What is a Psychological

Experiment?
 A well defined, systematic and controlled
procedure for identifying the causal relationship
between variables by:
 deliberately producing a change in one

variable (independent variable) and

 observing the effects of that change on another

variable (dependent variable)

Variables

 A variable is a condition that can change or

produce a change in a behavioral outcome.
 Major Types of Variables
 Independent Variable
 Dependent Variable
 Extraneous Variables
Independent Variable (IV)
 Condition(s) or factors altered or
manipulated by the experimenter
 Experimenter sets their size, amount, or
value.
 Differing values of the IV are called “levels”
 Hypothesized to cause an effect on
another variable
 The “cause variable”
Types of IV
 Stimulus Variables. Stimulus broadly
refers to any aspect of the environment
(physical, social, and so on) that excites
the receptors. e.g., light, sound etc
 Organismic Variables. Any relatively stable
physical characteristic of an organism such
as gender, eye color, height, weight, and body
build, as well as such characteristics as
intelligence, educational level, neuroticism,
and prejudice.
Dependent Variable (DV)

 Response variable
 The outcome of the experiment

 The behavioral variable being observed and

measured
 Hypothesized to be affected by an IV
 The “effect variable”
Extraneous Variables

 Any variables other than independent and

dependent variables.
 Conditions that a researcher wants to
prevent from affecting the outcomes of the
experiment (e.g., number of hours slept
before the experiment)
Experiments Step by Step
Hypothesis
 Hypothesis -- A testable prediction of the outcome of
an experiment or research
Research Hypothesis
 A hypothesis derived from an in-depth review of

the existing theories or literature

Null Hypothesis
 A statement that the independent variable will

have no effect on the dependent variable

(e.g., μ1 = μ2; σ12 = σ22).
Alternative Hypothesis
 A statement that the independent variable will

have an effect on the dependent variable

(e.g., μ1 ≠ μ2; σ12 ≠ σ22).
Select and Assign Ss to IV Levels
 Random Selection of Participants
 A procedure that assures that each individual within
the population has an equal chance of being selected.
 Random Assignment of Participants to Groups
 Participants are assigned to different groups, A and
B.
 Random Assignment of IV Levels to Groups
 IV levels are assigned to different experimental
groups on the basis of chance.
 Assures that each level of an extraneous variable has
an equal chance of occurring in all conditions of
observation. On average, the extraneous variable is
Experimental Group (Group A)

 A group of subjects in an experiment who are

exposed to the treatment (receive non-zero
values of the IV)
 Also called the experimental condition
 The group being studied and compared to the
control group
Control Group (Group A)
 A group of subjects who are exposed to a
value of zero of the IV (or receive a placebo).
 Results are compared to those of the
experimental group
 Also called the control condition

In some experiments there can be more than one

experimental group and/or more than one control group
What a Psychological Experiment
Looks Like?
Measures of a Dependent Variable
 Accuracy. The degree to which an individual responds correctly.
 Latency. Latency aka reaction time is the time (interval)
between the onset of a stimulus and the onset of a response.
 Duration/Speed. The time between the onset and the
termination of a response.
 Frequency/Rate.
 Frequency is the number of times a response occurs.

 Rate is the number of times a response occurs, on average,

in a specific period of time.

Extraneous/Confounding Variables:
Potential Problems in Experiments
 Extraneous Variables. An extraneous variable is any
variable (other than the IV and DV), that you're not
investigating that can potentially affect the dependent
variable of your research study.
 Confounding Variables. A type of extraneous variable
that not only affects the dependent variable, but is also
related to the independent variable.
 The most dangerous type in terms of challenging the validity
of experimental results
 An alternative explanation for observed findings in a study.
Sources of Extraneous/Confounding
Variables
 Individual Differences
 Ideally there should be minimum individual
differences between the experimental groups.
Sources of Extraneous/Confounding
Variables
 Environmental Differences
 Any differences in the experiment’s conditions
 between the experimental and control groups

 Differences include temperature, lighting, noise

levels, distractions, etc.
 Ideally, there should be a minimum of
environmental differences between the two
groups.
Sources of Extraneous/Confounding
Variables
 Subject’s Expectancy Effects
 Any change in DV due to the subject anticipating
certain outcomes to the experiment
 Self-fulfilling prophecy: A prediction that leads
participants to act in ways to make the prediction
come true.
 Experiment’s title: The effects of horror movies
on mood
 Subtle cues or signals by the researcher that
communicate type of responses that is expected.
 Biased or leading questions: Don’t you think it’s
bad to murder unborn children?
Sources of Extraneous/Confounding
Variables
 Experimenter’s Expectancy Effects
 The experimenter may influence the results
(intentionally and unintentionally)
Sources of Extraneous/Confounding
Variables
Techniques to Control Extraneous/
Confounding Variables
 Except for the IV, each subject should have
as closely similar an experience in the
experiment as possible.
 Elimination
 A goal in experimentation is to eliminate as
many confounding/ extraneous variables as
possible, to remove their potential effects on
the DV.
 Applies for the known extraneous/
confounding variables (e.g., sound, noise).
Techniques to Control Extraneous/
Confounding Variables
 Constancy of Conditions
 Applies when confounding/ extraneous
variables are known but elimination is not
possible.
 The values of the known confounding/
extraneous variables remain the same across
levels of the IV (e.g., room temp, light levels,
time-of-day, etc).
Techniques to Control Extraneous/
Confounding Variables
 Balancing
 Personal characteristics
 Sometimes called “demographic” variables.
 Sex, height, weight, age, education, ethnicity,
socio-economic status, etc.
 Can be balanced by getting an equal number
of participants of each characteristic in each
study group.
Techniques to Control Extraneous/
Confounding Variables
 Counterbalancing
 Counterbalancing is a type of experimental design in which all possible orders of presenting the variables are included.
 The general principles of counterbalancing are
 Each condition is presented to each subject an equal number of times.
 Each condition must occur an equal number of times at each experimental session.
 Each condition must precede and follow all other conditions an equal number of times.
Techniques to Control Extraneous/
Confounding Variables
 Counterbalancing with 2 Conditions
 Using an ABBA design when there are 2 experimental conditions, such as A and B.
 The simplest form of counterbalancing.
 Every subject is tested in both conditions. Researchers divide the Ss into two equal groups; one group is treated with Condition A, followed by Condition B, and the other group is tested with Condition B followed by Condition A.
Techniques to Control Extraneous/
Confounding Variables
 Counter Balancing with 3 Conditions
 If you have three experimental conditions, the process is exactly the same and you would divide the subjects into 6 equal groups, treated as
orders ABC, ACB, BAC, BCA, CAB and CBA.
Techniques to Control Extraneous/
Confounding Variables
 Randomization
 Confounding or extraneous variables can be controlled by allowing
them to vary randomly in an unsystematic or unbiased way across
levels of the IV.
 This can be done by random assignment of Ss to the IV levels.
 Personal/demographic characteristics
 Sex, height, weight, age, education, ethnicity, socio-economic status, etc.
 The variable thus created is known as a random variable.
 Techniques to Control Extraneous/
Confounding Variables
 Using a placebo
 Placebo- A false treatment or a non-active chemical
substance (e.g., pill) used instead of a drug or active
ingredient.
 The placebo group serves as a baseline to compare with
the behavior of the experimental group.
 Reduces expectancy effects.
Placebo: A Threat to Experimental
Validity
 Why is Placebo a Threat?
 The placebo effect is the effect produced by a sham
(placebo) treatment (e.g., sugar pill), generated by
subject's thinking they are being treated. This means that
a study that does a pre-test measure, gives all subjects a
treatment, then gives a post-test measure, has a
confounding variable.
Techniques to Control the Threat of
Placebo
 Single Blind Procedure
 An experimental procedure where the research
participants are ignorant (blind) to the expected
outcome of the experiment.
 Only the subjects have no idea whether they
get real treatment or placebo.
 Techniques to Control the Threat of
Placebo
 Double Blind Procedure
 Technique in which neither the experimenter
nor participant is aware of the group to which
participant is assigned.
 The subjects AND the experimenter have no
idea whether the subjects get real treatment or
placebo
 Best type of experiment, if properly set up
Ethical Considerations in
Research/Experimental Designs
 Research ethics involves the application of
fundamental ethical principles to research activities
which include the design and implementation of
research, respect towards participants, society and
others, the use of resources and research outputs,
scientific misconduct and the regulation of research.

 Ethics to Protect Participants

 Ethical Considerations in
Research/Experimental Designs
1. Central Issues in Research Ethics
 Informed Consent
 The voluntary and revocable agreement. Each participants sign a
document affirming that they know the basic outline (nature,
purpose) of the study
 Comprises four elements
 Disclosure – adequacy of the account provided by the

experimenter
 Comprehension – extent of understanding what he/she

has been told about the study.

 Competence – ability to reach a rational, autonomous

decision
 Voluntariness – absence of pressure, influence and

coercion
 Ethical Considerations in
Research/Experimental Designs
 Privacy and Confidentiality
 Anonymity
 Deception-- A technique whereby a participant is not made
fully aware of the true nature of a research study, such as
omitting some information or not informing specific purposes
of the study.
 In a psychological research, deception is a highly debatable ethical
issue.
 Sometimes, deception is used in social, behavioral and
educational research in order to obtain accuracy information.
For such a research, the less the subjects know the better.
 Some psychologists argue that deceiving participants in a
research study is dishonest.
 Ethical Considerations in
Research/Experimental Designs
 Risk or harm – should be free from physical,
psychological, social and economic harms
 Each participant should be informed even if there is any
minor irritations
 Exploitation
Ethical Considerations in
Research/Experimental Designs
2. Gaining Ethical Approval
 An application must be made to the relevant Research Ethics
Committee (or Institutional Review Board, USA).
 The study should not proceed until approval has been
granted.