Professional Documents
Culture Documents
Research Lesson 4 5 and 6
Research Lesson 4 5 and 6
Learning Objectives
Research Frameworks
Since one can never be sure whether a given theory provides the best explanation
for a set of observations, it is possible to use two or more competing theories and test
which theory best explains the problem. A competing theory may also be used to
explain the possible confounding in influence of other variables on the assumed
relationship between the major variables of the study.
Comment: A religious man who committed adultery may justify his action with “an
experience of a moment of weakness,” or by explaining that “being human, he can
succumb to temptation.”
Attribution Theory. Heider (1980) theorizes that “people tend to attribute someone’s
behavior either to internal causes (person’s disposition or feelings), or external causes
(a person’s situation or environment).”
Comment: A teacher may attribute a student’s poor performance in class for his lack
interest in the subject (a “dispositional attribution”) or to some social or economic
circumstances, like financial difficulties, malnutrition or family problems (a situational
attribution).
Self-Perception Theory. (Bem, 1972, in Myers, 1983). “When one is unsure of his/her
attitude, he/she infers it back by looking at a behavior and the circumstances under
which it occurs. When a person’s attitude is weak, he/she simply observes his/her
behavior and its circumstances and simply infers what his/her attitude will be.”
Comment: The theory suggests that man’s attitude is influenced by his actions. A child
abuser may tend to have an indifferent attitude towards children.
Social Loafing Theory. Myers (1986), explains that “people tend to exert less effort
when they pull their efforts towards a common goal than when they are individually
accountable.”
Comment: Contrary to the notion that “many hands make light work, “experiments have
shown that a group of people may be less motivated when performing additive tasks
(Steiner, 1972).
Theoretical Framework
A theoretical framework a theory that explains why a problem under study exists
(Mercado, 1994), and explains the connection between certain factors and the problem.
The choice of a theory depends on the number and nature of the variables and the
relationships being examined.
Conceptual Framework
Based on the theory used and/or related literature, the predicted association
between variables or the assumed effect of one variable (independent variable) on
another variable (dependent variable) is explained. Arguments on how and why a
particular factor can possibly influence another are presented. Findings of related
studies may be used to support argument.
Example No. 1
Research Title: “The Effect of Curfew on the Attitude of Students Towards their Studies
and Their Academic Performance”
Many parents or guardians prevent their children from staying out late at night by
imposing curfew, so that they can study and perform well in school. But, many students,
still perform badly in school, even if they are forced to be home early. Is curfew an
effective means of improving students’ attitudes towards their studies and
consequently their school performance? Does curfew adversely affect students’ school
performance?
“People value their sense of freedom and like to protect an image of efficacy
(Baer, et.al., 1980). When social pressure threatens their sense of freedom, they tend to
rebel.” According to the theory of psychological reactance, people act to defend their
freedom. Experiments have shown that attempts to restrict a person’s freedom often
results in a reactive “boomerang effect. Restricting someone’s movement is also
reducing or taking away one’s freedom. Most people use restrictions as a preventive
measure. For some it may work, for others, it may not. It may produce good result for
others, for some it may do more harm than good.
Conceptual Framework
Example No. 2
Objectives:
Conceptual Framework
_____________________________________________________________________
5. In my study, __________________________________________________________ is
assumed to be associated with or affected by ______________________________
_____________________________________________________________________
____________________________________________________________________________
______________________________________________________________
LESSON 5
Learning Objectives
At the end of the lesson, students will be able to:
1. define what a variable is and explain its uses in research,
2. describe and compare the different types of variables and give examples of each,
and
3. identify the variables in a given study and determine the nature of relationship
between them.
What is a Variable?
A variable is a concept that stands for a variation within a class of objects or
persons (Fraenkel and Wallen, 1996).
A variable is a characteristic or property that can take different values or
attributes (Schutt, 1999).
Variables are the basic elements which are measured in a study. They are
observable and measurable.
Examples of Variables:
` • age • location of business • degree of malnutrition
• sex • revenue •level of fertilizer
Types of Variables
Variables can be classified as: dependent, independent, intervening, and antecedent
variables
Dependent Variable
The dependent variable is the “assumed "effect" of another variable. It is the
change that occurs in the study population when one or more factors are changed or
when an intervention is introduced. Usually dependent variable is the problem itself.
Independent variable
The independent variable is the “assumed cause" of a problem. It is an assumed
reason for any "change" or variation in a dependent variable. An independent variable is
sometimes treated as "antecedent" variable (the variable before). Likewise, an
"antecedent" variable may be treated as an “independent” variable.
Example No. 1
In the study on “The Relationship Between Exposure to Mass Media and
Smoking Habits Among Young Adults,” the dependent variable is “smoking habits,”
while the independent variable is “exposure to mass media.” A person’s smoking habits
is assumed to change or vary depending on his/her mere exposure or degree of
exposure to print or broadcast media related to smoking.
Exposure to Smoking
Mass Habits
media
Example No. 2
In the experimental study to test the “Effect of Peer Counseling on the Students’
Study Habits,” the independent variable is “exposure to peer counseling.” It is assumed
that students who have been counseled by peers will have better study habits that those
who were not counseled by peers or those who have been exposed to traditional
counseling techniques.
Exposure to
Study Habits
Counseling
Example No. 3
In the study entitled “Factors that Influence of Extent of Participation in
Household Decision-making Among Married Professionals,” the dependent variable is
extent of participation in household decision- making,” while the independent variable is
“factors,” which include personal characteristics of the respondents, such as age, sex,
educational attainment and income.
Intervening Variable
The intervening variable is a factor that works "between" the independent and
dependent variables. It can weaken(decrease) or strengthen (increase) the effect of the
independent on the dependent variables. It is also called a "facilitating variable,"
"moderator" or a "control variable.”
Example No. 1
In the study on “Knowledge of the Dangers of Smoking, Attitudes towards Life,
and Smoking Habits of Young Professionals,” the intervening variable is “attitude
towards life.” A person’s attitude may increase or decrease the influence of “knowledge
on dangers of smoking (independent variable) on “smoking habits” (dependent variable).
Knowing the dangers of smoking, one may shun smoking. One may argue, however, that
knowledge about the dangers of smoking may not necessarily prevent a person from
smoking if he does not mind dying early as long as he/she enjoys life.
Knowledge of the Attitudes Smoking Habits
dangers of smoking towards life
Example No. 2
In the study on “Factors that Influence Household Decision-making Participation of
Married Professionals," the intervening variable “gender sensitivity’ may affect the
relationship between “selected factors” (independent variables) and “decision-making
participation” (dependent variable). Men are generally expected to participate in
decision-making more than women because of social prescription. Older, better
educated individuals and those with big income are also expected to participate more
actively in decision-making than their younger less educated counterparts. It may also
be possible that a woman with a gender sensitive partner may also be actively involved
in decision-making, despite poor education or low income.
Example No. 3
In the study on “The Effect of Information Education Campaign (IEC) on Land
Reform on the Farmer’s Attitude Towards Land Reform,” the “length of a farmer-landlord
relationship” is the intervening variable. It is assumed that this variable can strengthen
or weaken the relationship between “exposure to IEC materials” (independent variable)
and “attitudes towards land reform” (dependent variable). A farmer may have read or
heard about the benefits of land reform, but still reject it (negative attitude) because of
along and close relationship with his landlord and his family. which he does not want to
be “cut off” by land.
Antecedent Variable
An antecedent variable is a factor or characteristic which is found before (ante)
the independent variable. It is expected to influence the independent variable/s. It is
usually irreversible.
Example No. 1
In the study entitled "Attitudes Towards Land Reform and Acceptance of the
Program among Lowland Farmers of Northern Luzon,” the major concern of the study
is the influence of “attitude towards land reform” (independent variable) on the “farmers”
acceptance of the program” (dependent variable). The farmers’ attitude towards land
reform is expected to vary according to their “education, tenurial status and the size of
the land they own” (antecedent variables). More educated farmers who own their farm
lots and are tilling more than a hectare of land may be more receptive of land reform
than the less educated farmers and those who do not own any farm land or those who
own less than a hectare lot.
Education Attitudes Towards Acceptance of
Tenurial Status Land Reform Land Reform
Size of Land Owned Program
Example No. 2
In the study entitled "Extent of Exposure to Print Media and Reading Ability of
College Freshmen,” the main concern is the relationship between students’ “extent of
exposure to print media” (independent variable) and their “reading ability” (dependent
variable). The students’ exposure to print media, however, may depend on their sex,
residence and their parents’ education (antecedent variable).
Example No. 2
For a variable like “residence”, if its operational definition is “geographical
characteristics of the area where the respondents permanently reside,” the possible
answers may be categorized as “rural” and “urban.” The meaning of “rural” and “urban,”
however, may be different in other studies. The operational definition depends on how
the word is used and measured in the study. The categories may be defined as :
Rural - “refers to a place of residence which is located outside the geographical
jurisdiction of a city or a town center.
“Urban - refers to a place of residence which is located within the city proper or within
the town proper of a municipality.
Exhaustive Categories
Categories are exhaustive if all the possible responses are included among the
options of responses. The answers given by every respondent can be assigned to a
particular category. If a researcher is not sure about the exhaustiveness of the
categories identified, he/she should include “Others,” the “catch all” category. Under this
category, responses which can not be assigned to any of the other categories can be
classified.
Example
A list of categories like: “Protestant, Catholic, Muslim, and Budhist” for responses
to a question on religion is not exhaustive because a Mormon cannot be classified
under any of the categories in the list.
For instance, the variable “hobbies” is operationally defined as “a type of activity
a person engages in during leisure or free time.” The possible categories of this variable
may be: “singing,” “reading,” “painting,” “writing poems,” “sewing,” “Others, specify.”
What may not be classified under the five specific categories can be classified under
“Others.” However, if during data analysis, the number of responses falling under
“Others” exceed three, the responses must be specified and based on these an
additional category can be added.
LESSON 6
Threats to Validity
There are many threats to validity. The most common of them are history,
selection, testing, instrumentation, maturation, and mortality.
History. Sometimes there are events in the life of a research project, but which
are not part of the project, that can increase or decrease the expected project outcomes.
These events are not expected, they just happen and they produce effects that can
invalidate study results.
For example, in a study of the “Effect of Anti-Smoking Campaign on Cigarette
Consumption Among Young Adults in Cadiz City,” an intensive information campaign
against smoking was launched in order to discourage smoking among young adults.
Anti-smoking messages were disseminated on radio, television, and newspapers daily
for one month. In the course of the campaign, a cigarette company also launched a
product promotion, offering a free trip to Europe for the customer and dealer who could
collect and submit the most number of empty packs of the cigarette brand being
promoted. A month after the launching of the anti-smoking campaign, an evaluation
was conducted, and the results showed an increase in cigarette consumption in the
study area. The researcher might conclude that the campaign was a failure. The
conclusion here would be invalid because of the high possibility that the cigarette
promotion (the historical event) may have contributed to the increase in cigarette
consumption.
Selection. In an experimental study, a threat to validity occurs when the elements
or subjects selected for the experimental group is very different from those selected for
the control group. For instance, if at the beginning the experiment, the experimental
group already has an advantage over the control group in terms of the focus variables
of the study, this difference will definitely affect the results of the study.
For example, in an experiment conducted to determine if using games and
puzzles as instructional aids can improve performance of college freshmen in Basic
Math, the teacher used games and puzzles in the experimental group, but did not use
them in the control group. After the experiment, it was found that the experimental
group got significantly better grades in the subject than the control group. It was
discovered, however, that most of the students in the experimental group had very good
grades in high school math, while most of those in the control group had average
grades only. Attributing the better performance of the experimental group to the use of
games and puzzles can be questioned. To avoid this validity threat, the experimental
and the control group should have similar characteristics at the beginning.
Testing. Whenever a pretest is given, it may make the examinees “test wise,” and
this can therefore affect the posttest results. Research subjects who have been given a
pretest may remember some of the test items/questions for which they may search
answers and get these correct when they take the posttest. Better performance in the
posttest might be due to the effect of the pretest and not necessarily to the intervention
or treatment.
Instrumentation. When a research instrument, such as a questionnaire or a
measuring device, like a weighing scale or a thermometer is changed during the study
period or between the pretest and the posttest, the change could result in an effect that
is independent of the intervention and yet, may be attributed to it.
For example, in a survey study, an instrumentation effect may be caused by an
interviewer who after conducting the pretest interview becomes more experienced in
interviewing. The interviewer’s experience will enable him/her to generate better and/or
more complete information during the post test than what was collected during the
pretest.
In a biomedical study, the use of an unreliable device, like a scale that badly
needs calibration, a contaminated syringe, or a very old litmus paper may also threaten
the validity of test results.
Maturation. People and things change over time. In other words they become
more mature, and this change can threaten the validity of conclusions. Research
subjects can get tired, hungry, or bored during the duration of the project. If the effect of
a project is measured with a test, their tiredness or boredom can result in scores lower
than their “true” scores..
On the other hand, the subjects may become more experienced, more
knowledgeable as they grow older and as a result they may get higher scores than they
did in the pretest. In this regard the change can not be attributed to the intervention.
Mortality. In studies that take a long time to finish, say, one year or more, like
cohort studies, where the subjects (the same people) are followed up over time, some
cases may drop out, thus resulting in a loss of cases. Some cases may have transferred
residence and are difficult to locate during the follow-up interview. Cases which cannot
be contacted cannot be followed-up. This loss, called mortality, may distort findings and
conclusions, if substantial and if it has introduced a bias to the sample.
The loss could result in a big difference between the pretest and the post test
results. This change may be wrongly attributed to the intervention, thus, threaten the
validity of the conclusions.
Commonly Used Research Designs (Campbell and Stanley, 1968, Parel, et al., 1985,
Fisher, et al., 1994)
The choice of a research design depends on the objectives of the study. There
are many types of research designs that can be used in basic and experimental
research. Described here are some of the most frequently used designs. They are
classified into: non- or pre-experimental designs, true experimental designs, and quasi-
experimental designs.
Non/Pre-Experimental Designs
Non-experimental designs are appropriate for collecting descriptive information
about a population or subjects of a study. They are appropriate for descriptive studies,
like profile studies, exploratory studies, and for doing small case studies. They are also
ideal for diagnostic studies or situation ) analysis. They are not recommended for
evaluation studies intended to 7 determine the effect or impact of a certain intervention
or treatment. Three non-experimental designs are described below. They are the
posttest only or after only design, the pretest-posttest design, and the static group
comparison.
Posttest Only Design or After- Only Survey
Time
X O
(Observation/Testing/Survey)
The design is also called as one shot survey because the data are collected only
once (O). This design is used when the study objective is to describe a
situation/condition of a study population as it exists, or to | determine/describe the
characteristics of a population/ respondents. There is no baseline data.
This design is cheap and easy to conduct, but results cannot be conclusive in
terms of causality or effect of an intervention. It is not, { however, recommended for
evaluation studies that intend to measure the Ys effect of a program intervention, like
training.
Pretest-Posttest Design or Before-After Survey
X (Intervention)
1 2
O O
Observation/Survey 1 Observation/Survey 2
(Before X) (After X)
This design is used when the study wants to know the change in characteristics
(e.g. knowledge, attitude, practices) of the study population (students, nurses,
managers, clients, etc) in a given area. A survey, observation, or testing is conducted
before an intervention is introduced (O’). After a period of time the survey, observation
or testing is repeated (O°) and the results of the pretest (before) and the posttest (after)
are compared to determine change/s.
For example, if a researcher wants to know if an information campaign against
drug/substance abuse in a certain city has reduced drug use in the area after the
campaign, a survey before and after the campaign can-be conducted. No "control" area
(area where no campaign is conducted), however, is surveyed. With the absence of a
control area, this design cannot be considered an ‘experimental design. Any reduction in
drug use overtime, cannot be solely/conclusively attributed to the intervention
(campaign).
In the static group design, there are two groups involved, an experimental group
and a control group. The experimental group receives or is exposed to the
intervention/treatment (X). This is followed by a measurement (O' ), the result of which
is compared to the result of — the measurement/observation from a control group (O”
that did not receive the intervention. The random process, however, was not used in the
assignment of subjects to the experimental and control groups (indicated by a broken
line). The problem with this design is the validity threat of selection and mortality. It is
possible that the two groups differ greatly on the basis of the main variables of the
study (selection) or some subjects in the experimental group may drop out and be lost
to follow-up or second observation/testing (mortality).
True Experimental Designs
In true experimental designs, subjects are randomly assigned to the experimental
group and the control group to achieve pre-intervention/ treatment equality of the two
groups. With well-defined and properly selected experimental and control groups,
validity threats are avoided. Before a researcher decides on an alternative design, the
feasibility of using true experimental designs must first be considered. The two most
frequently used true experimental designs are the pretest-posttest control group design
and the posttest control group design.
1 3
Experimental group O X O
RA
2 4
Control group O O
Pretest Posttest
In the pretest-posttest control group design, the experimental group is exposed
to or covered by an intervention or treatment (X), for example, training or a new strategy,
while the control group is left alone or given another kind of treatment. Before the
intervention/treatment is introduced to the experimental group, a
survey/observation/testing is conducted for both experimental group (O') and control
group (O°) using the same device/ instrument. The pre-intervention
survey/observation/test serves as pretest and the data collected serve as baseline data.
After the introduction of the intervention in the experimental group or area, an_
evaluation survey/observation/testing is conducted in both experimental group/area (0°)
and the control group/area (O*), using the same instrument used in both during the
pretest. The results serve as the posttest/endline data.
The baseline (pretest) and endline (posttest) data are compared. If the change in
the "impact/effect indicator/s” or dependent variable/s is significantly better in the
experimental area/group than the change in the control area/group, then the
intervention is considered effective. If not, then the intervention is said to have had no
effect.
1
Experimental group X O
RA
2
Control group O
Posttest
The Posttest Only Control Group design is also used to determine the effects of
an intervention or treatment introduced to a group of subjects (people/objects). As in
the pretest-posttest control group design, at least two groups or areas (e.g. women
groups, communities, provinces) with virtually the same characteristics are chosen and
randomly assigned (RA) to the control and experimental group.
The experimental group or area is exposed to or covered by an
intervention/treatment, while the control group is left alone. No pretest/pre- intervention
study is conducted. The experimental and the control groups are assumed to have
similar characteristics at the start of the study. After the introduction of an intervention
in the experimental group or area, an evaluation survey/observation/testing is
conducted in both experimental and the control groups or areas, using the same “fair”
instrument.
The data gathered from the experimental and control groups are compared. If the
experimental group or area shows significantly better results than the control
area/group with respect to the "impact/effect indicator/s” or dependent variable/s, the
intervention or treatment is considered effective. If not, then, the intervention is not
effective.
Quasi-experimental Designs
In field studies, it is very difficult to meet the random assignment criterion of a
true experimental design. In this situation, a quasi-experimental design is recommended.
Quasi-experimental designs are nearly the same as the true experimental designs,
except that the former do not have restrictions of random assignment. The two most
commonly used quasi-experimental designs are the non-equivalent control group
design and the time series design.