Professional Documents
Culture Documents
Department of Education
Region V
12
Schools Division of Sorsogon
BULUSAN NATIONAL HIGH SCHOOL
Practical Research 2
Learning Activity Sheet 8
Name of Student: ______________________________________________ Date: __________________________
The discussion of designs will provide a more advanced understanding of research on your journey.
In this learning activity sheet, you will learn about each design: its definition, its historical development,
its key characteristics, and the steps and procedures of conducting and evaluating a study. Research
design and methodology are presented and explained in Chapter 3 of the conventional format of a research
manuscript.
III. Activities
A. Let Us Review
The first Learning Activity Sheet (LAS 1) introduced you to the fundamentals of quantitative
research. It also provided you inputs on the different types of quantitative research as well as their
strengths and weaknesses. Check the type/s of quantitative research to which each statement applies.
Write your answer on your answer sheet.
1
B. Let Us Study
What is Research Design?
Research design is the entire strategic plan or blueprint of how to go about finding the answers to
research question/s. It refers to the overall strategy used to logically and coherently integrate the various
components of a study and provides the glue that holds the research project together.
Research Design provides detailed information about the following aspects of the study:
Who will constitute the study population?
How will the study population be identified?
Will a sample or the whole population be selected?
If a sample is selected, how will it be contacted?
How will consent be sought?
What method of data collection will be used and why?
In the case of interviews, where will they be conducted?
How will ethical issues be taken care of?
Research Design vs. Research Methodology
Research design is different from the research method by which data are collected. Many tend to
confuse research designs with research methods and treat it as a mode of data collection rather than as
a logical structure of the research inquiry. Failing to distinguish between design and method leads to poor
evaluation of designs.
Descriptive research
Case study
Descriptive Designs Observe and describe
Naturalist observation
Survey
Descriptive research encompasses a variety of methodologies that are best suited to examining and
trying to make sense of a situation or event as it currently exists in the world. By and large, descriptive
research does not involve changing or modifying a situation under investigation, nor is it intended to
determine cause-and-effect relationships. This general category of research designs includes both
An observation study in quantitative research might be conducted with plants rather than animals,
or it might involve nonliving objects (e.g., rock formations, soil samples) or dynamic physical phenomena
(e.g., weather patterns, black holes). It tends to have a limited, prespecified focus.
When human beings are the topic of study, the focus is usually on a certain aspect of behavior.
Furthermore, the behavior is quantified in some way. In some situations, each occurrence of the behavior is
counted to determine its overall frequency. In other situations, the behavior is rated for accuracy,
intensity, maturity, or some other dimension. But regardless of approach, a researcher strives to be as
objective as possible in assessing the behavior being studied. To maintain such objectivity, the
researcher is likely to use strategies such as the following:
Define the behavior being studied in such a precise, concrete manner that the behavior is easily
recognized when it occurs.
Divide the observation period into small segments and then record whether the behavior does
or does not occur during each segment.
Use a rating scale (e.g., Likert Scale) to evaluate the behavior in terms of specific dimensions.
Have two or three people rate the same behavior independently, without knowledge of one
another’s ratings.
B. Correlational Study
A correlational study examines the extent to which differences in one variable are associated with
differences in one or more other variables. A correlation exists if, when one variable increases, another
variable either increases or decreases in a somewhat predictable fashion. Knowing the value of one
variable, then, enables us to predict the value of the other variable with some degree of accuracy.
In correlational studies, researchers gather quantitative data about two or more characteristics for
a particular group of people or other appropriate units of study. Whatever the nature of the data, at least
two different variables are assessed in order to determine whether and in what way these variables are
interrelated.
When two variables are correlated, researchers sometimes conclude that one of the variables must
in some way cause or influence the other. But ultimately, we can never infer a cause-and-effect
relationship on the basis of correlation alone. Simply put, correlation does not, in and of itself, indicate
causation.
Ideally, a good researcher isn’t content to stop at a correlational relationship because beneath the
correlation may lie some potentially interesting dynamics. One way to explore these dynamics is through
structural equation modeling (SEM) which is a statistical procedure.
C. Developmental Designs
Oftentimes, when researchers want to study how a particular characteristic change as people grow
older, they use one of two developmental designs: either a cross-sectional study or a longitudinal study.
In a cross-sectional study, people from several different age groups are sampled and compared.
For instance, a developmental psychologist might study the nature of friendships for children at ages 4, 8,
12, and 16. A gerontologist might investigate how retired people in their 70s, 80s, and 90s tend to spend
their leisure time.
In a longitudinal study, a single group of people is followed over the course of several months or
years, and data related to the characteristic(s) under investigation are collected at various times. For
3
example, a psycholinguist might examine how children’s spoken language changes between 6 months and
5 years of age. Or an educational researcher might get measures of both academic achievement and social
adjustment for a group of fifth-graders and then, 10 years later, find out what their high school grades
were and whether they had actually graduated and earned a diploma.
D. Experience-Sampling Methods
An experience-sampling method (ESM) is an approach in which a researcher collects frequent
and ongoing data about people as they live their normal, everyday lives. Many ESM studies require some
kind of technological device that people wear or carry with them. For example, a study might involve
having participants (a) wear small electronic devices that measure their movements, heart rate, or blood
pressure; (b) carry smartphones that regularly ask brief survey questions; or (c) carry cameras with which
they take pictures of their immediate surroundings or current activities.
E. Survey Research
In survey research, a researcher obtains information about one or more groups of people—
perhaps about their behaviors, opinions, attitudes, or previous experiences—by asking them questions
and either directly tabulating or systematically coding their answers. Often, it involves collecting data
about a sample of individuals that is presumed to represent a much larger population.
In the descriptive designs described earlier, there was no systematic attempt to determine the
underlying causes of the phenomena being studied. In order to convincingly pin down cause-and-effect
relationships, experimental design is used. In such a design, many possible factors that might cause or
influence a particular behavior, characteristic, or other phenomenon are considered. Such factor that
influences behavior or phenomenon is called an independent variable while the behavior is considered the
dependent variable. All influential factors except those whose possible effects are the focus of investigation
are controlled.
In experimental research, two groups are considered. We take steps to make sure that, on average,
the two groups are so similar that, for all intents and purposes, we can call them equivalent. One group is
called the control group while the other is the experimental group. Only one of the groups is exposed to a
treatment or intervention.
A diagram is one way to represent the experimental design when you are either conceptualizing or
designing one.
Experimental designs can be represented using four (4) symbols – O, X, R and a dashed line.
The symbol “X” represents the independent variable (experimental manipulation) which is presumed
“cause” for the behavior.
In simple experiment, one group is exposed to the experimental treatment and a control group is not
exposed to the experimental treatment.
Absence of “X” indicates no treatment.
The symbol “O” represents the dependent variable which is the observed variable and is measured
at more than one point in the study.
The symbols are arranged to represent order of events in the study.
This means that the first symbol stands for the first thing that happened in the experiment –
was it experimental intervention “X” or was it “O” to assess the participant’s behavior?
4
Either “X” or “O” can come first.
An initial “O” is called a pretest and provides baseline information to the researcher.
An “O” that follows experimental treatment is a posttest.
When there is more than one experimental group, one more design feature is added to the diagram.
How were the participants assigned to the different groups?
If they were assigned randomly, the symbol “R” is written at the beginning of each row of “Os”
and “Xs”.
Randomization creates equivalent groups such that extraneous variables like socioeconomic
status and personality characteristics are randomly distributed.
If random assignment is not used, the groups are said to be nonequivalent and is represented
by a dashed line between the rows of “Os” and “Xs”.
A. Pre-Experimental Designs
5
Assignment
Experimental Group O X O
Random
Control Group O O
The addition of two groups who are not pretested has a particular advantage. If the researcher
finds that in the final assessment, Groups 3 and 4 differ in much the same way that Groups 1 and 2 do,
then the researcher can more easily generalize his or her findings to situations in which no pretest has
been given. In other words, the Solomon four-group design enhances the external validity (i.e.,
generalizability) of the study.
Experimental Group 1 O X O
Assignment
Random
Control Group 1 O O
Experimental Group 2 X O
Control Group 2 O
Experimental Group X O
Random
Control Group O
In a strictly within-subjects design, all subjects or participants are exposed to all experimental
treatments and any control conditions. In a good within-subjects design, the various treatments are
administered very close together in time, in some cases simultaneously. If we use the subscripts a and b
to designate the different treatments and treatment-specific measures, then in its simplest form, a within-
subjects design is as follows:
Xa Oa
Experimental Group
Xb Ob
C. Quasi-Experimental Designs
The quasi-experimental research design aims to establish a causal relationship between two
variables. This effect is presumed to have occurred during the study itself. In this type of study, there is
no randomization. When quasi-experimental studies is conducted, researchers don’t control for all
confounding variables, and so they can’t completely rule out some alternative explanations for the results
they obtain.
Design 8: Nonrandomized Control-Group Pretest–Posttest Design
The nonrandomized control-group pretest–posttest design can perhaps best be described as a
compromise between the static group comparison (Design 3) and the control-group pretest–posttest design
(Design 4). Like Design 3, it involves two groups to which participants haven’t been randomly assigned.
6
But it incorporates the pretreatment assessments of Design 4. In sum, the nonrandomized control-group
pretest–posttest design can be depicted as follows:
Experimental Group O X O
Control Group O O
Identifying matched pairs in the two groups is one way of strengthening the non-randomized
control-group pretest–posttest design.
Design 9: Simple Time-Series Design
A time-series design consists of making a series of observations (i.e., assessing the dependent
variable on several occasions), introducing an intervention or other new dynamic into the system, and
then making additional observations. If a substantial change is observed in the second series of
observations in comparison to the first series, we might reasonably conclude that the cause of the change
was the factor introduced into the system. The design thus looks something like the following:
Experimental Group O1 O2 O3 O4 X O5 O6 O7 O8
In a variation of the time-series design, two groups are observed over a period of time, but one
group (a control) doesn’t receive the experimental treatment. The general design takes the following form:
Experimental Group O1 O2 O3 O4 X O5 O6 O7 O8
Control Group O1 O2 O3 O4 O5 O6 O7 O8
Experimental Group X O1 - O2 X - O3
Experimental Group Xa O1 - O2 Xb O3 - O3 Xa O4 - O5 Xb O6
Designs 11 and 12 are based on the assumption that the effects of any single treatment are
temporary and limited to the immediate circumstances. Thus, these designs won’t work if a treatment is
likely to have long-lasting and perhaps fairly general effects. Furthermore, if an experimental treatment is
apt to be quite beneficial for all participants, then ethical considerations may discourage us from including
an untreated control group.
In such instances, a multiple-baseline design provides a good alternative. This design requires at
least two groups. Prior to the treatment, baseline data are collected for all groups, and then the treatment
itself is introduced at a different time for each group. In its simplest form, a multiple-baseline design might
be configured as follows:
Baseline Treatment
Experimental Group 1
- O1 X O2 X O3
Baseline Treatment
Experimental Group 2
- O1 - O2 X O3
7
3. EX POST FACTO DESIGNS
Ex post facto designs (the term ex post facto literally means “after the fact”) provide an alternative
means by which a researcher can investigate the extent to which specific independent variables may
possibly affect the dependent variable(s) of interest. In an ex post facto study, a researcher identifies
events that have already occurred or conditions that are already present and then collects data to
investigate a possible relationship between these factors and subsequent characteristics or behaviors.
Design 14: Simple Ex Post Facto Design
Design 14 is similar to the static group comparison (Design 3) described in the previous section on
pre-experimental designs. The critical difference is one of timing: In this case, the “treatment” in question
occurred long before the study began; hence, we call it an experience rather than a treatment because the
researcher hasn’t been responsible for imposing it. A simple ex post facto design can be depicted as
follows, where Exp refers to a prior experience that one group has had and another has not:
Such designs are common in studying the possible effects of previously occurring environmental
variables such as television viewing habits, child abuse, and malnutrition. They are also used in studying
the potential influences of pre-existing characteristics—perhaps those that are inherited or congenital—
such as gender, mental illness, and physical disability.
4. FACTORIAL DESIGNS
The designs discussed previously dealt with only one independent variable. If a researcher
examines the effects of two or more independent variables in a single study; this approach is a factorial
design.
Experimental Group 2 X1 - O
Experimental Group 3 - X2 O
Control Group - - O
We can determine the effects of the first independent variable by comparing the performances of
Groups 1 and 2 with those of Groups 3 and 4. We can determine the effects of the second independent
variable by comparing Groups 1 and 3 with Groups 2 and 4. Such a design allows us to examine not only
the possible effects of two independent variables but also the possible interaction of the variables as they
influence the dependent variable.
Sample Output
Suggestions in
Acceptability of the Innovated Hand Tool Shadow Board Writing Research
Design
(A thesis presented by Gerald D. Plazo, MAT-Technology Education major in
Electrical Technology, 2020)
This study determined the acceptability of the Innovated Hand Tool Explain the
Shadow Board. This study employed a developmental-descriptive research research design
method. In this context, it is descriptive because this study aimed to determine which you have
the acceptability of the innovated product through these variables: functionality, chosen
usability, mobility and safety using a survey questionnaire. This paper utilized the particularly on
developmental research method because it involved procedures and steps such as its
planning, design, construction, testing and revisions to develop an innovated appropriateness
hand tool shadow board. Moreover, it also includes the problems met during the and how it
construction of the innovated product. Purposive sampling method was used for applies to your
more credible responses. Likewise, survey questionnaire was administered to a study.
total of 59 respondents. Furthermore, the statistical tools used are frequency
count, percentage, ranking and weighted mean.
C. Let Us Practice
Your Turn! Write down the Research Design section of your research paper using the example
given as your guide.
Research Design
_______________________________________________________________________________________________
_______________________________________________________________________________________________________
D. References
Creswell, J. 2012. Educational Research: planning, conducting, and evaluating quantitative and
qualitative research. USA: Pearson.
Leedy, P., and Ormrod, JE. 2021. Practical Research: planning and design. United Kingdom: Pearson
Education Limited.
Sevilla, C.G., et al. 1992. Research Methods. Manila: Rex Bookstore.