Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

Research Methods
Experiments

 An experiment is an investigation looking for a causal relationship in which an independent

variable (IV) is manipulated and is expected to be responsible for changes in the dependent
variable (DV).

 There are three types of experiments:

 Laboratory experiments: A research method in which there is an IV, DV, and strict
controls. This looks for a causal relationship and is conducted in a setting which is not
the usual environment for the participant with regard to the behaviour they are
performing.

 Field experiments: This is conducted in a setting which is the normal environment for the
participant with regard to the behaviour they are performing. The researcher has control
over a few variables, but it difficult to control all variables.

 Natural experiments: An investigation looking for a causal relationship in which the IV

cannot be directly manipulated by the experimenter. Instead, they study the effect of an
existing difference or change. This is not a true experiment as the experimenter cannot
manipulate the levels of the IV.

 Laboratory experiments:

Strengths Weaknesses

High levels of standardization hence it can be replicated Artificial Environment hence it

easily to test for reliability lacks ecological validity

High levels of control hence researches can be more Participants may show demand
confident that the IV is directly affecting the DV characteristics

 Field experiments:

Strengths Weaknesses

Situational variables are difficult to control so it is

Realistic setting hence high ecological validity
tough know if the IV is affecting the DV

Limited demand characteristics so behaviour Issues in breaking ethics since the participants do
is more likely to be natural and valid not know that they’re taking part in a study

 Natural experiments:
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

Strengths Weaknesses

High ecological validity because the IV is Difficult to know whether the IV caused an effect on
naturally occurring the DV

Valid representation of a person’s Difficult to replicate to test for reliability as the

behaviour event is naturally occurring

 Each experiment consists of an experimental and control condition.

 An experimental condition is one or more of the situations in an experiment which represent the
different levels of the IV and are compared, either with one another or with the control
condition.

 A control condition is a situation in which the IV is absent. This is compared to the experimental
condition(s).

Self-reports

 Self-reports consist of two main types — questionnaires and interviews.

 Questionnaires are a research method that involves asking questions, mainly written, to gain
information from the participants.

 There are four types of questionnaires:

 Likert scales: questions asking whether the participant likes or dislikes something.

 Rating scales: questions that require the participant to represent their answer on the
numerical scale provided to them.

 Open questions: questions which allow the participant to give detailed answers without
any restrictions.

 Closed questions: questions which allow the participant to respond using a few, stated
responses without the opportunity to expand on their answers.

 Interviews are a research method using verbal questions asked directly to the participants.

 There are three types of interviews:

 Structured: an interview with questions in a fixed order which may be scripted.

Consistency might also be required in the interviewer’s posture, voice, etc., and hence
these are highly standardized.

 Semi-structured: an interview with a fixed list of questions, however, the interviewer

could add more questions if required to clarify or get details on any previous answers.

 Unstructured: an interview in which most questions depend on the respondent’s

answers. A list of topics may be provided that need to be covered for the interview.
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

 Strengths Weaknesses

Participants are more likely to give

Participants may give socially
truthful answers as it does not involve
desirable answers
talking to someone face to face

Questionnaires
A large sample can answer the
Too many closed questions may
questionnaire in a short time span which
force an answer that does not
should increase the representativeness
reflect the participant’s opinion
and generalizability of the findings

Lots of open questions will make Participants may be less likely to

participants reveal reasons as to why they give truthful answers as they are
Interviews
behave in a particular way or have a face to face with the interviewer
particular opinion or because of social- desirability

Case studies

 A detailed investigation of a single instance, usually a person, family or institute, that produced
in-depth data specific to that instance.

Strengths Weaknesses

As researchers are focused on one

individual, they can collect rich, in- As the research is focused on one person, the case is
depth data which adds validity to the unique which makes generalisations difficult
findings

Attachments may be formed between researcher and

High ecological validity as participants participant which may reduce objectivity of data
are studied in their everyday lives collected and analysis of it. This could reduce the validity
of the findings.

Observations

 A research method that involves watching human or animal behaviour.

 An observer can be overt/covert or they can be participant/non-participant observers.

 Overt observers are when the participants know who the researcher is and that they are being
observed. A covert observer could be present in the group of participants observing them but
they do not know who it is.
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

 A participant observer is one who watches from the perspective of being part of the social
setting of the participants. A non-participant observer does not become involved in the situation
being studied.

 An observation can be structured/unstructured or naturalistic/controlled.

 A structured observation is a study in which the observer records only a limited range of
behaviours. An unstructured observation is one in which the observer records a range of
behaviours, which is usually confined to a pilot study to refine the behavioural categories.

 A naturalistic observation is a study conducted by watching the participants’ behaviour in their

normal environment without interference from the researcher in either social or physical
environment. A controlled observation is one which is conducted by watching the participants’
behaviour in a situation in which the social or physical environment has been manipulated by
the researcher.

 General:

Strengths Weaknesses

If participants are unaware of the If the participants are aware of the observation, they may
observation taking place - increases not act ‘naturally’ but show more socially desirable
ecological validity behaviour. This can reduce the validity of the findings

As behaviours are ‘counted’, data It may be difficult to replicate the study if it is naturalistic as
can be analysed statistically with many variables cannot be controlled which reduces the
minimal bias reliability

 Participant observation:

Strengths Weaknesses

High ecological validity as the participants are There are ethical problems of informed
observed in a real-life setting consent

As the observers become involved with the group,

The presence of an outsider can change
they are more likely to understand the motives and
the behaviours of the group members.
reasons for behaviours which increases the validity of
This lowers the validity of the findings
the findings

 Non-participant observation:

Strengths Weaknesses

Participants behaviour will not be affected It can be difficult to make detailed observations and
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

Strengths Weaknesses

to produce qualitative data that allows

by observation because the observer is
understandings as to why the behaviours are
out of sight
occurring

Researchers’ observations are more likely

to be objective as they are detaching from
the people they are observing

 Structured observation:

Strengths Weaknesses

The behavioural checklist allows objective The sampling of observed behaviour tends to be
quantitative data to be collected which can restricted and does not give an idea of the reasons
then be analysed statistically as to why the behaviours are occurring

 Unstructured observation:

Strengths Weaknesses

They can generate in-depth, rich quantitative Observers may easily be drawn to eye catching
data that can help explain why behaviours are behaviours and hence may not fully represent all
occurring the behaviours

 Naturalistic observation:

Strengths Weaknesses

As participants are unaware that they are being Very little control over extraneous variables
watched, they should behave more naturally, which makes it difficult to draw a cause and
removing the chances of demand characteristics effect relationship

Replication may be difficult as there cannot

High ecological validity as the observation takes
be a totally standardised procedure, hence
place in a natural setting
making it difficult to test for reliability

 Controlled observation:

Strengths Weaknesses

As the set-up is controlled, the observers can be more An artificial situation can easily
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

Strengths Weaknesses

confident about what is causing the behaviours influence participants’ behaviour

Less chance of extraneous variables affecting Low ecological validity as the setting is
participants’ behaviour artificial

Correlations

 A research method which looks for a causal relationship between two measured variables. A
change in one variable is related to a change in the other, although, the changes cannot be
assumed to be causal. None of the variables are manipulated, they are only measured.

 A positive correlation is a relationship in which the increase in one variable accompanies an

increase in the other.

 A negative correlation is a relationship in which the increase in one variable accompanies a

decrease in the other.

 No correlation refuters to a situation where no definite trend occurs and the two mentioned
variables do not appear to be related to each other.

Strengths Weaknesses

The researchers easily establish a cause Issues of causality because there could be a third
and effect relationship variable affecting the changes

Correlations do not require any Correlations are restricted to research that are
manipulation so can be used where quantitative and so they cannot be used to
experiments are unethical or impractical measure why behaviours are occurring

Hypotheses and aims

 An aim tells you the purpose of the investigation. It is generally expressed in terms of what the
study intends to show. It is written before the experiment is carried out and does not predict the
outcomes.

 A hypothesis is a testable statement predicting a difference between levels of the IV in an

experiment or a relationship between variables in a correlation.

 An alternative hypothesis is the testable statement which predicts the difference or relationship
between the variables in a particular investigation.

 There are three types of hypothesis.

 A directional (one-tailed) hypothesis is a statement predicting the direction of a

relationship between variables.
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

 A non-directional (two-tailed) hypothesis is a statement predicting only that one variable

will be related to the other, not the direction of the relationship.

 A null hypothesis is a testable statement stating that any difference or correlation in the
results is due to chance.

Variables

 Independent variable (IV): the factor under investigation in an experiment which is manipulated
to create two or more conditions and is expected to be responsible for changes in the DV.

 Dependent variable (DV): the factor in an experiment which is measured and is expected to
change under the influence of the IV.

 Operationalization is the definition of variables so that they can be accurately manipulated,

measured or quantified and replicated.

Experimental design

 This is the way in which participants are allocated to the different levels of the IV.

 An independent measures design is an experimental design in which a different group of

participants is used for each level of the IV. If the IV is naturally occurring the researcher must
use.

 A repeated measures design is an experimental design in which each participant performs in

every level of the IV. It cannot be used if the IV is naturally occurring. It also uses
counterbalancing (ABBA design).

 A matched pairs design is an experimental design in which participants are arranged in pairs.
Each pair is similar in ways that are important to the study and one member of each pair
performs in a different level of the IV.

 Independent measures design:

Strengths Weaknesses

As participants take art on only one condition, they are

There may be participant variables
less likely to guess the aim of the study hence reducing
affecting the DV rather than the IV
the effects of demand characteristics

More participants are required for

There are no order effects that can reduce the validity of
this type of design as compared to
findings
repeated measures

 Repeated measures design:

 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

Strengths Weaknesses

Eliminates any participant variables There is a chance of demand characteristics as

as all of them take part in all participants may work out the aim or change their
conditions behaviour.

Order effects can affect the findings of the study and

Fewer participants are needed as
reduce its validity. This could be overcome using
compared to independent measures
counterbalancing.

 Matched pairs design:

Strengths Weaknesses

Matching participants as close as

possible on measurable traits may Trying to match participants’ similar traits is very time
help control for individual consuming.
differences affecting the results.

Trying to match people exactly is impossible as there will

This design is better suited when a
always be individual differences from one person to
repeated measures design may not
another. Therefore the study may lack internal validity if
work due to an order effect
these differences affect the IV rather than the
occurring which may affect results.
experimental condition.

The sample may be smaller as trying to find a large sample

of people matching across similar traits may be difficult.
This may mean the findings may lack external validity.

Controlling of variables

 It is essential to control variables in order to be certain about the finding of a study.

 An extraneous variable is a variable which either acts randomly, affecting the DV in all levels of
the IV, or systematically, affecting only one level of the IV (called a confounding variable), so can
obscure the effect of the IV, making the results difficult to interpret.

 A situational variable is a confounding variable caused by an aspect of the environment.

 Participant variables are another confounding variable caused by the individual differences of
participants.

 Control is a way to keep any potential extraneous variables constant. These are required to
ensure that the results of the study are reliable.

Types of data
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

 There are two types of data: qualitative and quantitative.

 Qualitative data is descriptive in-depth data indicating the quality of a psychological

characteristic.

Strengths Weaknesses

In-depth, detailed accounts given in the words of

Interpretation of data could be subjective
participants are collected. It can be argued that using
as these are words rather than numbers
qualitative data is not reductionist

As the data comes directly from the participant we There may be researcher bias - the
can understand why the participant thinks, feels or researcher may only select data that fits
acts in a particular way into the hypothesis or aim of the study

 Quantitative data is the numerical data about the quantity of a psychological measure.

Strengths Weaknesses

As the data are numerical, they miss out on

As the data are numerical, it allows easier
why participants chose the answers that they
comparison and statistical analysis to take place
did

Numerical data are objective and scientific so Using quantitative data can be seen as
there is only minimal chance of psychologists reductionist as it involves researchers reducing
miscalculating the data and drawing invalid complex ideas and behaviours to a number or
conclusions percentage

Sampling of participants

 A population is a group, sharing one or more characteristics, from which a sample is drawn.

 A sample is the group of people selected to represent the population in a study.

 Sampling technique is the method used to obtain the participants for a study from the
population. There are three types of sampling techniques.

 Opportunity sampling is when the participants are chosen because they are available at
the time and place where the research is taking place.

 Volunteer (self-selected) sampling is when participants are invited to take part in studies
via advertisements or emails.

 Random sampling is when all members of the population are allocated number and a
fixed amount of these are chosen in an unbiased way, for example, picking out numbers
from a hat.
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

 Strengths Weaknesses

Large numbers of participants can be

Researchers are unlikely to gain a
Opportunity obtained relatively quickly and easily
wide variety of participants to allow
sampling because researchers use people who
for generalization
are around

Participants are more likely to Researchers are unlikely to gain a

participate if they have already wide variety of participants to allow
Volunteer
volunteered so the drop-out rate for generalisation because
sampling
should be lower, making participants will only be of a certain
generalisations stronger type

Obtaining details of the TP to use to

Researchers can generalise the target draw the sample may be difficult - a
population (TP) with more confidence representative sample cannot be
guaranteed
Random
sampling
Researchers may gain a ‘perfect
sample’ but still have the problem
that participants will not take active
part

Validity

 Validity is the extent to which the researcher is testing what they claim to be testing.

 Internal validity is how well an experiment controls confounding variables. This allows the
researcher to be more confident about the causal relationship.

 Ecological validity is the extent to which the findings in one situation would generalise to other
situations. This is influenced by whether the situation represents the real world effectively and
whether the task is relevant to real life.

 Mundane realism is the extent to which a task represents the real-world situation.

 Face validity is a measure of validity indicating whether a measure appears to test what it claims
to.

 Concurrent validity is when a test correlates well with a measure that has previously been
validated.

 Generalizability is defined as how widely the findings of a study apply to other settings and
populations.

 Demand characteristics are features of an experiment that give away the aims. This could cause
participants to change their behaviour and hence reduce the validity of the study.
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

 Objectivity is an unbiased viewpoint that is not affected by an individual’s feelings, beliefs or

experiences, so should be consistent between different researchers. This would increase the
validity of the study.

 Subjectivity is a personal viewpoint which may be biased by one’s feelings, beliefs or experiences
and may differ between researchers. Since this is not consistent, it may reduce the validity of the
study.

Reliability

 This is the extent to which a procedure, task or measure is consistent.

 Internal reliability refers to whether the procedures are standardised so that each participant
experiences the same thing.

 External reliability is the extent to which the results of a procedure can be replicated from one
time to another, gaining consistent results.

 Inter-rater/inter-observer reliability refers to the extent to which two researchers interpreting

qualitative responses will produce the same records from the same raw data.

 There are two methods to test the reliability of a study: the split-half method and the test-retest
method.

 The split-half method involves the results of the first half of the questionnaire or interview to be
the same as the results of second half when the questions are the same in both halves but
presented in different a manner.

 The test-retest method is a way to measure the consistency of a test or task by using it twice and
then comparing the results of each time to check how similar they are.

Data analysis

 Measures of central tendency: a mathematical way to find out the typical or average score from
a data set. This includes the mean, median and mode.

 Mean is calculated by adding all the scores in a data set and dividing them by the number of
scores in the data set.

 Median is the middle score of a data set when it is ranked in order (ascending order).

 Mode is the most frequent score in a data set.

 Measures of spread: a mathematical way to describe the variation or spread within a data set.
This includes the range and the standard deviation.

 Range is the difference between the largest and smallest values with an addition of 1.

 Standard deviation is a calculation of the average difference between each score and the mean
of the data set.
 Mrs SADAF KHAN [ Teaching Sociology, Psychology & English 03335611369]

 Normal distribution is an even spread of a variable that is symmetrical about the mean, median
and mode. It forms a bell-shaped curve and is symmetrical.

 Bar charts are graphs used for data in discrete categories and total or average scores. There are
gaps between the columns as the data is not related in a linear way.

 A histogram is used to illustrate continuous data.

 A scatter graph is a way to display data from a correlational analysis.