the research outcome. This may
include everything from the design of the study to the selection of and interaction with participants during
the research process.
- Can be reduced by using a double-blind trial where neither the researcher nor the participants
know which side of the study they are on.
Randomisation ~ the use of chance when designing investigations to control for the effects of bias.
Standardisation ~ using exactly the same formalised procedure for all participants in a study.
Control groups ~ used for comparison, act as a baseline
Experimental Design:
Independent groups – One group do condition A and one group do condition B. Participants should be
randomly allocated to experimental groups
AO3:
+ No order effects – participants are only tested once so can’t practise or become bored, controls
an important confounding variable.
+ Less likely to guess research aims, therefore behaviour may be more natural
- The participants in the two groups are different, acts as confounding/extraneous variables, may
reduce the validity of the study
- Need twice as many participants as repeated measures for the same data, more time spent
recruiting which is expensive.
Repeated Measures – Same participants take part in all conditions of an experiment. Order should be
counterbalanced (done in different orders by participants) to avoid order effects.
AO3:
+ The person in both conditions has the same characteristics, controls an important confounding
variable.
+ Half the number of participants is needed as an independent groups study, less time spent
recruiting participants.
- Order effects – participants may do better or worse when doing a task twice, reduces the
validity of the results.
- Participants may guess aims and change their behaviour, this may reduce the validity of the
results.
Matched Pairs – Two groups are used but they are also related to each other by being paired on participant
variables that matter for the experiment.
AO3:
+ Participants matched on a variable that is relevant to the experiment, enhances the validity of
results.
+ Only tested once so no order effects because of practice or fatigue, enhances validity
- Matching is time consuming and can’t control all relevant variables – may not address participant
variables
- Need twice as many participants as repeated measures for the same data, more time spent
recruiting which is expensive.
Types of Experiment:
Lab experiments – An experiment carried out in a controlled environment within which the researcher
manipulates the IV and records the effect on the DV. The participants go to the researcher.
AO3:
+ High control over extraneous variables, researcher can ensure the effect on the DV is a result of
the IV.
+ Replication is easy because of high levels of control
Experimental Method:
Experimental Method
Aim ~ a general expression of what the researcher intends to
investigate. E.g., To investigate whether drinking energy drinks makes Control of variables/Research issues
people more talkative. Experimental design
Hypothesis ~ a statement of what the researcher believes to be true
of the relationship between the independent and dependent variables. Types of experiment
- Directional hypothesis – predicts which if the two conditions Sampling
will result in a greater change in the dependent variable. E.g.,
Ethical issues and ways of dealing with
There will be significantly more cones knocked over by those
who have drunk 3 pints of beer compared to those who them
have not. Pilot studies
- Non-directional hypothesis – the experimenter thinks the
independent variable will affect the dependent variable but Observational techniques
not sure in what direction. E.g., There will be a significant Observational design
difference in the number of cones knocked over between
Self-report techniques
those who have drunk 3 pints of beer and those who have
not. Self-report design
- Null hypothesis – contradicts the experimental hypothesis. Correlations
E.g., There will be no significant difference in the number of
cones knocked over by people who have drunk 3 pints of Types of data
beer than those who haven’t. Any results are due to chance. Measures of central tendency and
- The independent variable is the variable that the
experimenter manipulates, and the dependent variable is the dispersion
variable that the experimenter measures. Graphs
Operationalisation IV – alcohol or no IV – whether Peer review and psychological research
~ clearly defining alcohol participants receive
variable in terms of 50ml of alcohol or and the economy
how they can be no alcohol Case studies and content analysis
measured. E.g., table DV – memory DV – result in a
Reliability
memory test
Types of validity
Control of Variables/ Research Issues:
Choosing a statistical test
Extraneous variables ~ Any variable other than the independent
variable that may affect the dependent variable if it is not Probability and significance
controlled e.g., time of day, order effects, investigator effects, age, Mann-whitney and Wilcoxon
gender
Confounding variables ~ any variable other than the independent Unrelated and related t-tests
variable that affects the dependent variable so we cannot be sure Spearman’s and pearsons
of the true source of changes to the dependent variable e.g., years of
Chi-squared test
driving experience
Demand characteristics ~ any cue from the researcher or from the Reporting psychological investigations
research situation that may be interpreted by the participants as Features of science
revealing the purpose of the investigation. This may lead to the
participant changing their behaviour within the research situation.
- This can be reduced by using different participants in each condition, so they are less likely to
realise the aims of the study
- Single blind experiment where the participant doesn’t know which side of the experiment they are
assigned to.
, Investigator Effects ~ any effects of the investigator’s behaviour on the research outcome. This may
include everything from the design of the study to the selection of and interaction with participants during
the research process.
- Can be reduced by using a double-blind trial where neither the researcher nor the participants
know which side of the study they are on.
Randomisation ~ the use of chance when designing investigations to control for the effects of bias.
Standardisation ~ using exactly the same formalised procedure for all participants in a study.
Control groups ~ used for comparison, act as a baseline
Experimental Design:
Independent groups – One group do condition A and one group do condition B. Participants should be
randomly allocated to experimental groups
AO3:
+ No order effects – participants are only tested once so can’t practise or become bored, controls
an important confounding variable.
+ Less likely to guess research aims, therefore behaviour may be more natural
- The participants in the two groups are different, acts as confounding/extraneous variables, may
reduce the validity of the study
- Need twice as many participants as repeated measures for the same data, more time spent
recruiting which is expensive.
Repeated Measures – Same participants take part in all conditions of an experiment. Order should be
counterbalanced (done in different orders by participants) to avoid order effects.
AO3:
+ The person in both conditions has the same characteristics, controls an important confounding
variable.
+ Half the number of participants is needed as an independent groups study, less time spent
recruiting participants.
- Order effects – participants may do better or worse when doing a task twice, reduces the
validity of the results.
- Participants may guess aims and change their behaviour, this may reduce the validity of the
results.
Matched Pairs – Two groups are used but they are also related to each other by being paired on participant
variables that matter for the experiment.
AO3:
+ Participants matched on a variable that is relevant to the experiment, enhances the validity of
results.
+ Only tested once so no order effects because of practice or fatigue, enhances validity
- Matching is time consuming and can’t control all relevant variables – may not address participant
variables
- Need twice as many participants as repeated measures for the same data, more time spent
recruiting which is expensive.
Types of Experiment:
Lab experiments – An experiment carried out in a controlled environment within which the researcher
manipulates the IV and records the effect on the DV. The participants go to the researcher.
AO3:
+ High control over extraneous variables, researcher can ensure the effect on the DV is a result of
the IV.
+ Replication is easy because of high levels of control
