Psychological Experiment: Dr. Most. Aeysha Sultana (MAS1)

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 12

PSY 101L:

Psychological Experiment
Dr. Most. Aeysha Sultana (MAS1)
Professor
North South University

Lecture Outline
 Psychological experiment
 Variables
 Hypothesis testing
 Manipulating IV: Choosing its levels
 Types of dependent variable
 Measuring dependent variable
 Operational definitions
 Potential problems
 Control/Elimination of biases
 The Ethics of Experiment /Research
 Post-Experimental Interview
 Steps in writing an experimental report

What is Psychological Experiment?


 The experiment is a well defined, systematic and controlled procedure for identifying
the causal relationship between two (or more) variables by:
 deliberately producing a change in one variable and
 observing the effects of that change on other variable
Variables
 A variable is a characteristic whose value varies from person to person, object to
object or from phenomenon to phenomenon.
 For example, age, sex, height, weight, intelligence etc.

1
 Types of Variables
 Independent Variable
 Dependent Variable
 Extraneous Variable
Independent Variable (IV)
 The independent variable is the condition or factor that is altered or manipulated by an
experimenter.
 Types of independent variables:
• Treatment variable
• Classification variable
• Treatment variable- The modification in the experimental subject is manipulated
(created) by the experimenter. Example- different dosages of a drug or different method
of learning
Independent Variable (IV) (cont.)
Classification variable-
(i) a characteristic exists prior to the experiment;
(ii) not created by the experimenter; rather
(iii) selected by the experimenter
Example – experimental subjects may be classified on IQ level or socioeconomic status
(classification variable) by the experimenter.
 Differing values or categories of the IV are called “levels”. Thus, an IV must have at
least two levels.
 Hypothesized to cause an effect on another variable
 Called as the “cause variable”
Dependent Variable (DV)
 The variable that is measured and is expected to change as a result of changes caused by
the experimenter’s manipulation of the independent variable.
 Hypothesized to be affected by an IV
 Called as the “effect variable”
 Experimental manipulation- the change that an experimenter deliberately produces in a
situation.

2
Extraneous Variable
 Conditions or factors that an experimenter wants to prevent from affecting the outcomes
of the experiment (e.g., walking activities between the time of sugar water consumption
and taking the measure of sugar level of diabetic patients)
 Any variables other than independent and dependent variables.
Hypothesis Testing
 Hypothesis: a tentative statement about the relationship between two or more variables.
 A specific, clear, testable prediction about the outcome of the experiment or research
---Example – “sleep-deprived people will perform worse on a test than individuals who
are not sleep deprived.”
 Research Hypothesis
A hypothesis derived from an in-depth review of the existing literature or theories

 Null Hypothesis
 A statement that the independent variable will have no effect on the
dependent variable.
 No significant difference observed between specified populations due to
manipulation in independent variable,
 Rather, observed difference being due to sampling or experimental error.
 The null hypothesis is assumed as correct until it is rejected through
scientific evidence.
 It reduces the possibility of confirmation bias
Manipulating IV:
Choosing its Levels
 Methods of manipulation
 Straightforward
• Stimulus manipulation - different conditions use different stimuli
• Instructional manipulation – different groups are given different
instructions

3
 Staged
• Event manipulation – manipulate characteristics of the context, setting, etc.

 Selection– Select participants from pre-existing groups or categories (e.g., males


vs females; muslim vs nonmuslim)
• leads to a quasi-experiment
Experimental Manipulation: Assigning Ss to the Levels of IV
 Treatment
 Manipulation implemented by the experimenter
 Random Assignment of Participants to Groups
 Participants are assigned to different groups, say A and B.
 Random Assignment of IV Levels to Groups
 IV levels are assigned to different experimental groups on the basis of chance.

The Process of Random Assignment


 Randomization –The procedure which assures that-
 each member of population has equal probability of being selected
in the experiment.
 each level of an extraneous variable has an equal chance to be
occurred in all conditions of observation.
 the extraneous variable is not confounded with our manipulated
variable (or have no confounding effect on the relationship
between IV and DV. ) because randomization may help to
eliminate many confounding variables
 Through randomization procedure, the researcher creates both a control and a
experimental group which are -
 chosen from a population and
 considered equal reliably on dependent variable at the start of the experiment.

4
 Experimental Group
 A group of subjects (participating in an experiment) are exposed to the treatment
(receive non-zero values of the IV)
 Also called the experimental condition in sum situation
 The group is studied for comparing with the control group
 Control Group
 A group of subjects (participating in an experiment) are not exposed to the treatment
(receive a zero value of IV).
 The control group are compared to those of the experimental group on dependent
variable
 Also called the control condition
*The experimenter may create more than one experimental group and/or more than one
control group deepening on the purpose of experiment

 Dependent Variable
Types of dependent variables
 Directly observable
• example- choice/decision (sometimes timed)
 Indirectly observable
• Example- Physiological measures (e.g. GSR, heart rate) Behavioral measures (e.g.
speed, accuracy)
Measuring DV
 The way to measure DV:
 Participant’s self-report
(through administering scales/tests of measurement)
 Asking questions

Operationally Definitions
 Variables must be operationally defined (specifying the operations or procedures) due to
-manipulate the IV of interest.
-measure the DV of interest

5
-enable others to replicate that
*For a single conceptual definition, there may be several operational definitions (and DVs).
Examples: Quality of memory -- accuracy of recall in a certain task

Basic Characteristics of an Experiment


 Randomization
Many basic experiments consist of two levels of the independent variable which are randomly
assigned to study groups.
 Control over extraneous variables
 holding constant
 randomizing effects
 A causal relationship can be established between the independent and dependent variables.
 Operational definitions

Confounding Variables
 A type of extraneous variable that -
--changes or varies systematically across levels of the IV
--challenges the validity of experimental results
---may be a potential cause for the experimental effect, other than the IV
--may be an alternative explanation for observed findings in a study.

6
 Examples of Confounding Variables
 Individual Differences
 Environmental Differences
 Subject’s Expectancy Effects
 Experimenter’s Expectancy Effects

 Individual Differences
Ideally there should be minimum individual differences between the experimental groups
 Environmental Differences
Any differences in the experiment’s conditions (between the experimental and control groups),
such differences may include temperature, lighting, noise levels, distractions, etc.
*Ideally, there should be a minimum of environmental differences between the two groups.

 Subject’s Expectancy Effects


 Any change in DV due to subject’s anticipation regarding 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?
 Experimenter’s Expectancy Effects
 Experimenter bias (expectancy effects)
• The experimenter may influence the results (intentionally and unintentionally)

7
Eliminating/Controlling Bias:
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

8
Eliminating/Controlling Bias:
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 experimenters have no idea whether the subjects get real treatment
or placebo.
• Best type of experiment, if properly set up.

Eliminating/Controlling Bias:
Control Variable
 A variable whose values remain the same across levels of the IV (e.g., room temp, light
levels, time-of-day, etc.).
 A goal in experimentation is to control as many variables as possible, to eliminate their
potential effect on the DV. Such as eliminating both confounds and noise.
 Except for the IV, each subject should have as closely similar an experience in the
experiment as possible.

9
Eliminating/Controlling Bias:
Random Variable
 Variable whose values vary randomly in an unbiased way across levels of the IV.
 Random variables are usually created by the process of random assignment to levels in
the experiment.
Eliminating/Controlling Bias:
Subject Variable
 A personal characteristic
• Sex, height, weight, age, education, ethnicity, socio-economic status, etc.
 Sometimes called a “demographic” variable.
 Data describing subject characteristics should be collected in every study.
 Can be controlled or left to vary unsystematically (through random assignment to levels).

Eliminating/Controlling Bias:
Control Group
 The group that receives no intervention, “zero” or “the absence of” the IV.
• For example, the placebo group in a drug experiment.
 Placebo- A non-active substance or condition administered instead of a drug or active
agent
 The group that serves as a baseline to compare with the behavior of the experimental
groups.
 Reduces expectancy effects

The Ethics of Experiment /Research


 Protecting Participants as The Aim of The Ethical Guidelines
 APA (American Psychological Association, 2002)Ethical Guidelines:
 Assurance that participation is completely voluntary
 Protect from physical and mental harm
 Participants’ right to privacy regarding behavior
 Informing participants about the nature of procedures prior to participation

10
 Informed Consent: One of Key Ethical Principles
 A document signed by participants affirming that they know:
 the basic outlines of the study
 what their participation will involve
 the risks the experiment may hold
 that their participation is purely voluntary
 they may terminate the study at any time

Experiments Step by Step

11
Post-Experimental Interview
The participant’s reactions to the test/ experiment/ research are assessed.
 Participants are asked to express their thought about the research.
 When the research uses deception, the participants will be given a suspicion check -
questions about the extent to which they believe the experimental manipulation was real.

Steps in Writing Experimental Report

 Title page
 Abstract
 Introduction: State the research question, review the literature, make the predictions
(hypotheses). The subheadings under this section are as follows-
 Literature review
 Objective of the experiment
 Variables
 Hypothesis
 Method: Describe how you explored the question in sufficient detail to permit replication.
This section includes the following subheading-
 Design
 Participant(s)
 Materials
 Procedure
 Results: Describe your findings and test your hypotheses using statistics.
 Discussion: Analyze your results and put them back into the context of your question.
 Conclusion
 References
 Appendices

12

You might also like