Professional Documents
Culture Documents
Research is
- A study/investigation
- A scientific investigation
- Is a study on investigation which is done systematically, empirically, scientifically, and logically for the purpose
of achieving knowledge and helping solve situational problems.
- Empirical – measurable and observable things or phenomenon that you can put in print on the bases of your
senses.
Purpose of Research
2. It must be a loaded statement that would drive an impact to emote interest from the reader.
This introductory page acquaints the reader with the problem to be dealt with. This orientation is best
accomplished by providing rationale or background.
The background intends to draw a clearer picture of what you want to say. It describes clearly, colorfully and
vividly the problem situation which serves as the rationale of the study.
It presents in details the problem situation based on what you
The purpose of the background is to highlight the need for the study by presenting what is happening at
present and what ought to be using the data that the researcher has gathered.
It identifies the area in which the problem is to be found, and points out that the problem had not been fully
studied.
2. Conceptual Framework
This deals with the key concepts and related literature underlying the framework that guides the study. The purpose
of this is:
The initial step is to identify the key variables of the study. This refers to the independent, dependent and moderator
variables to be investigated.
The second step is to look for the definitions of the variables. For the dependent variables the following should be
done:
1. Define the variable (universal definition)
3. Discuss its importance (how it affects other variables) and how it is affected by other variables (independent
variables)
For the independent variable, define and describe its characteristics and indicators. Discuss its effect on the
dependent variable on the basis of the review of related literature and studies. The same should be done for
the moderator variables.
The discussion should point out how the previous studies relate to the present investigation by highlighting
their similarities and differences. More importantly, it must include some relevant theories and concepts that
help in the development of the present study.
Organizing the literature review section by subheadings makes it easier for the researcher to follow. To be
meaningful, this subheadings should reflect the variables and their relationship.
We should remember that the purpose of literature review is to provide a basis for the formulation of
hypothesis.
The conceptual framework is summarized or synthesized into a logical network of relationship of the key
concepts or variables involved in the study. This is further simplified by presenting a research paradigm or
hypothetical illustration of the relationship of variables and their corresponding indicators.
3. Research Hypothesis (for quantitative research)
Hypothesis – is a conjectural statement of the relation between two or more variables. It is a tentative or
temporary answer to a research problem.
3. It should be testable; that is it should be possible to restate it in an operational form which can be evaluated
based on data.
Example:
1. It provides the reader with an immediate basis from which to interpret subsequent statements
2. It makes it possible to quickly determine the purpose of the study. The reader will not have to search for the
introduction and background to discover the problem being examined.
One or two sentences will normally suffice to state the problem. Often the statement begins as follows:
The purpose of this study is to examine the relationship between…….(state the variables, locale and time as the case
maybe).
5. Definition of Terms
The definition is based on the observable characteristics of that which is being defined.
What is important is the nature of these observations upon which definitions are based.
There are 3 approaches or types of constructing definitions. These are arbitrarily labelled as A, B, and C by Bruce W.
Tuckman.
A type A definition can be constructed in terms of the operations that must be performed to cause the phenomenon or
state being defined to occur.
An intelligent child can be defined operationally as the child produced by the marriage of above average, intelligent
couples.
A type B definition can be constructed in terms of how the particular object or thing defined operates, that is what it
does or what constitute its dynamic properties.
Thus an intelligent student can be operationally defined as a person who gets high grades in school or a person who
demonstrates capability for solving complicated mathematical problems.
A type C definition can be constructed in terms of what the object or phenomenon being defined looks like that is
what constitutes its static properties. Thus, an intelligent student can be defined for instance as a person who has a
good memory, large vocabulary, good reasoning ability, good mathematical skills, etc.
Ideally, the operational definition should contain three parts. The first part is its universal meaning. The second part is
how it is being used in the study. The third is how it is being measured.
It is at this point that the researcher described who will benefit and what benefits can be derived from the findings of
the study. The writer, under this section, tries to sell its importance to the panel or to the funding agency.
This tells the specific boundaries of the study by describing the place or venue of the study, the population,
subjects/respondents, time frame, the variables and their indicators.
Any weakness of the study such as failure to use a more precise data gathering or measuring instrument or
failure to execute an important procedure due to certain circumstances beyond the researcher’s control form part of
the study’s limitations.
Learner’s Output:
List of Related Literature
LITERATURE REVIEW
A literature review is a critical and in depth evaluation of previous research. It is a summary and synopsis of a
particular area of research, allowing anybody reading the paper to establish why you are pursuing this particular
research project.
Search through databases that have indexed information on thousands of research articles that have been conducted
Do not limit your search to only studies that examine all of the same variables as your study.
When searching online, use the limit function to reduce searches that have too many results.
Do not cite wikipedia as a source. Like Google, anybody can edit articles on wikipedia. Therefore, wikipedia
should never be used as a source for an academic paper.
Boolean logic is the way to put terms together in a search by using AND, OR, NOT
Using AND
When you use AND you will be looking for articles containing two or more words within each article.
For example, employee AND motivation would retrieve articles with both words in the article.
Use AND when you are searching for concepts and want to be more specific in your search (to narrow it down).
Using OR
When you use OR you will be looking for articles containing either one word or the other word.
For Example, employee OR personnel OR staff. You would use OR for similar concepts and alternative words or
synonyms (to broaden out your search).
Using NOT
When you use NOT you will be looking for one term but not the other.
For example, you might search for broadband NOT wireless. You would use NOT to exclude irrelevant results (to
narrow down your search).
Stating what has been said about the variable (relationship, effect, difference) or it historical development
Build arguments either through sentence of problematising (SOP) or the need for the study (NFS)
The conceptual framework underlying this study is anchored on the concepts of research capability, workload, and
research productivity.
Research Capability
Research capability is simply the capability of the faculty to undertake research. All the resources or inputs which
enable the faculty member to conduct research are considered as components of research capability (Deza, 1999;
Banaag, 1994). Salazar-Clemena and Almonte-Acosta (2007) enumerated indicators of research capability which
include budget for research, the ability to obtain research grants, the provision of research infrastructure, the ability to
collaborate with and access to research professionals, and the presence of rules and procedure on the granting of
rewards for research.
Previous foreign and local studies have revealed that the reasons for low research productivity among faculty
members are poor or lack of research skills (Anunobi & Emerole, 2008; Iqbal, 2011); lack of research funds (Anunobi
& Emerole, 2008; Iqbal, 2011; Mahilum, 2010); and heavy workload or teaching overload (Iqbal, 2011; Mahilum, 2010;
Mordeno, 2002). Iqbal (2011) added performance of administrative duties along with academic duties, nonexistence of
research leave, negative attitude of the faculty towards research and absence of professional journals while Anunobi
& Emerole (2008) included time constraints as impediments to research publication.
Predictors of research productivity include teachers training or having research orientation (Finkelstein, 1984, Banaag,
1994, Mordeno, 2002); academic rank (Flanigan, et al.,1988; Banaag, 1994); highest educational attainment
(Finkelstein, 1984; Flanigan, et al.,1988; Banaag, 1994);and sufficient time allocated to research (Finkelstein, 1984).
While several studies have been made to investigate correlates of research productivity, studies on research
capability in terms of specific research skills of teachers were lacking. In this end, the researchers were motivated to
conduct this research that explored the levels of proficiency of teachers on different skills that determine their
capability in doing research and how this capability can be associated to research productivity. Workload in terms of
hours of work and number of teaching preparations was also investigated to verify its impact on faculty productivity in
research. In the end, it is aimed that this research may contribute to the existing literatures on determinants of
research productivity.
Remember!
Read enough background material to discuss the research and the theory giving a reasonably complete account of
our knowledge of the topic
Present data that are based on data and theory, including conflicting views of different researchers.
Make it easy for the reader to understand how all of the studies interrelate.
Presenting a Statistics
“Authors do not present the work of another as if it were their own work”.
Whether paraphrasing, quoting an author directly, or describing an idea that influenced your work, you must credit the
source. To avoid charges of plagiarism, take careful notes as you research to keep track of your sources and cite
those sources according to the guidelines.
References
Beins, B.C. APA simplified style: Writing in psychology, nursing, education, and sociology. USA: John Wiley & Sons,
Inc.
explorable.com/what-is-a-literature-review
1. Research Design
A research design is a plan or strategy in order to answer the research problem and control (variance) for
validity. This is the over-all plan for the conduct of the investigation.
Hence, substantially a design is intended to answer the problem; and, technically it provides control for
validity.
1. Research Design
Essentially, research designs may be classified only in two (2) categories on the basis of maximum control for
validity:
1. Research Design
EXPERIMENTAL RESEARCH
B. Quasi-experimental design
1. Research Design
EXPERIMENTAL RESEARCH
A. Pre-experimental design (non-design)
B. Quasi-experimental design
-this design controls some but not all sources of internal invalidity due to existing conditions by which experimental
control is difficult if not impossible.
1. Research Design
EXPERIMENTAL RESEARCH
B. Quasi-experimental design
1. Expost facto design – This is the study in which the researcher examine the effects of naturalistically occurring
treatment after that treatment has occurred rather than creating the treatment itself. The researcher attempts
to rotate this after the fact.
2. Co-relational standard
1. Research Design
EXPERIMENTAL RESEARCH
B. Quasi-experimental design
2. Co-relational standard – this involves two or more sets of data from a group of subjects with an attempt to
determine the subsequent relation between those sets of data.
1. Research Design
EXPERIMENTAL RESEARCH
B. Quasi-experimental design
2. Co-relational standard – serve as useful purpose in determining the relationship among measures and
suggesting possible bases for causality, while correlation does not necessarily imply causation.
1. Research Design
EXPERIMENTAL RESEARCH
B. Quasi-experimental design
C. True Experimental Design – provide complete adequate controls for all sources of internal invalidity (only possible
for non-human subjects
Experimental Research
Used to establish cause and effect by manipulating (influencing) an IV (independent variable, aka treatment or
experimental variable) to see its effect on a DV (dependent variable ,aka criterion or outcome variable)
Experimental Research
Comparison of groups (at least two groups of subjects, called treatment and control groups)
Manipulation of the IV (experimenter changes something for the treatment group that’s different than the control
group)
Randomization (true experiments require random assignment into treatment/control conditions…after random
selection of subjects to participate in study)
Experimental Research
Experimental Research
Hold certain variables constant (i.e. age, IQ) or build them into to the design
Experimental Research
Use subjects as their own controls (treat same group first in control condition then in treatment OR use pre-
test/posttest on same group)
Experimental Research
(Group Designs)
Pre-Experimental Designs
Do not adequately control for the problems associated with loss of external or internal validity
One-Shot Design
One-Shot Design
Diagrammed as: X O1
Subjects in the experimental group are measured before and after the treatment is administered.
No control group
Offers comparison of the same individuals before and after the treatment (e.g., training)
If time between 1st & 2nd measurements is extended, may suffer maturation
Diagrammed as O1 X O2
Control group is measured without having been exposed to the experimental treatment
No pre-measure is taken
Major weakness is lack of assurance that the groups were equal on variables of interest prior to the treatment
Control Group O2
Control group tested at same two times without exposure to experimental treatment
Diagrammed as
Experimental Group: O1 X O2
Control Group: O3 O4
Diagrammed as
Experimental Group: X O1
Control Group: O2
(O2 – O1)
Example
Combines pretest-posttest with control group design and the posttest-only with control group design
Provides means for controlling the interactive testing effect and other sources of extraneous variation
Diagrammed as
Experimental Group 1: O1 X O2
Control Group 1: O3 O4
Experimental Group 2: X O5
Control Group 2: O6
Quasi-Experimental Designs
Includes
Involves periodic measurements on the dependent variable for a group of test units
After the treatment, periodic measurements are continued in order to determine the treatment effect
Diagrammed as:
O1 O2 O3 O4 X O5 O6 O7 O8
The intentional or unintentional influence that an experimenter (researcher) may exert on a study
Correlation Research
(Predicting Outcomes Through Association)
Descriptive in nature
Often a precursor to experimental research
Correlation Research
(Predicting Outcomes Through Association)
For causation: 1) A before B; 2) A and B related; 3) Rule out other causes of B (need experiment)
Prediction studies identify predictors of criterions (i.e. HS GPA and College GPA)
Correlation Research
(Predicting Outcomes Through Association)
Complex Correlation Techniques, such as multiple regression allow use of several predictors for one criterion
Coefficient of multiple correlation (R) gives strength of correlation between predictors and criterion
Descriminant function analysis is for non-quantitative criterion (predict which group someone will be in)
Other techniques also used (factor analysis, path analysis, structural modeling)
Correlation Research
(Predicting Outcomes Through Association)
Problem selection – usually it’s are x and y related or how well does p predict c
Data analysis – correlation coefficient, r, and plot (r is -1 to +1, and the closer to plus or minus 1, the stronger the
relationship)
Correlation Research
General guidelines:
Need .5 or better for prediction of any use, and .65 for accurate predictions
Correlation Research
Subject characteristics – may get different correl w/ different ability levels, gender, etc. (can control with partial
correlation)
Instrumentation problems – helps to standardize instrument and data collection for both groups
Correlation Research
Does any factor affect BOTH variables? (this is where threats occur)
Determines cause (or effect) that has occurred and looks for effect (or cause) from it
Need to remember the cause may be the effect; they may only be related and there is some other variable that is the
cause (lurker)
Causal Comparative works with different groups; correlation examines one group on different variables
Sample – define (operationally) characteristics of study carefully, then select individuals who possess
Groups should be homogeneous in regard to several important variables (to control for them as causes) then match
control/experimental groups on one or more variables
Design – basic CC involves 2 or more groups that differ on variable of interest (basic design is one group possesses
trait (athlete) other doesn’t compare DV (GPA)
Subject characteristics – since don’t select subjects and form groups, there may be unidentified lurking variables
Can use matching to control for any identified differences, but limits samples size
Can find or create homogeneous groups (for example compare only high GPA students to other high GPA students)
on attitudes toward x
Other threats – location, instrument, history, maturation, loss of subjects can be concerns
Survey Research
(Used to describe what people think/do/believe)
Types
Longitudinal collect data at different points in time to study changes over time
Cohort study - sample from same cohort members year after year
Panel study - same individuals surveyed year after year (mortality a problem over long time periods)
Often surveys are the data collection instrument in correlation (or cc/exp’l) studies
Survey Research
(Steps to conduct survey research)
Direct administration to a group (such as at a meeting) - good response rate, limited generalize.
Mail survey (inexpensive way to get large amount of data from widespread pop) - lower response rates, not in-
depth info, illiterate missed
Telephone survey (cheap/fast) - response rates higher due to encouragement (“I’m not selling…”); miss some
pop members, interviewer bias possible
Personal interviews (face-to-face has good response rate but time and cost high) - lack anonymity, interviewer
bias
Survey Research
(Steps to conduct survey research)
Select the sample (randomly, but check to see respondents are qualified to answer)
Pilot test can indicate likely response rate and problems with data collection or sample
Survey Research
(Steps to conduct survey research)
Population
This describes the population of the study and the method of getting the representative sample (of the population).
The total population of interest and the number of the sample subjects of the study are given and embodied in a table.
Population must be defined first; more closely defined, easier to do, but less generalizable
Study a subset of the population because it is cheaper, faster, easier, and if done right, get same results as a census
(study of whole population)
Accessible population – the group you are able to realistically generalize to…may differ from target population
Sampling Method
Random – every population element has an equal and independent chance to participate
Uses names in a hat or table or random numbers
Elimination of bias in selecting the sample is most important (meaning the researcher does not influence who
gets selected)
Any difference between population and sample is random and small (called random sampling error)
Multistage sampling
Multistage sampling
Considered random is list if randomly ordered or nonrandom if systematic w/ random starting point
Convenience Sampling
Purposive Sampling
Using personal judgment to select sample that should be representative (i.e., this faculty seems to represent all
teachers) OR selecting those who are known to have needed info (interested in talking only to those in power)
Sampling
Sampling
Ecological generalization (generalizable to other settings/conditions, such as using a method tested in math for
English class)
Instrumentation
(Measurement)
Demographic data are characteristics of subjects such as age, gender, education level, etc.
Assessment data are scores on tests, observations, etc. (the device used to measure these is called the
measurement instrument)
Instrumentation
Instrumentation
• Usability of instruments
Consider ease of administration; time to administer; clarity of directions; ease of scoring; cost; reliability/validity data
availability
Instrumentation
(Classifying Data Collection Instruments)
Subject instruments (subjects record data about themselves, such as taking test)
Others/Informants (3rd party reports about subjects such as teacher rates students)
Instrumentation
(Classifying Data Collection Instruments)
• By response type
Written response – preferred – objective tests, rating checklist
Rating scales (mark a place on a continuum for example numeric rating 1=poor to 5= excellent)
Interview schedules (complete scales as interview takes place; use precoding; beware of dishonesty)
Instrumentation
• Item Formats
Unobtrusive measures (no intrusion into event… usually direct observation and recording)
Instrumentation
• Types of Scores
Derived scores (raw scores translated to meaningful usage with standardized process)
Age/Grade equivalence; Percentile ranks; Standard scores (how far a score is from a given reference point, i.e. z and
T scores);
Instrumentation
• Norm referenced scores give a score relative to a reference group (the norm group)
These are used to improve instruction since they indicate what students can or cannot do or do or do not know
Instrumentation
(Measurement Scales)
Numbers are only name tags, they have no mathematical value (gender: 1=male and 2= female OR race: 1= Blk,
2=Wht, 3=other)
• Ordinal (in name, plus relative order)
Numbers show relative position, but not quantity (grade level, finishing place in a race)
Instrumentation
(Measurement Scales)
Numbers show quantity in equal intervals, but an arbitrary zero (can have negative numbers; degrees C or F)
Numbers show quantity with base of zero where zero means the construct is absent
• Higher levels more precise…collect data at highest level possible; some statistics only work with higher level
data
Instrumentation
(Preparing for Data Analysis)
• Scoring data – use exact same format for each test and describe scoring method in text
• Tabulating and Coding – carefully transfer data from source documents to computer
Measurement Instruments
Types of instruments
Cognitive – measuring intellectual processes such as thinking, memorizing, problem solving, analyzing, or reasoning
Aptitude – measuring general mental ability, usually for predicting future performance
Measurement Instruments
Interests – inclinations to seek out or participate in particular activities, objects, ideas, etc.
Measurement Instruments
Affective (continued)
Positive or negative statements to which subjects respond on scales such as strongly disagree, disagree, neutral,
agree, or strongly agree
Semantic differential
Bipolar adjectives (i.e., two opposite adjectives) with a scale between each adjective
Rating scales – rankings based on how a subject would rate the trait of interest
Measurement Instruments
Affective (continued)
Thurstone – statements related to the trait of interest to which subjects agree or disagree
Measurement Instruments
Bias – distortions of a respondent’s performance or responses based on ethnicity, race, gender, language, etc.
Accuracy of responses
Response sets
Quantitative Analysis
Descriptive Statistics
For descriptive problems that require finding out “what is,” as the term implies, descriptive statistical analysis can be
used to describe the data. The mean, median, mode and standard deviation are the main descriptive statistical
treatment applicable. The mean or median is used to indicate the average while the standard deviation provides the
variability of the data/scores in the sample.
Sample Frequencies
Illustration:
Characteristic Profile
A. Gender
Sample Interpretation
as to gender, the respondents were mostly female (since the modal class is female).
Illustration 2.
Age
F %
30-32 5 6.25
27-29 43 53.75
24-26 29 36.25
21-23 3 3.75
Total 80 100
Interpretation
Results on the table show that most of the respondents were within the age range of 27-39 (43 or 53.75%). However
it could be seen that the combined ranges from 24-26 to 27-39 composed almost 90% of the respondents.
From this, it could be said that most of the respondents were young adults.
Illustration
Sufficiency of Problem
Sufficiency of questions to
The concepts in the CTL were presented in real situations that are familiar to the students (X=4.6). This is the basic
principle strictly adhered to in a contextual teaching approach, thus, if the materials fail in this aspect, there is no
contextual approach. Since the experts judged the criterion as excellent, it only means that the CTL materials were
successful in translating the concepts to true-to-life experiences.
Inferential Statistics
Correlation Techniques
Bivariate Analysis
Kendall Tau
Comparison of Groups
Comparison of Pre & Posttest) T-test of Difference Between Means of Correlated Data
Positive correlation:
X Y
X Y
Negative correlation:
X Y
X Y
Illustration
Related
It is necessary to explore the statistical significance by using the critical value, however, it is much better to determine
whether the computed Pearson's r denotes a high correlation between the variable concerned because statistical
significance may only be negligible or too low to consider. Computer statistical outputs provide the probability of alpha
which may indicate the percent of occurrence of the error to reject the null hypothesis when it is true.
Sample Interpretation
As shown in the table, math achievement is significantly related to the result of the NEAT in mathematics (r=.77). This
means that the NEAT results in mathematics relate to the math achievement of the students in school. If a pupil
performs well in school mathematics, he is likely to get high in the NEAT.
Experimental grp. R O1 X O2
Control grp. R O3 O4
where: 01 and 03 are pretests
O2 = O4; The traditional and experimental approach have the same results.
T Stat continued
T Stat continued
SD 11.1 6.0
N 50 50
t – Value = 0.8972
(Probability of t = 0.4831)
Interpretation
The computed t-value for the difference between the pretest scores of the control and experimental groups shows no
significant difference since the probability of error (.4831) is more than the target level (.05).
The two groups are equally prepared for the experimentation as indicated by the very close means of the control (7.6)
and experimental groups(7.4).
Total 11 0.2411
The ANOVA table shows that the computed F is significant at 0.04 level. The difference was significant among the
groups concerned. At 0.05 level, the null hypothesis, which states that no difference exists among the groups, was
rejected. It means that the three groups of broilers were significantly different in terms of feed conversion.
(It is necessary to show the basis of the difference, thus, the researcher must present next the means of the three
groups.
Groups Mean
Group A 18.5
Group B 15.2
Group C 15.4
The difference was explicit on the weight of the broilers. The broilers mixed fed with corn were heavier than the rest.
The two groups, those mixed fed with grass and camote tops had almost similar mean weights. This shows that corn
mixed in feeds resulted to heavier chicken because of the high protein carbohydrate content of corn compared to
those mixed fed with plant products.
Two-Way ANOVA
Two-Way ANOVA
Mean1=Mean2=Mean3=…=Mean4
MeanB11=MeanB12=MeanB13…=MeanBij
Illustration 1
Is there an interaction between method of teaching and the ability of the students?
Solution
Use two-way ANOVA to compare between groups and determine interaction between variables.
Is there an interaction between This Method and the ability of the students?
Using and Interpreting the Two-Way ANOVA Results
Analyze mean performances and try to find out the highest and the lowest.
Observe that for those with high math ability group the highest mean was for the T2 group.
For the Average and Low Math ability groups, the highest means were also recorded for the T2 Group.
Among the three math ability groups, the highest recorded performance was for the average math ability group.
SV SS df X2 F F Prob
Total 377.90 35
To interpret the results, observe the probability of alpha (p-value). This will indicate whether the result is significant or
not. Since alpha is the probability of rejecting the Ho when it is true, its value must be less than the targeted alpha.
Thus, the table shows that the interaction is significant. This will be the basis for answering the problem. If it is not
significant, it follows that the researcher should examine the significance of the row or column differences between the
means.
Since the Interaction effect is significant, the researcher could pinpoint in the conclusion the observe differences. The
higher means could be used as basis for the conclusions.
Since the highest mean was observed for the average mathematics ability group, it could be said that the
constructivist method worked well with them.
T2 had the higher mean score compared to T4 which is also an experimental group. Compared to the control groups,
both experimental groups had high mean performances.
2. Conceptual Framework
This deals with the key concepts and related literature underlying the framework that guides the study. The purpose
of this is:
1. To expand the context and background of the study
Summary of Findings
Conclusions
Recommendations
List of References
APA Style