Experimental Research Strategy

Experimental Research Strategy
 Intended to answer cause-and-effect questions about the relationship between two

variables
 If the two groups differ only on the one variable, then the variable may be considered to
be the cause of the difference
Cause and Effect Relationships
4 elements*
1. Manipulation
 Researcher manipulated one variable to create a set of 2 or more Tx conditions
Purposes:
 To allow researchers to determine the direction of a relationship
 Manipulate A
 Observe what happens to B
 Manipulation of A causes changes in B = conclude that A caused B
 To allow researcher to command one of the variables
2. Measurement
 Second variable is measured for a group of participants to obtain a set of scores in each
Tx condition
3. Comparison
 Scores in two conditions are compared
 Consistent differences between Txs = evidence that manipulation was the cause of
difference in scores
4. Control
 All other variables are controlled to be sure they do not influence the variables being
examined
Terminology
 Independent variable (IV)
 The variable manipulated by the experimenter
 Treatment condition (TC)
 A situation or environment characterized by one specific value of the manipulated

variable
 Experiment contains 2 or more TCs that differ according to the values of the IV
 Different values of IV can be selected to create different TCs = levels of IV
 Dependent variable (DV)
 A variable observed for changes in order to assess the effect of manipulating the IV
Causation & the Directionality Problem
 When cause-and-effect is demonstrated, you still may not know which is the cause and which is
the effect
E.g. successful executives tend to be more assertive than less successful executives
 Assertive people who enter these careers will tend to be successful
 Assertiveness causes success
OR
 Executive positions require people to become assertive
 people who persist and are successful tend to become assertive
 success causes assertiveness
Remember: Distinguishing Elements of an Experiment

It is possible for two variables to be related but one does not Goal:
cause the other
To establish a cause-and-effect relationship between 2
 A could cause B variables
 B could cause A
Additional goals:
 Both A and B could be caused by a
third variable Show that changes in one variable cause changes in the
other variable
Rule out possibility that the changes are caused by some

other variable
Manipulation & the Directionality Problem
Manipulation helps researchers control the influence of outside variables
Control and the Third Variable Problem
 Confounding variable
 An extraneous variable that changes systematically along with the variables being
studied
 Provides an alternative explanation for the observed relationship between the two
variables
In a true experiment…
 Experimenter wants to rule out any other explanations for the observed changes in the
DV
 Want to ensure that it was not a third confounding variable that caused the change
Dealing with Extraneous Variables
 Types of extraneous variables
 Environmental variables
 Participant variables
 Time-related variables
Control
 Researcher tries to prevent extraneous variables from becoming confounding variables
a) Holding a Variable Constant
E.g. test all individuals…

 In the same room
 At the same time of day
 By the same researcher
Disadvantages
 Requires extra effort

 Can reduce external validity
b) Randomization
Random Assignment (a.k.a. random allocation)
 Assignment process that gives each subject an equal and independent chance of being
placed in any of the groups (EG or CG)
 Reduces likelihood confounding of subject variables with IV
Advantage: can control wide variety of extraneous variables simultaneously
Disadvantage: not guaranteed to be successful
c) Matching
Procedure that ensures that both groups are equated on one or more variables before the
experiment
Match up pairs that are similar on a variable and then randomly assign each to a group
Disadvantages
 Requires extra effort

 Can reduce external validity
Control Groups
 Experimental Group
 The Tx condition
 Control group
 The group that receives no Tx or placebo Tx
 Types: No-treatment control group and Placebo control group
 No-treatment control group

o A Tx condition in which the participants do not receive the Tx being evaluated
o Provides a standard of normal behaviour – a baseline to compare the Tx condition to
o Creates a “full amount” Tx group and a “zero amount” Tx group
 Placebo Control Group

o Participants receive a placebo instead of the real Tx
o Used to separate out “real” effects from those that come from expectation
o May choose to add a 3rd, no-treatment group to evaluate the magnitude of the placebo
effect
Manipulation Checks
An additional measure to…
 assess how participants perceived and interpreted the manipulation
 assess the direct effect of the manipulation
2 ways to check:
 Use an explicit measure of the IV
 Embed specific questions about the manipulation in a questionnaire that participants

complete after their participation in the experiment
 Important in 4 situations:
1. Participant manipulations
2. Subtle manipulations
3. Simulations
4. Placebo controls
Simulation
 The creation of conditions within an experiment that simulate or closely duplicate the
natural environment being examined
 E.g. flight simulators, Stanford prison experiment
 Mundane realism
 The extent to which the superficial (usually physical)

characteristics of the research environment duplicate the Simulation & Field Study Pros & Cons
real-world environment that is being simulated
 Advantages
 Experimental realism
Allow researchers to examine
 The extent to which the psychological aspects of the behaviour in more lifelike situations =
research environment duplicate the real-world increased chances that results reflect
environment that is being simulated real events
Field Study  Disadvantages
 An experiment conducted in a place that the Allowing nature to intrude decreases

participant/subject perceives as a natural environment control (especially in field
experiments)
 Taking the experiment into the field
 E.g. staging flat tire to measure helping behaviour, placing litter on the ground to
measure littering behaviour

Experimental Research Strategy

Uploaded by

Copyright:

Available Formats

Experimental Research Strategy

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Experimental Research Strategy

Uploaded by

Copyright:

Available Formats

Experimental Research Strategy

 Intended to answer cause-and-effect questions about the relationship between two

Cause and Effect Relationships

 To allow researchers to determine the direction of a relationship

 Observe what happens to B

 Manipulation of A causes changes in B = conclude that A caused B

 To allow researcher to command one of the variables

 Independent variable (IV)

 The variable manipulated by the experimenter

 Treatment condition (TC)

 A situation or environment characterized by one specific value of the manipulated

 Different values of IV can be selected to create different TCs = levels of IV

 Dependent variable (DV)

Causation & the Directionality Problem

 Assertive people who enter these careers will tend to be successful

 Assertiveness causes success

 Executive positions require people to become assertive

 people who persist and are successful tend to become assertive

 success causes assertiveness

Remember: Distinguishing Elements of an Experiment

Rule out possibility that the changes are caused by some

Manipulation helps researchers control the influence of outside variables

Control and the Third Variable Problem

Dealing with Extraneous Variables

 Types of extraneous variables

 Researcher tries to prevent extraneous variables from becoming confounding variables

a) Holding a Variable Constant

E.g. test all individuals…

 Requires extra effort

Random Assignment (a.k.a. random allocation)

Advantage: can control wide variety of extraneous variables simultaneously

Disadvantage: not guaranteed to be successful

 Requires extra effort

 The group that receives no Tx or placebo Tx

 Types: No-treatment control group and Placebo control group

 No-treatment control group

 Placebo Control Group

An additional measure to…

 assess how participants perceived and interpreted the manipulation

 assess the direct effect of the manipulation

 Use an explicit measure of the IV

 Embed specific questions about the manipulation in a questionnaire that participants

 E.g. flight simulators, Stanford prison experiment

 The extent to which the superficial (usually physical)

Field Study  Disadvantages

 An experiment conducted in a place that the Allowing nature to intrude decreases

You might also like