Methods in

Psychological
Research

Psychology is a science
Methods in Psychological
Research
Psychology requires
information which is
accurate, reliable and
appropriate
Research to answer
questions about behaviour
and mental processes
Lahey, B. (2009); Fieldman R. S. (2010) Understanding
Psychology (9th edition)
Methods in Psychological Research

Two forms of psychological

research:
Basic research seeks answers for
the purpose of increasing knowledge.
(e.g. What role do the frontal lobes play in
memory?)
Applied research seeks answers for
specific problems. (e.g. What types of
memory strategies and
Lahey, rehabilitation
B (2009); Fieldman R. S (2010)
strategies are most effective
Understanding for people
Psychology (9 edition)
th
 Key Terms Let’s take a more objective
look (Stanovich, 2007).
Empirical evidence & Operational Definitions

Empirical evidence:
Evidence from observations of publicly observable
behaviour/phenomena
Psychologists often observe public behaviour and
often use those observation to draw inferences
about private processes that are not publicly
observable

Lahey, B (2009); Stanovich, 2007;

 Key Terms
 Theories & Hypotheses

 Theories: Broad explanations

Once a question has been identified, the next step
in the scientific method is to develop a theory to
explain the observed phenomenon.
Is a framework for understanding the relationships
among a set of otherwise unorganised
facts/principles
Unlike Personal explanations of behaviour,
psychologists’ theories are more formal and
focused (theory of Diffusion of responsibility by Latane &
Darley, 1970).
 Key Terms
Theories & Hypotheses

Hypotheses
A theory is tested by testing a prediction
based on that theory
Hypothesis stems from theories and helps
to test the underlying soundness of
theories
It is a prediction stated in a way that allows
it to be tested; this involves creating an
 Key Terms
 Operational Definitions
Psychologist describe their empirical evidence
through the use of operational definitions
specifies the exact meaning of a variable in an
experiment/study by defining it in terms of
observable operations, procedures, and
measurements.
An acceptable operational definition is that the
procedure is specified precisely enough to
allow replication by others.
Exmples:
 quality of memory -- accuracy of recall in a
certain task Lahey, B (2009); Fieldman R. S (2010) Understanding
Psychology (9 edition)
th
 Examples
Verbal Statement Operational Definition

1. Comes to class early

2. Does not use phone during class
He is a good student 3. Contributes to discussions
4. Writes short notes and quickly
 Sample & Representativeness of Sample
 Sample
Psychologist study small groups of participants in
order to understand something about the
population.
Small groups of participants should be
representative of the population
Using sample data, psychologists calculate
various statistics, such as the mean and standard
deviation.
 Sample & Representativeness of Sample
 Sample
These sample statistics summarize (describe)
aspects of the sample data.
These data, when treated with other statistical
procedures, allow psychologist to make certain
inferences about the population.
From the sample statistics, we make
corresponding estimates of the population
parameters.
 The Scientific Method: Steps

Psychologist rely of the scientific method to

ask appropriate questions and properly
answer them
Steps of the Scientific method
1. Identifying questions of interest (Make
observations & define problem)

2. Formulate an explanation (propose hypothesis)

3. Carrying out research (gather evidence)

4. Draw conclusions
5. Communicating the findings (Publish results)
Psychology is a science
6. Theory building
Steps in the Scientific method

1. Identifying questions of interest

 Questions of interest can stem from a behaviour and
phenomenon, prior research findings, curiosity, creativity,
insight
2. Formulation of an explanation
 Specify a theory,
 Develop a hypothesis
3. Carrying out research designed to support or refute the
explanation
 Devise an operational definition of the hypothesis
 Select a research method
 Analyze the data
4. Draw conclusions
5. Communicating the findings
 At Conferences, in journals etc
Methods in Psychological Research

Psychologist employ a variety of

methods for collecting data,
which may be divided into three
groups
1. Descriptive Methods
2. Correlational Methods
3. Experimental Methods
 1. Descriptive Methods

Seek to describe a sample of subjects, usually

with the aim of generalising the results to the
larger population of which the sample is
representative
Allows the estimation of the population
parameter
Descriptive methods use a minimum of one
variable
Common types of descriptive
method are;
1. The survey
2. Naturalistic observation
3. Laboratory observation
4. Case study
 The survey

an investigation of many cases in less

depth by asking people to report opinions
and behaviours
Uses interviews or questionnaires to collect
data from large numbers of people, for
example by post, telephone or face to face
Usually done by asking a representative
What is a
sample of people—accurately portrays
population?
the
population of interest. What is
representativeness
Naturalistic observation

Recording behavior in its natural

environments, and describing it in
detail
Observations can be overt or covert;
includes case studies (or clinical
observations)
e.g., effects of social interaction on people’s
behavior; one study found that people laugh
30 times more often in social situations than
 Of Chips

Primatologist Jane Goodall

studied Chimps in their
natural environment.
 Case Study: The clinical method

one case at a time

Is an in depth investigation of a
single (or very few) case
The Case Study

Through a series of
case studies, often
of his own children,
Jean Piaget
developed the
theory of cognitive
development, which
assumes that
cognitive functions
unfold through a
series of distinct
stages.
Correlational Methods

Consider an association
between:
the IQs of parents and their
children,
beauty and social popularity,
anxiety and test performance,
Crime and the weather.
Correlational Methods
Purpose is to observe naturally
occurring relationships between
two or more variables
No independent variables are
manipulated
Two or more variables are
measured and a relationship
established
Measure the relationship in terms
Correlational Methods
Can be extended to include
interrelationships between many
variables
Since these methods are measures of
association only, Correlational
research does not PROVE causality.
Sometimes however, causality may
be argued, following complex
multivariate correlational
 Correlational Coefficients
How is the degree of correlation expressed?

The strength and direction of a

relationship can be expressed as a
coefficient of correlation.
This can be calculated as a number falling
somewhere between 0.00 and 1.00.
Drawing graphs of relationships can also
help clarify their nature (Scatter plots)
If the number is zero or close to zero,
the association between two measures is
weak or nonexistent
What do you think is the correlation between shoe
size and intelligence?
 Correlational Coefficients
How is the degree of correlation expressed?

If the correlation is 1.00, a perfect

positive relationship exists
if it is –1.00, a perfect negative
relationship has been discovered
What about 0.5?
 Experimental Methods
Purpose is to explore cause and effect by
manipulating one or more factors, while holding other
factors constant
An experiment is a formal trial undertaken to confirm
or
disconfirm a hypothesis about the causes of
behaviour
Intended to test hypothesis (what is a hypothesis?)
A change in variable A will cause a change in
variable B
Which one is the IV and which the DV?
Variable: anything that can fluctuate
To discover the causes of behaviour, we must usually
conduct an experiment.
 Experimental Methods

In an experiment, we distinguish between the

independent variable (IV) and a dependent
variable (DV)

In an experiment, the experimenter manipulates

the IV and measures the effect on the DV?

Variable: anything that can fluctuate

e.g., memory, attention, time taken to perform a task

effects of Alcohol (IV) on driving ability (DV)

The IV is often manipulated into
two conditions which are tested on
an experimental group and a
control group of subjects
Control group exposed to all
conditions except the IV.
The number of IVs and DVs vary
with experiments
Unwanted variables, other than
IVs and DVs may affect the
accuracy ofexperimental
experiments group and a control group?
Back to ‘effects of Alcohol (IV) on
driving ability (DV)”
Give examples of extraneous
variables:
Familiarity with the car
Familiarity with the test.
Used to drinking
Full stomach
Uncontrolled extraneous variables
may become confounding
Uncontrolled extraneous variables may become
variables
confounding variables
 4 types of Extraneous
variables
Situational Variables
Aspects of the environment that might
affect the participant’s behaviour, e.g.
noise, temperature, lighting conditions,
instructions
Standardization ensures that conditions
are the same for all participants. This
includes standardized instructions
Counterbalancing, half the participants
condition 'A' first, while the other half
 4 types of Extraneous
variables
Participant/Person Variable
Ways in which each participant varies
from the other, e.g., mood, intelligence,
anxiety, nerves, concentration ability
Imagine participants performance on a
memory task, a participants is tired,
dyslexic or had poor eyesight
Random assignment to the conditions
of the IV used to control participant
variables
 4 types of Extraneous
variables
Experimenter/Investigator Effects
Happens when the experimenter
unconsciously conveys to participants
how they should behave (called
experimenter bias).
Might happen through giving
unintentional clues to the participants
about what the experiment is about
and how they expect them to behave.
Experimenter personal attributes (e.g.
age, gender, accent, manner etc.) can
 4 types of Extraneous
variables
Demand Characteristics
 All clues in an experiment which convey to
the participant the purpose of the research.
They include:
a. The surroundings;
b. Researcher’s characteristics;
c. The researcher’s behaviour (e.g. non-
verbal)
d. Own interpretation of what is going on in
the situation.
 To minimize these experimenters should
keep the environment as natural as possible,
In a lab, extraneous variables
can also be controlled through
the following techniques:
Eliminating the variable from
the research setting
Holding the variable at a
constant value
Choosing subjects who
represent a wide or matched
 An example?
Social loafing refers to people’s tendency to
slack on group tasks. In one study on social
loafing college participants cheered alone,
and in groups of 2, 4, or 6 people. They were
told to cheer as loud as possible at specific
times so researchers could determine how
much noise people made in social settings.
The amount of noise made by each
participant dropped as group size increased.
1) What is the IV?
2) What is the DV?
3) Why is random assignment important here?
Quasi-experiement

Similar to the experimental design, but

NO “random assignment”; does not
meet all of the requirements necessary
for controlling the influence of
extraneous variables, especially those
identified with the individual subject
{e.g., family history)
Quasi-experiement
In a quasi-experiment, an IV can only be
manipulated indirectly, usually by
appropriate selection of subjects
Easily and more frequently
implemented
Widely used in the social sciences
A useful method for measuring social
variables
Suppose a teacher wants to perform an educational
experiment: She divides her class arbitrarily by seating
arrangement. The division is often convenient and, causes as
little disruption as possible
BUT are we Measuring what we think we’re testing?

 Measurement Error
When we measure some psychological
construct, we do so with some amount
of error
 Observed Score = True score + Error of measurement

Type of error we are concerned with: A

measure’s inability to capture the
true response for an individual
1. Reliability
2. Validity
Imagine:

 You get one score when I

mark the test but a
completely different
score when the
Departmental chair
marks the same test!
Reliability
Would a particular technique (or
survey question) yield the same
result each time?
A measure is reliable if it
produces the same data each time
over repeated tests/ observations.
 Reliability

Reliability refers to the consistency

of experimental operational
definitions and measured operational
definitions.

Example: Should a reliable BP scale

display the same BP if you measure
yourself three times in the same
minute.
Interrater reliability

Interrater reliability is the degree

to which observers agree in their
measurement of the behavior: how
closely different people who are
marking a test or observing a
behaviour agree with each other.
Test-retest reliability means the
degree to which a person's scores
are consistent across two or more
administrations of a measurement
procedure.
Example: highly correlated scores
on the Wechsler Adult Intelligence
Scale-Revised
when it is administered twice, 2
weeks apart.
Interitem reliability measures the
degree to which different parts of an
instrument (questionnaire or test) that
are designed to measure the same
variable achieve consistent results.
 Validity

Validity means the operational definition

accurately manipulates the independent
variable or measures the dependent
variable.
Refers to the extent to which a method
truly tests what the researcher is trying
to test
Face validity is the degree to
which the validity of a
manipulation or measurement
technique is self-evident.
This is the least stringent form
of validity.
Content validity means how
accurately a measurement procedure
samples the content
of the dependent variable.

Example:
Predictive validity means how
accurately a measurement procedure
predicts future performance.

Example:
Construct validity is how
accurately an operational definition
represents a construct.

Example:
Internal validity is the degree to
which changes in the dependent
variable across treatment conditions
were due to the independent variable.

Internal validity establishes a cause-

and-effect relationship between the
independent and dependent variables.
The extent to which the
measurement object of a test
is self-evident is known as
what?

A. Face validity
B. Content Validity
C. Construct validity
 Problem of confounding Revisited.

Confounding occurs when an extraneous

variable systematically changes across
the experimental conditions.

Example: a study comparing the effects of

meditation and prayer on blood pressure
would be confounded if one group
exercised more.
History threat occurs when an
event outside
the experiment threatens internal
validity by changing the dependent
variable.
Maturation threat is produced
when physical
or psychological changes in the
subject threaten internal validity by
changing the DV.

Example: boredom may increase

subject errors on a proofing task (DV).
Testing risk occurs when prior
exposure to a measurement
procedure affects performance on this
measure during the experiment.

Example:
Instrumentation threat is when
changes in
the measurement instrument or
measuring procedure threatens internal
validity.

Example: if reaction time measurements

became less accurate during the
experimental than the control conditions.
Selection threat occurs when
individual differences are not
balanced across treatment conditions
by the assignment procedure.

Example: despite random

assignment, subjects in the
experimental group were more
extroverted than those in the control
group.
Subject mortality threat occurs
when subjects drop out of
experimental conditions at different
rates.

Example: even if subjects in each

group started out with comparable
anxiety scores, drop out could
produce differences on this variable.
 RESEARCH
ETHICS
Free scientific inquiry
Vs.
Human dignity and a
person’s right to privacy
and protection from harm
 Research Ethics

Research ethics concerns the responsibility of

researchers to be honest and respectful to all
individuals who may be affected by their
research studies or their reports of the
studies’ results
 When & why?
Ethical issues must be considered at
each step in the research process
When you are considering
measurement techniques to be used
for certain individuals
When selecting individuals to
participate in studies
Deciding on research strategies and
designs to use with certain populations
and behaviors
The processing of carrying out studies
with individuals
When & why?
 Researcher has Ethical responsibility
To the human and nonhuman
individuals who participate in the
research study
To the discipline of science
Ethical issues

Justification for the research

Informed consent
Protection from harm
Maintain confidentiality
Use of Deception
Debrief
Justification for the research

When human are involved as subjects

in a research, the risks and costs must
be balanced against the potential
benefits

Trivial or repetitive research may be

unethical where the subjects are at
risk
Ethical issues and human participants in research

No harm
protect participants from physical or
psychological harm
Psychological harm – participants may
feel increased anxiety, anger, lower self-
esteem especially in situations where
they feel that they have been cheated
or insulted
any risk of harm must be justified
participants must be informed of any
APA Guidelines (major ethical issues
potential risks
Ethical issues and human participants in research

Informed consent
Give complete information about the research
and participant’s role in it
Participants should understand the
information and then voluntarily decide
whether or not to participate
information
understanding –e.g. children, provide the
information to a parent or a guardian
voluntary participation

APA Guidelines (major ethical issues

Ethical issues and human participants in
research

Deception – when informed consent can not be

obtain before the study
 to obtain unbiased results researchers must sometimes
use deception because participants may adjust their own
levels of performance in an attempt to satisfy the
experimenter
 Deception can be:
 Passive deception (or omission) is the withholding or
omitting of information (researcher intentionally does not
tell participants some information about the study)
 Active deception (or commission) is the presenting of
misinformation about the study to participants (misleading
participants about the specific purpose of the study)

APA Guidelines (major ethical issues

Ethical issues and human participants in research

 guidelines for a study involving deception:

 Deception must be justified in terms of some benefit

that outweighs the risk to the participants

 But the researcher reveals to participants any

significant aspects of the study that is expected to
cause physical pain or severe emotional stress

 After completing the study, provide debriefing that

explains the true nature of the experiment, including
the use and purpose of deception
APA Guidelines (major ethical issues
Ethical issues and human participants in
research

Confidentiality
o Keeping strictly secret and private the
information or measurements obtained
from an individual during a research study

Anonymity
o Ensuring that an individual’s name is not
directly associated with the information
or measurements obtained from that
individuals (e.g. using codes)

APA Guidelines (major ethical issues

End