Psyc 224 - Lecture 6

PYSC 224: Experimental Psychology
• Lecture 6
Quasi Experiments
Quasi Experiment
• Quasi experiment- ‘an experiment that does not meet
all the requirements necessary for controlling the
influence of extraneous variable’ (Christensen, 2007, p. 330)
• Participant variables such as age, sex, etc. cannot be

experimentally manipulated
• Participants cannot be randomly assigned to a

particular condition
• Instead they are exposed to a condition because they

already qualify for that condition
Quasi Experiment
• The experimenter can only select instances that

satisfy different categories and study them
• Uses natural manipulations rather than

manipulations by the researcher
• ‘Manipulation’ could be naturally occurring attribute

or events such as ethnic group, age, sex, intelligence
etc.
Quasi Experiment
• Sometimes called ‘ex post facto’ or ‘after the fact’
experiments
• The experiment is conducted after the groups
have been formed
• The inability to control confounding variables
reduces the internal validity of a quasi experiment
but does not make it invalid
Quasi Experimental Designs
Quasi Experimental Designs
• Two types of quasi experimental designs
❑1. Non-equivalent control group design
❑2. Non-equivalent Pretest-posttest design

Non-equivalent control group design
• The performance of an experimental group is

compared with that of a non-equivalent control
group
• There is no random assignment of subjects thus,

the groups are not equivalent
• Thus, difference between the groups becomes a

confounding variable
• This provides an alternative explanation for the

results obtained
• Testing non-equivalent groups of subjects

creates selection difference
Experimental Independent Measure

Group Variable Dependent Variable
Lottery
Non-equivalent No Measure
Control Independent Dependent Variable
Group Variable
• Example-The effect of stress management on

hypertensive patients
• An experimenter may recruit ‘willing’ hypertensive

patients who serve as the experimental group and
are administered stress management
• The experimenter later recruits more hypertensive

patients to serve as the control group
• Thus, the two groups are not equated

• Differences found between the two groups, may be
as a result of the stress management or difference
between the two groups
• This design is similar to the true experiment

posttest-only
Non-equivalent pretest- posttest design
• An experimental and control group are pretested

and posttested
• However, the two groups are not equivalent

• Differences between the groups, may be as a
result of the initial difference or the effect of the
independent variable
Non-equivalent pretest- posttest design
Pretest: Administer Posttest: Measure

Experimental Measure Independent Dependent Variable
Group Dependent Variable
Variable
Non-equivalent Pretest: No Posttest: Measure

Control Measure Independent Dependent Variable
Group Dependent Variable
Variable
Comparing Quasi Experiments
and True Experiments
True Experiments and Quasi Experiments
• 1. Major difference- random assignment of

participant to experimental groups in true
experiments but not quasi experiments
• 2. Experimenter manipulates variables in

true experiments but observes categories of
participants in quasi experiments
True Experiments and Quasi Experiments
• 3. True experiments- Control permits the

establishment of cause effect relationship
• 4. Quasi experiment- cannot be determined

whether difference in behaviour is caused by the
independent variable or the difference between the
two groups
• Generally, true experiments are preferred to a quasi

experiment
Faulty Experimental Designs
Faulty Experiment
• Faulty experimental designs usually do not have a
control group and sometimes do not include a pretest
• There is internal invalidity as a result of not minimizing

extraneous variables
• Two types of faulty research designs

❑1. One group posttest-only design
❑2. One group pretest-posttest design
One Group Posttest-only design
• An experimental group is administered the

independent variable and then tested on the
dependent variable
• There is no comparison group or pretest measure

• At a minimum, participants should be pretested
• Also, an equivalent control group must be included
One Group Posttest-only design
Experimental Independent Posttest:

Group Variable Measure Dependent
(listen to Variable
music) (Mood)
One-Group Pretest-Posttest design
• The effect of an independent variable is inferred
from the pretest-posttest differences in a single
group
• This design is faulty because it does not take into

account extraneous variables such as history,
maturation, etc.
• Also, there is no control group to compare the

experimental group with
Pretest-Posttest design
Experimental Pretest: Administer Posttest:

Group Measure Independent Measure
Dependent Variable Dependent
Variable Variable

Psyc 224 - Lecture 6

Uploaded by

Copyright:

Available Formats

Psyc 224 - Lecture 6

Uploaded by

Document Information

Original Title

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

Psyc 224 - Lecture 6

Uploaded by

Copyright:

Available Formats

PYSC 224: Experimental Psychology

• Participant variables such as age, sex, etc. cannot be

• Participants cannot be randomly assigned to a

• Instead they are exposed to a condition because they

• The experimenter can only select instances that

• Uses natural manipulations rather than

• ‘Manipulation’ could be naturally occurring attribute

• Two types of quasi experimental designs

❑1. Non-equivalent control group design

❑2. Non-equivalent Pretest-posttest design

• The performance of an experimental group is

• There is no random assignment of subjects thus,

• Thus, difference between the groups becomes a

• This provides an alternative explanation for the

• Testing non-equivalent groups of subjects

Experimental Independent Measure

• Example-The effect of stress management on

• An experimenter may recruit ‘willing’ hypertensive

• The experimenter later recruits more hypertensive

• Thus, the two groups are not equated

• This design is similar to the true experiment

• An experimental and control group are pretested

• However, the two groups are not equivalent

Pretest: Administer Posttest: Measure

Non-equivalent Pretest: No Posttest: Measure

• 1. Major difference- random assignment of

• 2. Experimenter manipulates variables in

• 3. True experiments- Control permits the

• 4. Quasi experiment- cannot be determined

• Generally, true experiments are preferred to a quasi

• There is internal invalidity as a result of not minimizing

• Two types of faulty research designs

• An experimental group is administered the

• There is no comparison group or pretest measure

Experimental Independent Posttest:

• This design is faulty because it does not take into

• Also, there is no control group to compare the

Experimental Pretest: Administer Posttest:

You might also like