Beruflich Dokumente
Kultur Dokumente
Resty Samosa
LEARNING OUTCOMES :
At the end of this chapter, students should be able to
1. chooses appropriate quantitative research design
2. describes sampling procedure and the sample
3. constructs an instrument and establishes its validity and reliability
4. describes intervention (if applicable)
5. plans data collection procedure
6. plans data analysis using statistics and hypothesis testing (if appropriate)
7. presents written research methodology
8. implements design principles to produce creative artwork
Before proceeding, it is necessary to define the terms that will be used in this
chapter, and to differentiate them from one another.
A method is a technique which the researcher uses to gather and generate data about
the subjects of their study.
A methodology is the section of the research paper which explains why the researcher
chose to use particular methods. The methodology also includes descriptions of any and
all theoretical and / or ideological concepts informing and influencing the course of the
study, and the researcher‟s rationale behind adhering to these concepts.
A research design is a plan which structures a study to ensure that the data collected
and generated will contain the information needed to answer the initial inquiry as fully
and clearly as possible.
With this in mind, a common mistake made by researchers is that they begin their
investigations far too early, before they have thought critically about what information is
required to address the research problem. Without attending to these design issues beforehand,
the overall research problem will not be adequately addressed and any conclusions drawn will
run the risk of being weak and unconvincing. As a consequence, the overall validity of the study
will be undermined.
The length and complexity of describing research designs in your paper can vary
considerably, but any well-developed design will achieve the following:
1
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
1. Identify the research problem clearly and justify its selection, particularly in relation to any
valid alternative designs that could have been used,
2. Review and synthesize previously published literature associated with the research
problem,
3. Clearly and explicitly specify hypotheses [i.e., research questions] central to the problem,
4. Effectively describe the data which will be necessary for an adequate testing of the
hypotheses and explain how such data will be obtained, and
5. Describe the methods of analysis to be applied to the data in determining whether or
not the hypotheses are true or false.
Methods or research design may be classified from many points of view such as:
There are four basic types of quantitative research design, these are:
1. Descriptive research designs help provide answers to the questions of who, what, when,
where, and how associated with a particular research problem; a descriptive study cannot
conclusively ascertain answers to why. Descriptive research is used to obtain information
concerning the current status of the phenomena and to describe "what exists" with respect
to variables or conditions in a situation.
2
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
d) Descriptive studies can yield rich data that lead to important recommendations in
practice.
e) Approach collects a large amount of data for detailed analysis.
a) The results from a descriptive research cannot be used to discover a definitive answer or
to disprove a hypothesis.
b) Because descriptive designs often utilize observational methods [as opposed to
quantitative methods], the results cannot be replicated.
c) The descriptive function of research is heavily dependent on instrumentation for
measurement and observation.
a) Not all relationships are casual! The possibility always exists that, by sheer
coincidence, two unrelated events appear to be.
3
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
3. The essentials of action research design follow a characteristic cycle whereby initially an
exploratory stance is adopted, where an understanding of a problem is developed and
plans are made for some form of interventionary strategy. Then the intervention is carried out
(the "action" in Action Research) during which time, pertinent observations are collected in
various forms. The new interventional strategies are carried out, and this cyclic process
repeats, continuing until a sufficient understanding of (or a valid implementation solution for)
the problem is achieved. The protocol is iterative or cyclical in nature and is intended to
foster deeper understanding of a given situation, starting with conceptualizing and
particularizing the problem and moving through several interventions and evaluations.
a) This is a collaborative and adaptive research design that lends itself to use in work or
community situations.
b) Design focuses on pragmatic and solution-driven research outcomes rather than testing
theories.
c) When practitioners use action research, it has the potential to increase the amount they
learn consciously from their experience; the action research cycle can be regarded as a
learning cycle.
d) Action research studies often have direct and obvious relevance to improving practice
and advocating for change.
e) There are no hidden controls or preemption of direction by the researcher.
4. Experimental Research design - A blueprint of the procedure that enables the researcher to
maintain control over all factors that may affect the result of an experiment. In doing this, the
4
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
researcher attempts to determine or predict what may occur. Experimental research is often
used where there is time priority in a causal relationship (cause precedes effect), there is
consistency in a causal relationship (a cause will always lead to the same effect), and the
magnitude of the correlation is great. The classic experimental design specifies an
experimental group and a control group. The independent variable is administered to the
experimental group and not to the control group, and both groups are measured on the
same dependent variable. Subsequent experimental designs have used more groups and
more measurements over longer periods. True experiments must have control,
randomization, and manipulation.
a) Experimental research allows the researcher to control the situation. In so doing, it allows
researchers to answer the question, “What causes something to occur?”
b) Permits the researcher to identify cause and effect relationships between variables and
to distinguish placebo effects from treatment effects.
c) Experimental research designs support the ability to limit alternative explanations and to
infer direct causal relationships in the study.
d) Approach provides the highest level of evidence for single studies.
a) The design is artificial, and results may not generalize well to the real world.
b) The artificial settings of experiments may alter the behaviors or responses of participants.
c) Experimental designs can be costly if special equipment or facilities are needed.
d) Some research problems cannot be studied using an experiment because of ethical or
technical reasons.
e) Difficult to apply ethnographic and other qualitative methods to experimentally
designed studies.
The basic unit for a survey is the population of the area in which it is performed. It is not
usually possible to include the entire population so that people are selectively chosen to
participate in a survey.
Sampling is the process of choosing a representative part of the population under study.
“Typical” or representative of the population” means that a part of the population is chosen in
such a manner that the characteristics and variation are reflected. It is, therefore, not just taking
any part but rather that which is representative of the entire population (Sanchez, 1997).
The problem of sampling is one of the most important as well as one of the most difficult
problems in social and behavioral science researchers. Orth (1976), a senior research scientist,
point out that good sampling is an effective means of reducing the number of persons
contacted to get a relatively accurate picture of the sample population‟s attitude and opinion.
5
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
There are two groups of population: the target population and the accessible
population. The target population is composed of the entire group of people or objects to which
the researcher wishes to generalize the findings of the study, while the accessible population is a
portion of the population to which the researcher has reasonable access. For example, in a
study about common difficulties encountered by senior high school students in their first semester
of school year 2017-2018, the target population may be all senior high school students in metro
manila. However, the researcher may have access only to the students of a specific school -
these students comprise the accessible population.
Researchers commonly select samples for study rather than entire populations due to
constraints in budget, time, and manpower. A good sample should be representative of the
population, such that the characteristics of the population - especially those pertinent to th
study - are reflected in the sample with a fair amount of accuracy.
The individual participants in the study are often referred to as subject or respondents.
The subjects are individuals or entities which serve as the focus of the study. Respondents are
individuals or groups of people who actively serve as source of information during data
collection. The subjects of the study may also be its respondents, but there also times that these
are two groups of different individuals or entities. Subject and respondents may also be referred
to as elements - particularly if said elements are objects, rather than people.
Take for example a study focused on the behavior of the students who belong to broken
families. The students who belong to these families are the subjects of the study, which may also
be the respondents the researcher seeks to interview directly. If the researcher interviews or
surveys the classmates of these students, the students remain the subjects and the classmate
then become the respondents.
6
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
This figure is a statistic. Using this figure, she concludes that the mean age of Filipino men who
married in 2016 is likely to be close to 31, as well.
It is important for the researcher to us an acceptable sample size to ensure that their
study will be accurate. Generally the larger the sample, the, more reliable the result of the study
will be. Hence, it is advisable to have a sample large enough to yield reliable results, yet small
enough to be manageable within the constraints of the study.
Advantages of Sampling
1. It saves time, money, and effort. The researcher can save time, money, and effort
because the number of subjects involved is small. With only a small number subjects
to be collected, tabulated, presented, analyzed and interpreted, the use of sample
gives comprehensive information of the results of the study.
2. It is more effective. Sampling is more effective if every individual of the population
without bias has an equal chance of being included in the sample and data are
scientifically collected, analyzed, and interpreted.
3. It is faster, cheaper and economical. Since sample is only “drop in a bucket,” the
collection, tabulation, presentation, analysis and interpretation of data are rapid
and less expensive due to small number of subjects and few copies of the
questionnaires are used.
4. It is more accurate. Fewer errors are made due to small size of data involved n
collection, tabulation, presentation, analysis and interpretation.
5. It gives more comprehensive information. Since there is a thorough investigation of
the study due to small sample, the results give more comprehensive information
because all members of the population have an equal chance of being included in
the sample.
Disadvantage of Sampling
If sampling design has strength, it also has its weakness. The disadvantages of sampling
are as follows.
1. Sample data involve more care in preparing detailed subclassification due to small to
small number of subjects.
2. If the sampling plan is not correctly designed and followed, the results may be
misleading.
3. Sampling requires an expert to conduct the study in an area. If this is lacking, the result
can be erroneous.
4. The characteristics to be observed may occur rarely in a population, for instance over 30
years of teaching experience o teachers with outstanding performance.
5. Complicated sampling plans are laborious to prepare.
7
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
Factors to consider in determining the sample size. (Macmillian & Schumacher, 1989)
1. Sample sizes as small as 30 are generally adequate to ensure that the sampling
distribution of the mean will approximate the normal curve (Shott, 1990).
2. When the total population is equal to or less than, this same number may serve as the
sample size. This called universal sampling.
3. Slovin‟s formula is used to compute for sample size (Sevilla, 1990).
n=
Where n stand for a sample; N, the population size, and e is for desired margin of error
n=
= = 1,905
8
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
4. According to Gay (1976), offers some minimum acceptable sizes depending on the type
of research as follows.
a) Descriptive research - 10 percent of the population. For smaller populations, a
minimum of 20 percent may be required.
b) Correlational research - 30 subjects
c) Ex - post facto or causal comparative research - 15 subjects per group.
d) Experimental research - 15 subjects per group. Some authorities believe 30 per
group should be considered minimum.
5. By using the Calmorin‟s formula, the problem is solved as follows.
Ss =
Where Ss stand for sample size; N, the population; V standard value (2.58) of 1 percent
level of probability with 0.99 reliability level; Se, sampling error (0.01); and p, the largest possible
proportion (0.50).
Ss =
Ss = 218
9
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
items. The population of a city, the number of workers in a factory and the like are
examples of finite universes, whereas the number of stars in the sky, listeners of a specific
radio programme, throwing of a dice etc. are examples of infinite universes.
2. Sampling unit: A decision has to be taken concerning a sampling unit before selecting
sample. Sampling unit may be a geographical one such as state, district, village, etc., or
a construction unit such as house, flat, etc., or it may be a social unit such as family, club,
school, etc., or it may be an individual. The researcher will have to decide one or more of
such units that he has to select for his study.
3. Source list: It is also known as „sampling frame‟ from which sample is to be drawn. It
contains the names of all items of a universe (in case of finite universe only). If source list is
not available, researcher has to prepare it. Such a list should be comprehensive, correct,
reliable and appropriate. It is extremely important for the source list to be as
representative of the population as possible.
4. Size of sample: This refers to the number of items to be selected from the universe to
constitute a sample. This major problem before a researcher. The size of sample should
neither be excessively large, nor too small. It should be optimum. An optimum sample is
one which fulfills the requirements of efficiency, representativeness, reliability and
flexibility. While deciding the size of sample, researcher must determine the desired
precision as also an acceptable confidence level for the estimate. The size of population
variance needs to be considered as in case of larger variance usually a bigger sample is
needed. The size of population must be kept in view for this also limits the sample size. The
parameters of interest in a research study must be kept in view, while deciding the size of
the sample. Costs too dictate the size of sample that we can draw. As such, budgetary
constraint must invariably be taken into consideration when we decide the sample size.
5. Parameters of interest: In determining the sample design, one must consider the question
of the specific population parameters which are of interest. For instance, we may be
interested in estimating the proportion of persons with some characteristic in the
population, or we may be interested in knowing some average or the other measure
concerning the population. There may also be important sub-groups in the population
about whom we would like to make estimates. All this has a strong impact upon the
sample design we would accept.
6. Budgetary constraint: Cost considerations, from practical point of view, have a major
impact upon decisions relating to not only the size of the sample but also to the type of
sample. This fact can even lead to the use of a non-probability sample.
7. Sampling procedure: Finally, the researcher must decide the type of sample he will use
i.e., he must decide about the technique to be used in selecting the items for the
sample. In fact, this technique or procedure stands for the sample design itself. There are
several sample designs (explained in the pages that follow) out of which the researcher
must choose one for his study. Obviously, he must select that design which, for a given
sample size and for a given cost, has a smaller sampling error.
10
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
11
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
which has a smaller sampling error for a given sample size at a given cost. In practice, however,
people prefer a less precise design because it is easier to adopt the same and also because of
the fact that systematic bias can be controlled in a better way in such a design.
In brief, while selecting a sampling procedure, researcher must ensure that the
procedure causes a relatively small sampling error and helps to control the systematic bias in a
better way.
Sampling techniques
1. Probability sampling - In probability sampling, the sample is a proportion (a certain
percent) of the population and such sample is selected from the population by
means of some systematic way in which every element of a population has a chance
of being included in the sample.
Properties of Random Sampling
Equiprobability - means that each member of the population has equal chance
or being selected and included in the sample.
Independence - means that the chance of one member being drawn does not
affect the chance of the other member.
Kinds of Random Sampling
a) Restricted Random sampling - involves certain restriction intended to improve the
validity of the sampling. This design is applicable only when the population being
investigated requires homogeneity. A study on the effectiveness of a new drug
can be tested to two groups of animals, the controlled and experimental groups.
Those animals that belong to controlled groups will not be treated with a new
drug while those that belong to the experimental group will be treated with a
new drug. The selection of a sample of paired animals should be with restriction
according to their degree of illnesses so that significant difference between the
two groups will accepted.
b) Unrestricted random sampling - is considered the best random sampling design
because there were no restriction imposed and every member in the population
has an equal chance of being included the sample.
Types of Random Sampling
a) Simple random sampling is the probability sampling design, in which the
sample is selected by a process that does not only give each element in the
12
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
population a chance of being included in the sample but also makes the
selection of every possible combination of the desired number of cases
equally likely. The sample is selected in one of three ways: by means of a
table of random number, by using the lottery technique or by using roulette
wheel technique.
In the fishbowl technique, elements of the population are arranged
sequentially and assigned numerical identification. Corresponding
numbers are marked on separate sheets of paper and put into a box
or closed container. Numbers are tossed so that they are mixed. The
researcher then has to pick out these sheets of paper one by one,
without looking, until the number of sheets drawn equals the sample
size determined.
The roulette wheel technique is appropriate to use when the
population is 75 or less. In this technique, each individual is assigned a
number in an orderly sequence: alphabetically, by birth date or by
any other systematic arrangement. Corresponding numbers are on a
roulette wheel. A spin of the wheel and its stopping at a particular
number selects the individual assigned to that number as a unit in the
sample. The process goes on until all the individuals needed to
compose the sample size have been selected.
When using the table of random numbers, random numbers are
assigned to each of the elements of the population, based on the
table of random numbers found in most statistics books. In this
method, the researcher has to choose number from the table by
means of random start through the fishbowl technique or any other
random technique. Once the list of random numbers has been
selected, the samples will be chosen based on the random list. In
choosing the sample, the digits to be used have to parallel the digits
of the population.
b) Systematic random sampling. This is sampling by regular interval or according
to a predetermined sequence, such that every n th of the population
becomes part of the sample. In this method of sampling the origin of
sequence has to be controlled by chance. In using this method, the
researcher has to determine first the sampling interval he will use. To
determine the sampling interval, the following formula can be applied
(Alreck &Settle, 1995).
K=
Where:
K = sampling interval
N = total population
n = the desired sample size
13
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
Applying the formula, what is the appropriate sampling interval if the desired
sample size is 286 and the total population is 1000?
K=
K= = 3.49 or 3
After determining the sampling interval, the researcher has to list all the
elements comprising the population in arbitrary order. Every n th or kth unit is
chosen as a sample. The process is repeated until the required number of
sample is obtained.
c) Stratified random sampling. This is sampling by stratum or layer. This method of
drawing a random sample is used when the researcher wants to ensure that
the different groups comprising the population are adequately represented
in the sample. When using this sampling method, the researcher has to divide
the population into groups or strata into which he wants to stratify it (e.g. by
age, gender, religion or other classificatory schemes). Samples are then
drawn from each group through proportional or non- proportional stratified
techniques. Proportional stratified random sampling is based on the
percentage of subjects in the population that is present in each stratum.
Thus, if 30% is represented in the first stratum, then 30% of the final sample
should come from that stratum. In non - proportional stratified random
sampling, the researcher selects the same number of subjects to be in each
stratum of the sample. Whether proportional or non- proportional, stratified
random sampling is often more efficient than simple random sampling
because a smaller number of subjects will need to be used. Dividing the
population into subgroups also allows a researcher to compare subgroup
results.
d) Cluster random sampling. This method of drawing random samples is similar
to stratified random sampling in that groups of individual are selected from
the population and subjects are drawn from these groups. In cluster
samplings, however, the researcher identifies convenient, naturally occurring
group units, such as neighborhoods, school districts or regions, not individual
subjects, and then randomly selects some of these units for the study. Once
the units have been selected, individuals are randomly selected from each
one. This method of sampling is used most often in cases when it is not
feasible to obtain a list of all the members of the population.
e) Multi - stage random sampling. This design is used for national, regional,
provincial or country level studies (Rebullida, et al. 1993). It involves several
stages in drawing the sample from the sample from the population. In this
method of drawing random samples, the researcher first decides on the level
of analysis that will be studied. This is followed by the determination of the
sample size per stage or level. After the sample size had been determined,
14
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
15
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
3. Mixed - Methods Sampling. This is a sampling method that combines different types of
sampling method into a single design. This is supported by the idea that the weakness
of one method may be compensated by the strengths of the other method that is
used. The use of mixed methods research design was spurred by application of two
key concepts. “multi- method, multi - trait matrix and triangulation” which were
introduced by Campbell & Fiske in 1959 (multi - method - multi- trait) and the four
types of triangulation by Denzin (2009); “data triangulation, method logical
triangulation, investigator triangulation, and theory triangulation” (in Daniel, 2012).
Through the years, researchers have made adjustment in their sampling procedure as
a response to change in technology, lifestyles, the legal environment, and
nonresponse rates.
a) Telephone - based sampling. This is a sampling procedure that utilizes
telephone numbers as sampling units. According to research, telephone
surveys were the dominant survey methodology since the 1980s. There are two
subtypes of telephone - based sampling, list - based sampling taken from
telephone directories, list of employees, customers, etc. and random digit
dialing (RDD). The random sampling procedure previously discussed can also
be applied in the telephone - based sampling procedure.
b) Web - based sampling. In this sampling procedure, email addresses, website
visits, and recruited users of the internet are utilized as sampling units. There are
three categories of web - based sampling, namely list - based sampling,
sampling of website visits, and sampling from recruited panels of potential
participants in research projects.
c) Address - based sampling (ABS). In this kind of sampling procedure, postal
addresses are utilized as sampling units. The ABS sampling is used mostly in
national surveys.
d) Time - based sampling. Units of time are used as sampling units in this type of
sampling. This is used in studying repeated outcomes that vary a great deal
over time. The units of time may be time of the day, days of the week, months
of the year, or some other unit. The time intervals may be sampling units. The
length of the interval would depend in part on the rate of occurrence of what
is to be observed. Preparation for this type of sampling typically involves visits
to the locations was the data will be collected, observing the density of the
target population over time and gathering information from informants. Using
the information obtained, a sampling frame of time units is developed. Data
might be collected several times per day at time periods selected using simple
random sampling or systematic sampling, upon the occurrence of a specific
event, or at specially scheduled time intervals. Subtypes of time- based
sampling according to Daniel (2012) are experience sampling method, events
sampling methodology; and the use of the time by employees‟ equipment,
and facilities, known as work sampling. The variables that may be studied are
social interaction, mood swings, levels of stress, or factors that have impact on
work experiences and productivity.
16
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
e) Space - based sampling. This refers to a set of sampling procedures that utilize
space as a sampling unit. This type of sampling is also referred to as area
sampling, spatial sampling, location- based sampling, venue - based sampling
and facility - based sampling. The space may be geographical units or various
locations or venues. It is the principal mode of sampling utilized in nationwide
personal interview surveys, environmental sampling, and ecological sampling
(Daniel, 2012).
Research Instrumentation
Alongside with choosing the method of data collection is choosing the research
instrument. Dagdag et. al (2006) defined research instruments as devices or tools which the
research uses to gather answers to his research questions.
Researchers can choose the type of instruments to use based on their research question
or objectives. There are two broad categories of instruments namely; researchers - completed
instruments and subject - completed instrument. Examples are shown on the following table
Researcher - completed Instruments Subject - completed Instruments
Rating scales Questionnaires
Interview schedules or guides Self - checklists
Tally sheets Attitude scales
Flowcharts Personality inventories
Performance checklists Achievement and Aptitude tests
Time - and - motion logs Projective devices
Observation forms Sociometric devices
Treece and Treece (1977), divided the research instrument or tools for gathering data in
research are of two categories or kind.
Clerical tools are used when the researcher studies people and gathers data on the
feelings, emotions, attitudes, and judgments of the subjects. Some of clerical tools are: filled
record, histories, case studies, questionnaires, and interviews schedules.
A critical potion of the research study is the instrument used to gather data. The validity
of the findings and conclusion resulting from the statistical instruments will depend greatly on the
characteristics of your instruments.
There are different ways of choosing for research instruments (Nalzaro, 2012):
17
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
1. Read professional journals to learn what kind of instruments are being used for similar
studies, their format, style, and how they are used by the writers.
2. Read books that provide a description or an actual copy of various instruments for the
reader.
3. Talk with other researchers who may know of certain tools they have developed for
themselves, or may have used tools developed by others.
4. Combine or adapt one or more tools used by other researchers.
5. Develop one‟s own instrument to fulfill a specific need.
According to Falatado et al. (2016) the following are the general criteria of good research
instruments.
1. Validity - refers to the extent to which the instrument measures what it intends to measure
and performs as it is designed to perform. It is unusual and nearly impossible that an
instrument is 100% valid that is why validity is generally measured in degrees. As a process,
validation involves collecting and analyzing data to assess the accuracy of an instrument.
There are numerous statistical tests and measures to assess the validity of quantitative
instruments that generally involves pilot testing. There are three major types of validity. These
are the following.
a) Content validity primarily focuses on the appropriateness, authenticity and
representativeness of the items of the test to measure the behavior or
characteristics to be investigated. This normally determined after a group of
experts on the subject matter has examined systematically the test items. These
items are pilot tested and hereafter certain statistical calculations can be done
on the results depending on the type and purpose of the test. Item analysis, for
example may be done with respect to achievement tests to determine the
difficulty and discrimination indices of each item. Difficulty index describes how
18
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
easy or difficult the test items are. The discrimination index gives the ability of
each item to identify those who know and do not know the items.
b) Criterion- related validity is achieved by determining the effectiveness of the test
to measure results against a given set of criteria or standards. In achievement or
performance test, the desired competencies are used as the criteria. This type of
validity is better understood statistically. A criterion is any other instrument that
measures the same variable. Correlations can be conducted to determine the
extent to which the different instruments measure the same variable. Criterion
validity is measured in three ways:
Convergent validity - shows that an instrument is highly correlated with
instruments measuring similar variables. Example: geriatric suicide
correlated significantly and positively with depression, loneliness and
hopelessness.
Divergent validity - shows that an instrument is poorly correlated to
instruments that measure different variables. Example: there should be a
low correlation between an instrument that measures motivation and
one that measure self - efficacy.
Predictive validity - means that the instrument should have high
correlation with future criterions. Example: a score of high self- efficacy
related to performing a task that should predict the likehood a
participant completing the task.
c) Construct validity refers to whether you can draw inferences about test scores
related to the concept being studied. The extent of a test to appropriate its
ability to demonstrate a particular theoretical construct or development
characteristics or indicator is described by the materials‟ construct validity. There
are three types of evidence that can be used to demonstrate a research
instrument has construct validity:
Homogeneity - this means that the instrument measure one construct.
Convergence - this occurs when the instrument measures concept similar
to that of other instruments. Although if there are no similar instruments
available this will not be possible to do.
Theory evidence - this is evident when behavior is similar to theoretical
proposition of the construct measured in the instrument.
2. Reliability relates to the extent to which the instrument is consistent. The instruments should
be able to obtain the same response when applied to respondents who are similarly
situated. Likewise, when instrument is applied at two different points in time, the responses
must highly correlate with one another. Hence reliability can be measured by correlate the
responses of subjects exposed to the instrument at two different time periods or by
correlating the responses of the subjects who are situated. An example of this is when a
participant completing an instrument meant to measure motivation should have
approximately the same responses each time the test is completed. Although it is not
possible to give an exact calculation of reliability, an estimate of reliability can be achieved
through different measures. The three attribute of reliability are the following:
19
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
20
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
Instrument Development
Research instrument refers to various methods through which a researcher obtains data
from respondents for his research work. The term data refers to all forms of information that
researchers obtain from the participant of the study. Adedokun (2003) asserts that data refers
“to any fact, observation or facts relating to the subject of the study”. There are different types
of research instruments that can be used by researchers for their studies; it depends on the
nature of research that is to be carried out. In this write up, we shall discuss various measurement
instruments that can be used alongside with studies that are suitable for them.
However, the collection of data is an important part of any research activity. This is
because; the conclusions of the study are based on what the data reveals. Hence, no
researcher is greater than his data. Basically, data can be obtained from two major sources;
primary and secondary sources. Primary data represents the information gathered by the
researcher through the use of questionnaire or personal interview or observation method; while
in secondary data, the researcher collects information that has already been obtained and
processed by government departments or various agencies before it is made available for other
interested users. These are published and unpublished sources e.g. journals, textbooks,
newspapers, magazines, fliers, annual reports, bulletins, periodicals etc As a result, the kind of
data to be collected, the method of collection to be used, and the scoring of the data must be
considered when undertaken any research activity.
According to Aina, 2004; Adedokun, 2003; Avwokeni, 2006; Adeniyi; Oyekanmi and Tijani,
2011. Researchers can collect the following types of data from respondents:
21
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
22
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
4. Focus Group Discussion: - This data collection instrument refers to a process whereby
researchers obtain data from large group of people at the same time. This method is
23
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
different from interview method; in an interview method, researcher focuses on one person
at a time but in a focus group discussion method, the researcher obtains data from large
number (group) of people for his research activity. Focus group discussion method is very
popular when carrying out research in the field of behavioral science, library and information
science, archival science, records and information technology. It could be noted here that
a need may arise for a researcher to use more than 2 or 3 approaches to obtain data for his
research activity. This depends on the supervisor, nature of the research or problem to be
investigated.
However, in focus group discussion; a researcher identifies key informants that may be
contacted to elicit the deserved information on the variable(s) of interest in a study. It is very
important to note that in evaluator study or when accessing the performance of a system or
a project or when working at a policy and its impact on a particular operation in a society or
organization; focus group discussion method could employed. The approach is used to
generate qualitative data in explaining a phenomenon under study or investigation.
Membership of the focus group discussion should not exceed 10 members at a time. It is like
a mini conference where members of a group could be assembled in a conducive location.
Before now, it is needful for the researcher to have obtained their consent to take part in the
study. Besides, the researcher must design a focus group discussion guide. The guide must
contain outlines that capture variables of interest in the study.
The following materials are needed for this method of data collection:
Research assistants;
Video recorder and cassette;
Biro and paper;
Tape recorder and cassette, and
Light refreshment to entertain the participants.
After the focus group discussion exercise, the researcher has to transcribe the data into
qualitative information e.g. on the nature of reference services available in the library; in a group
where 10 members are involved, if 7 members affirmed that they are having good reference
services in their library while the rest members‟ response are negative. Then it can be
calculated/quantify as: 7/10 *100 = 70%; this is the figure that the researcher will report in his
work. Moreover, the major advantage of this method is that it added credibility and originality to
the research activity while it challenges include: too cost to carry out, it takes too much of time
to conduct and some of the respondents may not be free to contribute extensively especially if
their boss is invited to such gathering.
5. Experiment
This type of data collection instrument takes place in pure and applied science research.
Here the researchers carry out some experiments in the laboratory setting in order to test some
reactions that may take place in the object of research. The advantages of this method is that it
produces immediate result, its results are viable and error free if it is well carry out under normal
condition/circumstances. While, its problems include: it is too costly to undertake and those
chemicals used may cause permanent damage to the researcher if they are carelessly
24
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
handled.
Classification of Research Based on Data Collection Instruments (Yaya, 2014).
Types of Research Data Collection Instruments
Applied research Questionnaire, Interview and observation.
Questionnaire, focus group discussion, interview and
Survey research observation.
Correlational research Observation, questionnaire, focus group discussion and
interview
Evaluation research Focus group discussion, interview and observation
Experimental research Experiment and observation
Action research Questionnaire and interview
Research Intervention
Summarize data and reveal what is typical and atypical within a group.
Show relative standing of individual in a group through the use of percentile rankings,
grade equivalents, age equivalents, and stanines;
Show relationship among variables by means of statistical correlations;
Show similarities and differences among groups with the use of the tests of differences;
Identify error that is inherent in the selection of samples;
Test for significance of findings; and
Make other inferences about the population.
25
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
Analytic Procedures for Quantitative Data. There are five types of analytic procedure that a
researcher can choose from, to answer the problems posed in his study namely: descriptive
analysis, univariate anlaysis, bivariate analysis, multivariate analysis and comparative analysis.
Let us describe how each of these analytic procedures is done.
1. Descriptive Analysis. In this type of analysis, the researcher is only after describing the
characteristics of the subjects under study. Data are usually analyzed to -
Identify the general characteristics of a group, with the use of descriptive statistics
such as percentage, mean, median, and mode.
Determine differences in the group or how members of a group vary with
reference to a given variable or factor being studied with the use of the standard
deviation and coefficient of variation.
2. Univariate analysis. This type of analysis is employed when the researcher wants to
analyze one variable or factor at a time. Univariate analysis relies heavily on the use of
summary statistics, namely: measure of central tendency and measures if variability.
Mean is the most common average used to indicate the most typical response. It
is computed by dividing the sum of the values by the number of values or cases.
It can only be subjected to arithmetical operations.
Median is the middlemost value in an array, such that 50% are below it and 50%
are above it. This is the appropriate average to use when the data are ordinal.
Mode is the category or value with the greatest frequency of cases. It is the only
acceptable indicator of the most typical case for data which are nominal or
categorical.
Measures of variability are measures that reflect the amount of variation in the scores of
a distribution. The most commonly used measures for Univariate analysis are defined below.
Minimum and maximum values. The minimum value indicates how far the spread
toward the lower direction and the maximum value shows the extent of spread
towards the upper direction from the average. These values describe the
respondents or cases that represent the least and the most in whatever
dimension is being measured.
Range. It is simply the distance or difference between the maximum and
minimum value, showing the total spread between extremes. It is the most
unreliable measure of variability or dispersion as it is affected by extreme scores
at either end of the distribution.
Standard deviation. It is a measure of deviation or spread away from the mean. It
is a single value that indicates the amount of dispersion in an array of scores.
Quartile deviation. It is the appropriate measure of variability to employ when the
median is the average used in describing a given distribution.
3. Bivariate Analysis. This type of analysis is used when the researcher is interested in probing
into the relationship of two variables at a time. Bivariate analysis of relationship requires
the use of Correlational statistics, such as Pearson‟s r, Spearman rho, Chi -square and
other associational techniques.
26
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
4. Multivariate Analysis. This procedure for analyzing data is utilized when there are
research question which cannot be responded using bivariate analysis. This analytic
procedure permits the determination of the degree of relationship between one
dependent variable and two or more independent variables simultaneously. The most
commonly used statistical tools for multivariate analysis are multiple regression analysis
and multiple classification analysis.
5. Comparative analysis. When research participants have to be compared on the basis of
certain variables being studied, comparative analysis is appropriate to use. This type of
analysis requires the use of statistical tests of significant difference, like the t- test, critical
ratio test and analysis of variance (ANOVA).
Hypothesis testing
27
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
Summarizes the four levels of measurement scales and the appropriate statistics
for each level.
Quantitative variables like nominal and ordinal variables cannot make use of
parametric statistical test unlike interval and ratio variables. Interval and ratio levels of
measurement can be applied with both the parametric and nonparametric statistical
tests. In parametric statistical tests, we can conveniently make use of the mean and
standard deviation, the z- test, the t-test, the analysis of variance (ANOVA), and the Chi -
square test, the Friedman‟s test, Kendall‟s tau, the Binomial test, the Spearman rank
correlation, the Kruskall - Wallis test, and Wilcoxon signed rank test, to name a few, to
interval and ratio levels of measurements. Interval and ratio measurement can be
reduced to nominal or ordinal measurement, while nominal and ordinal measures
cannot be upgraded to interval or ratio measures.
3. State the level of significance (α) and the sample size.
In starting the level of significance (α), the researcher sets up the rejection region
and acceptance region for null hypothesis. The rejection region is called the critical
region. The remaining region is called the acceptance region is called the critical region.
The remaining region is called the acceptance region.
28
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
The type of symbol in the alternative hypothesis H1 tells us what type of rejection region to
be used as shown in table below.
Location of the rejection region to One region on Two regions, One region
be used the left side one on each on the right
side side.
A one - sided test or a one - tailed test is a statistical test which has the rejection
region located in the left tail or the right tail of the distribution. On the other hand, a two -
sided test or two - tailed test is a statistical test in which the rejection region is located in
both of the distribution.
The level of significance (α) is the probability that the test statistic falls within the
rejection region. The most commonly used levels of significance are 0.05 and 0.001. these
are the risk taken in rejecting a true hypothesis. When a null hypothesis is rejected or
accepted, there is a risk of making an error. There are two types of possible errors that
can be made at this point. We can make a type I error when we reject a true hypothesis
when we should accept it. On the other hand, we make a type II error when we accept
a false null hypothesis when in fact we should reject it.
The probability of making a type I error is equal to the level of significance which is
either 0.05 or 0.01 level. This is denoted by the Greek letter alpha (α). The probability of
making a correct decision is 1 - α.
29
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
We see from table above that the type I error is rejecting a null hypothesis that is
true while a type II error is accepting a null hypothesis that is false. In any decision that
we make, there is always a risk of making an error.
30
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
Assessment Tasks
A. Direction: Read and analyze the following research topics and identify what types of
quantitative research is appropriate for each. Then justify your answer by providing
explanation.
1. A research investigated the medical properties of the rare Amazonian tree and
discovered that its component can be made into drugs that can cure dengue.
2. A researcher wishes to correlate the performance between English (X) and
Mathematics (Y) of freshmen nursing students in the college of Nursing at the Central
Philippine University, Iloilo City.
3. A researcher wishes to examine the smoker and non-smoker to determine the extent of
hearing losses related to the duration of smoking. Subjects with family histories of
deafness, exposure to disturbing or loud noises or histories of ear discharges were
excluded from the study. Based on the research results, it was concluded that smoking
increases the incidence and severity of deafness and considerably diminishes the
quality of life.
4. A researcher explored how the community could be engaged in the implementation
of the Brigada Eskwela Program for a strong and sustainable school - community
partnership.
B. Direction: Identify the type of sampling to be used in each of the following.
1. In a large school district, all teachers from two building are interviewed to determine
whether they believe the students have less homework to do now than in previous
years.
2. Every seventh customer entering a shopping mall is asked to select his or her favorite
store.
3. Nursing supervisors are selected using random numbers in order to determine annual
salaries.
4. Mail carries of a large city are divided into four groups according to gender (male or
female) and according to whether they walk or ride on their routes. Then 10 are
selected from each group and interviewed to determine whether they have bitten by
a dog in the last year.
5. In the study of a cause of lung cancer in particular patients who have the disease,
patient were matched with control by age, sex, place of residence, and social class.
The frequency of cigarette smoking in the two groups was then compared. What type
of sampling should be used?
C. Direction: Below are hypotheses stated in different ways. Answer the following questions
about each item.
a) In what form is the hypothesis stated?
b) Does it use a directional or non - directional test?
c) What level of measurement is each of the variables?
d) Convert the non - directional into directional.
1. There will be a significant difference in mean scores between boys and girls in a
reading test.
31
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
Compute the sample size (20%) for each school using stratified sampling method. Present
them in a table
2. Below is table showing the population of the study. Determine the sample size using
Slovin‟s formula, then, apply stratified random sampling. Present them in a table.
Performance tasks
Do the following:
1. Read and download at least five (5) research articles about the topic have chosen for
your research output.
2. Identify and describe the research design and sampling techniques used in the
chosen research articles.
3. Describe what research design and sampling techniques you are going to use in
conducting your research topic.
4. Write your research design and sampling techniques of your topic.
32
Digging - up the Principles and Concepts of Practical Research: A Quantitative Approach by Mr. Resty Samosa
33