By : Ahmad Adnan bin Mohd Shukri
By :
Ahmad Adnan bin Mohd Shukri
Introduction
– QD is based in the scientific method.
– Uses deductive reasoning.
– Researcher forms hypothesis, collects data in an
investigation of the problem.
– Then, uses the data from the investigation, after analysis is
made and conclusions are shared, to prove the hypotheses
are true or false.
4 Types of Quantitative Design
1. Experimental studies
2. Comparative
3. Correlational
4. Survey
Experimental Studies
– Often called true experimentation.
– Use the scientific method to establish cause-effect
relationship among variables in a research study.
– Researchers make an effort to control for all variables except
the one being manipulated (independent variable).
– The effects of the independent variable on the dependent
variable are collected and analysed for a relationship.
– Although questions may be posed in the other forms of
research, experimental research is guided specifically by a
hypothesis.
– Sometimes experimental research can have several
hypotheses.
– A hypothesis is a statement to be proven or disproved.
– Once that statement is made, experiment is begun
The major feature that distinguishes
experimental research from other types of
research is ….
–the researcher manipulates
the independent variable.
–Subjects are randomly
assigned to experimental
treatments
Experimental designs should be
developed to ensure internal and
external validity of the study
Internal Validity
– Are the results of the study (DV) caused by the factors
included in the study (IV) or are they caused by other factors
extraneous variables (EV) which were not part of the study.
– EV are unwanted variables that may have an effect on the
experimental outcome. (ex: if you ware worried about
gender, only include one gender in the study).
Threats to Internal Validity
– Subject characteristics ( Selection Bias)
– The groups may have been different from the start. If you
were testing instructional strategies to improve reading and
one group enjoyed reading more than the other group, they
may improve more in their reading because they enjoy it,
rather than the instructional strategy you used.
– Location
– Perhaps one group was at a disadvantage because of their
location.
– Example, the city may have been demolishing a building next
to one of the school in your study, there are constant
distractions which interfere with your treatment.
– Instrumentation (Instrument Decay)
– The testing instruments may not be scored similarly. Perhaps
the person grading the post test is fatigued and pays less
attention to the last set of papers reviewed. It may be that
those papers are from one of your groups and will receive
different scores from the earlier group’s paper.
– Data collector bias
– The person collecting data may have favours one group or
some characteristics some subject posses over another.
– Example, a teacher who favours strict classroom
management may rate student’s attention under different
teaching conditions with a bias toward one of the teaching
conditions.
– Resentful demoralization of the control group
– The control group may become discouraged because it is not
receiving the special attention that is given to the treatment
group. They may perform lower than usual because of this.
Once the researchers are confident that the outcome
(DV) of the experiment they are designing is the result
of their treatment (IV) internal validity, they determine
for which people or situations the results of their study
apply external validity
External Validity
– Are the results of the study generalizable (can be
applied) to other populations and settings
– Comes in two forms :
1) Population validity
2) Ecological validity
Population Validity
– Is the extent to which the results of a study can be
generalized from the specific sample that was
studied to a larger group of subjects
Ecological Validity
– Is the extent to which the results of an experiment
can be generalized from the set of environmental
conditions created by the researcher to other
environmental conditions (settings and conditions)
Threats to External Validity
– Pretest Sensitization
– A treatment might only work if a pre-test is given. Because they have
taken a pretest, the subjects may be more sensitive to the treatment. Had
they not taken a pre-test, the treatment would not have worked.
– Measurement of the DV
– A treatment may only be evident with certain types of measurements. A
teaching method may produce superior results when its effectiveness is
tested with an essay test, but show no differences when the effectiveness
is measured with a MCQ test. (maybe only works with MCQ test)
– First and foremost, an experiment must have internal validity.
If the researchers cannot certain that the results of the
experiment are dependent on the treatment, it does not
matter to which people or situations they wish to generalize
(apply) their findings. The importance of external validity is
reliant on having internal validity in much the same way that
the validity of a measurement instrument is reliant on the
instrument being reliable.
Different Research Designs
1) One-shot case study design
2) One-group pre test-post test design
3) Static group pre test-post test design
4) Static group comparison design
5) Randomized post test only, control group design
6) Randomized pre test-post test control group design
7) Randomized Solomon four-group design
One-shot case study design
One-group pre test-post test
design
Static group pre test-post test
design
Static group comparison design
Randomized post test only, control
group design
Randomized pre test-post test
control group design
Randomized Solomon four-group
design
– Each of the design described in this section has
advantages and disadvantages that influence the
studies internal and external validity.
Quasi is
“resembling”
Quasi experiment involve procedures that resemble those of true experiments.
31
QUASI-EXPERIMENTAL RESEARCH
Include intervention or treatments but lack degree of “control”
e.g Lack of Randomization
32
33
Quasi Experimental Designs
This type of design involves a treatment (manipulation ) and an outcome but lacks one of the other two properties that characterize a true experiment: randomization or a control group.
Example: if you want to study the effects of smoking on a variable, you cannot randomly assign people to smoking vs nonsmoking group.
34
Quasi-experimental Methodology
In this methodology, the essential controls are not administered, such as treatments not being randomized. It is otherwise similar in structure to a true experimental design.
Types of Quasi Experiments
One group pre-test post-test design
Non equivalent control group design
Interrupted time series design
Time series with non-equivalent control group designs
35
Why need quasi experiments ?
One group pretest- post test design representsPre –experimental design
36
One group pretest – post test design
Comparison of treatment group and comparison group/ control group
Pre-test and post-test measures are used
37
Non equivalent control group design
38
Non equivalent control groups - other than the absence of randomly assigned groups, these designs are similar to experimental designs . However, lack of random assignment to control and experimental groups, can not assure that the groups are equal. The researcher must do everything possible to show that there are no differences. For example, a pretest may show that there is no difference. If the study is done on "after only data", this control is not present
Manipulation of independent variable
Pretest for all of the comparison groups
Post test for all comparison groups
No random assignment to the comparison groups (which as you can imagine is going to cause some problems with this design as compared to the strong “randomized” experimental designs.
39
Essential features
In education, difficult to do true experiment because of the difficulty to have randomization, no control on the scheduling of treatment.
Lost part of the power due to lack of randomization (assignment of subjects)
Control of extraneous variable, difficult. External validity is enhanced ―> may be moving
toward real world setting
40
41
Use when true experiment is not possible
Any design that does not randomly assigned subjects to the group is known as quasi-experimental designs.
Researchers do not use randomization but rely instead on other techniques to control threat to internal validity
CORRELATIONAL RESEARCH
Muhamad Aisamuddin Ridhuan
To discover c0-relationships
among two or more variables
To describe the relationship; to predict one variable from the
other
.
is considered type of observational research as nothing is manipulated by the
experimenter or individual conducting the research
Also known as
associational
research
Nothing was controlled by the researchers.
In other words, we can not make statements concerning cause and effect on the basis of this type of research.
Is often conducted as exploratory or beginning research. Once variables have been identified and defined, experiments are conductable.
also known as
associational
research
INTRODUCTIONAND
PURPOSE
.
also known as
associational
research
To describeCo-relationships that exist between two or
more variables(Explanatory Design)
also known as
associational
research
To identify relationship that can be useful in making predictions.
(Prediction Design)
To describeCo-relationships that exist between two or
more variables
also known as
associational
research
.
.
If we know vocabulary and school learning are correlated
We can predict that students with better vocabularies will usually learn more than students with limited vocabularies.
is considered type of observational research as nothing is manipulated by
the researcher
To describeCo-relationships that exist between two or
more variables
also known as
associational
research
To identify relationship that can be useful in making
predictions.
is considered type of observational research as
nothing is manipulated by the researcher
It often conducted as exploratory or beginning research.
To describeCo-relationships that exist between two or
more variables
also known as
associational
research
To identify relationship that can be useful in making
predictions.
is considered type of observational research as
nothing is manipulated by the researcher
In other words, we can not make statements concerning cause and effect on the basis of this type of research.
It often conducted as exploratory or beginning research.
To describeCo-relationships that exist between two or
more variables
also known as
associational
research
To identify relationship that can be useful in making
predictions.
To discover c0-relationships
among two or more variables
To describe the relationship; to predict one variable from the
other .
is considered type of observational research as nothing is manipulated by the
experimenter or individual conducting the research
Also known as
associational
researchIn other words, we can not make statements concerning cause and effect on the basis of this type of research.
Is often conducted as exploratory or beginning research. Once variables have been identified and defined, experiments are conductable.
INTRODUCTIONAND
PURPOSE
NTS
CORRELATION COEFFICIENTS
.
CORRELATION COEFFICIENTS
.
To determine the degree of relationship between two variables, researchers calculate a statistic called a
correlation coefficient.( represented pictorially by a scattergram )
.
Scattergrams
.
high scores on one are associated with high scores on the other, and that low scores on one are associated with low scores on the other.
.
high scores on the first thing are associated with low scores on the second or low scores on the first are associated with high scores on the second.
.
.
.
Correlational Research Design
1. Variables whose relationship is to be explored are identified and clarified.
.
2. Questions or hypotheses are stated
Correlational Research Design
.
Correlational Research Design
.
Correlational Research Design
3. A sample is selected – preferably 30 or more
.
Correlational Research Design
3. A sample is selected – preferably 30 or more
.
Correlational Research Design
4. Measurements are obtained from each of the sample members on each of the variables being explored.
.
Correlational Research Design
5. Correlations between and among variables are computed to determine degrees of relationship.
.
Example of research
.
Example of research
.
Example of research
What is survey ?
Method of gathering information
Measurement tools used in research to collect data
Measurement procedures that involving respondents by asking and answer the questions given
Types of survey :
a) Questionnaire
Type of survey
Questionnaire
Consist of a series of questions & other prompts
Usually the items used are essay or agree/neutral/disagree style
Questionnaire
Open-ended questions Closed-ended questions
Question ask respondent to
formulate their own
answer/opinions
Useful for descriptive study
Respondent pick an answer from given answer option
4 types of scales response:
Dichotomous – 2 options
Nominal – polytomous –more than 2 unordered options
Ordinal-polytomous – more than 2 ordered option
Bounded (continuous) –respondent is presented with a continuous scale
Definition of closed – ended questions Dichotomous – The questions that only have two possible answer ( Yes/No),
(Agree/Disagree) or (True/False)
Nominal – Polytomous – The questions that have more than two unordered answer (Education level)
Ordinal – Polytomous – The questions that have more than two ordered answer ( Answer has meaning = Rating scales from lowest
to highest/highest to lowest )
Bounded (continuous) – Questions should flow logically from the least sensitive to the most sensitive
Dichotomous questions Ordinal Questions
What is your household annual income?
1 Less that $5,0002 $5,000 to $9,9993 $10,000 to $14,9994 $15,000 to $19,9995 $20,000 to $29,0006 $30,000 to $39,9997 $40,000 to $49,0008 $50,000 to $75,0009 Over $75,000
11. What is your education level?
1 - High School or lower2 - Some College3 - College Graduate4 - Some Graduate School5 - Master's Degree6 - Doctorate
Nominal Questions
Example journal
Journal using questionnaire
Effectiveness of ICT Integration in Malaysian Schools: A Quantitative Analysis by Ghavifekr Simin and Ibrahim Mohammed Sani, (2015,August 8) Faculty of Education, University of Malaya.
Interviews
Face to face
Telephone
Video – conferencing
Advantages Disadvantages
Can be developed in short period of time
Cost are effective and low
Capable of collecting data from large number of respondents
May not accurate/honest answer given by respondent
Survey question answer options could lead to unclear data
Selecting the Survey Method
There are 6 criteria of decisions:
1. Population issues
2. Sampling issues
3. Question issues
4. Content issues
5. Bias issues
6. Administrative issues
Population issues
• Can population be enumerated?
• Is the population literate?
• Are there language issues?
• Cooperation from respondents
• Demographic restrictions
Sampling issues
• What data is available?
• Respondents availability?
• Respondents target
• Can all members of population be sampled?
Question issues
• What type of questions can be asked?
• Level of difficulties?
• Will lengthy questions be asked?
Content issues
• Respondent knowledge about the issues asked?
Bias issues
• Can social desirability be avoided?
• Can false respondents be avoided?
Administrative issues
• Costs
• Facilities
• Time
• Personnel
.