EXPERIMENT

• In an experiment, the researcher or experimenter manipulates

certain conditions or attributes known as independent variables.

• and investigates their effects on the observed behaviour of the

participant known as the dependent variable,

• while controlling other influencing conditions known as extraneous

variables.
•
In an experiment, a causal relationship is
examined as follows: an experimenter
•
• (i) manipulates the presumed cause and observes an outcome
afterwards;
• (ii) sees whether variation in the cause is related to variation in the
effect
• (iii)... uses various methods during the experiment to reduce the plau-
sibility of other explanations for the effect... (Shadish, Cook, &
CHARACTERISTICS OF EXPERIMENTAL
RESEARCH APPROACH
• Experiments are pre-planned with design and follow a standard
procedure of measurement for variables.
• The basic characteristics of the experimental approach are as
follows:
• 1. Manipulation and control in Experiments.
• 2. Standardized procedures.
• 3. Randomization
• 4. Experimental designs
• 5. Experimenter effect
Manipulation and control in
Experiments
• In an experiment, a causative relationship is investigated between
independent and dependent variables,

• where the experimenter manipulates or changes a condition related

to the stimulus/task, situation or person, and observes its effect on
the behaviour of the participant.
EXPERIMENT ON CONFORMITY
• . In the example of an experiment on conformity, the independent
variable (IV) was group pressure,
• which is a situational variable,
• and the dependent variable (DV) was line judgement.

• The DV, which was dependent on IV, investigated whether it was the
same or different from the group decision and why conformity
behaviour was shown under group pressure
• The experimenter decided the group size and examined whether the
confederates unanimously performed the task erroneously or not.
• These factors may have affected the dependent variable, that is, the
extent of conformity.

• The first step was to define the variables theoretically and opera-
tionalize them, so as to choose how the independent variable would
be varied.
EXTRANEOUS VARIABLES
• Other variables that also influence the DV, beside IV, are known as
extraneous variables.
• Extraneous variables cause systematic and random errors in the
outcomes, and the design of the experiments is expected to control
the extraneous variables.
• Random errors occur due to participants' attitudes and systematic
errors occur due to confounding extraneous variables.
•
EXTRANEOUS VARIABLE
• In an experiment, an extraneous variable is any
variable that you’re not investigating that can
potentially affect the outcomes of your research study.
• If left uncontrolled, extraneous variables can lead to
inaccurate conclusions about the relationship between
independent and dependent variables.
• They can also introduce a variety of research biases to
your work, particularly selection bias.
 RESEARCH QUESTION Extraneous
variables

Is memory capacity related to •Test-taking time of day

test performance? •Test anxiety
•Level of stress

Does sleep deprivation affect •Road conditions

driving ability? •Years of driving experience
•Noise
Confounding variables
• Confounding variables (a.k.a. confounders or
confounding factors) are a type of extraneous variable
that are related to a study’s
independent and dependent variables.
• A variable must meet two conditions to be a
confounder:
• It must be correlated with the independent variable.
This may be a causal relationship, but it does not have
to be.
• It must be causally related to the dependent variable.
EXAMPLE OF CONFOUNDING
VARIABLE
• You collect data on sunburns and ice cream
consumption.
• You find that higher ice cream consumption is
associated with a higher probability of sunburn.
• Does that mean ice cream consumption causes
sunburn?
• Here, the confounding variable is temperature: high
temperatures cause people to both eat more ice cream
and spend more time outdoors under the sun, resulting
in more sunburns.
experiment
• Consider a fictitious experiment in which Dr. Starr examines how
listening to different types of music influences people’s feelings of
relaxation.
• The independent variable is the type of music: new age,country, or
rock.
• Sixty college students are randomly assigned to listen to one of the
three typesof music for 20 minutes.
• Afterward, they rate relaxed they feel on a questionnaire.
example
• Dr. Starr believes that the experiment will be more realistic if the
• new age music is played at a low volume,
• the country music at a moderate volume,
• and the rock music at a loud volume.
• The results show that students who listened to the new age music
felt most relaxed, while those who listened to the rock music felt least
relaxed.
• Dr. Starrconcludes that, of the three types of music, new age music is
the most relaxing.
• What is wrong with Dr. Starr’s conclusion that the type of music
caused the differences in how re laxed students felt?
• Stated differently, can you iden tify another major factor that could
have produced these results?
• Perhaps students who listened to new age music felt most relaxed
because their music was played at the lowest, most soothing
volume.
• . Had they listened to it at a high volume, maybe they would have felt
no more relaxed than the students who listened to the rock music.
•
• We now have two variables that, like the strands of a rope, are inter
twined:
• the independent variable (the type of music) that Dr. Starr really was
interested in and
• a second variable (the volume level) that Dr. Starr was not interested
in but foolishly did not keep constant.
• Confounding of variables means that two variables are intertwined in
such a way that we cannot determine which one has influenced a
dependent variable.

• In this experiment the music’s volume level is called a confound or a

confounding variable.
• Extraneous variables can be of different types and those related
with the independent variable cause systematic errors.
• Such variables are termed as confounding extraneous variables.
• Confounding variables reduce the internal validity or quality of an
experiment.
• An experimenter is required to know the sources of extra-neous
variability so that with proper designs he/she is able to control these
variables and improve the quality of results.
An experimenter can know the extent of systematic variance by
independent variables by adopting an experimental design to reduce or
eliminate systematic and random errors caused by extraneous
variables.
Extraneous variables can be controlled through random assignment of
conditions, use of control groups and through experimental
PROCEDURE.
Participant-related extraneous
variable
• Participant-related extraneous variable:
• A participant's attitude, familiarity and knowledge about the purpose
or hypothesis of the experiment can affect the response and produce
biased results.
• Using the single blind design where participants are not aware about
the objective and hypothe-sis can eliminate this random error.
• Participants who are familiar with the experiment or any part of the
tasks to be performed must not be included in the experiment. A
proper procedure with clear instructions must be followed.

• Any dependent variable influenced by intelligence level, gender and

practice level should be controlled through the experiment design.

• For example, in the previously mentioned field experiment on

impression formation (Kelly, 1950), the stimulus person was male and
the participants who comprised students were males.
Situation-related variables:
• 2. Situation-related variables:

• Variables related with task and laboratory environmental conditions,

such as noise and temperature, need to be controlled if they can
influence the dependent variable related to participant performance.
For example, hunger, fatigue or loss of concentration can set in if the
experimental task is of long duration.
• Such variables can be controlled through standardized procedures.
• 3. Experimenter-related variables:
• The experimenter may be biased if he/she is aware about the
hypothesis.
• Such errors can be controlled through double blind designs where
both the experimenter and the participants are not aware of the
objectives or hypotheses of the experiment.
Standardized procedures
• An experiment is performed objectively following proper guidelines
related to the selection of proper tools to measure IV and DV;
• instructions to the participants;
• ethical consent of the participant;
• recording of data and any qualitative observation to be noted.
•
Randomization
• Random assignment of subjects to groups: Randomization is based on
probability theory.
• It is considered the best technique of attaining experimental
equivalency.
Randomization
• According to Kerlinger (1978, pp. 123-124):Randomization is the
assignment of objects (subjects, treatments, groups) of a universe in
such a way, that, for any given assignment to a subset, every member
of the universe has an equal probability of being chosen for that
assignment.
•
• Since, in random procedures, every member of a population has an
equal chance of being selected, members with certain distinguishing
characteristics-male or female, high or low intelligence, Republican or
Democrat, dogmatic or not dogmatic, and so on and on-will, if
selected, probably be counterbalanced in the long-run by the
selection of other members of the population with 'opposite quantity
or quality of the characteristic.
True randomized experiment
• Therefore, in a true randomized experiment, the causal effects are
inferred with more accuracy due to randomization.
• Some traits of randomization are as follows:
• 1. Randomization eliminates the experimenter's biases in participant
selection for any condition.
• 2. Randomization eliminates pre-existing systematic differences in
different groups and makes the treatment and control groups
equivalent.
• 3. Randomization provides unbiased estimates of differences in the
impact of treatment as seen in the comparison of treatment and
control groups.
• The causal effect is achieved with high accuracy in a randomized
experiment. This is an index of high internal validity in a randomized
experiment.
• Internal validity also influences external validity as the precise
estimates of a laboratory experiment would lead to an accurate
prediction for field experiments.
• There are different experimental designs which are used in
experiments to control the influence of extraneous variables. Some of
these are summarized as follows:
Internal validity VS
External validity
• Internal validity refers to the degree of confidence
that the causal relationship being tested is
trustworthy and not influenced by other factors or
variables.
• External validity refers to the extent to which results
from a study can be applied (generalized) to other
situations, groups, or events.