Sampling

 It is the process of selecting the sample or a portion of the population.

 refers to the process of systematically selecting individuals, units, or groups to be analyzed
during the conduct of study.
 The reason for selecting the samples is to get information about the target population.
 An important characteristic of a sample that must be considered is Representatives.

Sample

 It is a small portion of the population selected for observation and analysis.

 is a subset of the population elements.

Population

 It refers to a collection of individuals who share one or more noteworthy traits that are of
interest to the researcher.
 May be all the individuals belonging to a specific category or a narrower subset within that larger
group.

Types of Sampling:

 Probability Sampling
 It is random selection of sample. Each element in the population has the same equal
chance of being selected as a sample.
 Every member of the population has a probability of being selected or included in the
sample.
 There is greater representation in each unit in the population
 The findings can be generalized to the population

Types of Probability Sampling

 Simple Random Sampling

 Also known as Fishbowl technique. In this technique selection is purely based on
chance.
 All members of the population have an equal chance at being chosen as part of
the sample.
 Systematic Random Sampling
 using kth interval formula.
 The sample is drawn by randomly selecting a starting number and then selecting
every nth unit in arbitrary order until the desired sample size is reached.
 Stratified Random Sampling
 Divided into subgroups or strata.
 Just like in Quota, Stratification is based on variables that are relevant to the
study.
 The population is split into different groups. People from each group will be
randomly chosen to represent the whole population.
 Cluster Sampling
  it was use when the population is large and widely dispersed. Also called multi-
stage sampling.
 Districts or blocks of a municipality or a city which are part of the cluster are
randomly selected.
 Non-Probability Sampling
 There is a form of bias in the selection of sample.
 There is no assurance that each unit in the population has the same equal chance of
being selected as a sample.
 There is no assurance that each unit in the population is properly presented
 The findings are limited to the sample
 Participants are intentionally selected based on certain identified factors.

Types of non-probability sampling:

 Convenience Sampling
 Selection of samples based on the convenience of the researchers.
 Participants are chosen for their convenience and availability, rather than
through a random or systematic selection process.
 Snowball Sampling
 referral system, with this sampling technique, initial sample members are asked
to refer other people who meet the criteria required by the researcher.
 Participants are chosen based on referrals or recommendations from existing
participants.
 Purposive Sampling
 Selection of sample is based on the judgement of the researcher or sets a
criteria.
 Also called Judgmental Sampling.
 Quota Sampling
 Identifies population sections or strata and decides how many participants are
required from each section.
 Participants are selected based on pre-defined quotas to represent specific
characteristics or subgroups.
 Expert Sampling
 Individuals with specialized knowledge or expertise in a particular field are
selected to participate in a study.

Quantitative Data Analysis

Descriptive Statistics

 A statistical technique that provides simple description and summary about the
sample and about the observations that has been made.

Examples of descriptive statistics that define the data:

 Frequency Percentage distribution

 Refers to the display of data that specifies the percentage of observations that exist
for each data point or grouping of data points.
  This is a useful method of expressing the frequency of survey responses and other
data.
 Are often displayed as tables or as bar graphs or pie charts (Lavrakas, 2008)
 Central Tendency
 is an estimate of the “center” of a distribution of values.

Three major types of estimates of central tendency:

o Mean
 Or average, is probably the most commonly used method of describing central
tendency.
 To compute the mean, all you do is add up all the values and divide by the number
of values.
o Median
 Is the score found at the exact middle of the set of values.
 One way to compute the median is to list all scores in numerical order, and then
locate the score in the center of the sample.
o Mode
 Is the most frequently occurring value in the set of scores.
 To determine, you have to arrange again in order the scores as shown and then
count each one.
 Graphs
 Includes pie or bar charts.

Inferential Statistics

 Inferences or generalizations are made beyond the sample data.

Inferential Statistics include:

 Independent T-Test
 used in determining significant group differences between two unrelated samples
(e.g., math grades of male and female students).
 Correlation Analysis (Pearson’s r moment of Correlation)
 used in determining significant relationship or association between two continuous
variables.
 One-way ANOVA (Analysis of Variance)
 used in determining group differences between three or more unrelated samples
(e.g., consumer’s buying decision by marital status)
 Paired T-Test
 used in determining significant group differences between related or matched
samples (e.g., weight before and after 3-month exercise programme)

Conceptual Framework

 or conceptual models, like theories, deal with abstractions (concepts) that are assembled by
virtue of their relevance to a common theme.
  provide a perspective regarding interrelated phenomena but are more loosely structured than
theories.
 broadly presents an understanding of the phenomenon of interest and reflects the assumptions
and philosophic views of the model’s designer.
 can serve as springboards for generating research hypotheses (Polit and Beck, 2007).
 is a graphical presentation of concepts under study and the existing relationships that exist
between or among these concepts.
 there are times that a research study is based on an existing established theory. In this case, the
framework is referred to as the theoretical framework; in a study that has its roots in a specified
conceptual model, the framework is often called the conceptual framework (although the terms
conceptual framework and theoretical framework are frequently used interchangeably).

Purposes of Conceptual Frameworks:

 To make research findings meaningful.
 To link observations and facts into a meaningful and orderly structure or
scheme.
 To allow researchers to make prediction on the occurrence of
phenomena.
 To serve as catalyst for future research endeavors.

Developing a Framework in a Quantitative Study

 Induction – In developing a framework, one must be able to create generalizations by the
process of reasoning from specific observation.
 You may follow the following steps in developing a framework.
 Select a topic and clarify your objectives.
 Review the literature and discuss problem with colleagues.
 Develop ideas based on the reviewed literature and based on one's own experiences.
 Create a conceptual scheme based on the developed ideas.

Hypothesis
 is a statement of the researcher’s prediction about relationships between or among the variables
under investigation.
 in other words, are predictions of expected outcomes; they state the relationships researchers
expect to find as a result of the study.
 Most quantitative studies are designed to test hypotheses through statistical analysis.

Types of Hypotheses:

 Types of hypotheses according to number of variables: simple versus complex

 Simple hypothesis
 a hypothesis which expresses prediction between one independent variable and
one dependent variable
 states a relationship between a single independent variable, which we will call X,
and a single dependent variable, which we will label Y.
  Y is the predicted effect or outcome of X, which is the presumed cause, or
antecedent
 (e.g., Unemployment leads to higher incidence of crime.)
 Complex hypothesis
 a prediction of a relationship between more than one independent variable
and/or more than one dependent variable (also known as multivariate
hypothesis because of the presence of several variables).
 there is more than one Xs (independent variables), or more than one Ys
(dependent variable).
 (e.g. with multiple independent variable; Illiteracy and unemployment leads to
higher incidence of crime.)
 (e.g. with multiple dependent variable; Unemployment leads to higher incidence
of crime and poverty.)
 Types of hypotheses according to predicted result: null versus research
 Null hypothesis
 explicates that no relationship exists between the dependent and the
independent variable.
 It may also show that the X (independent variable: cause or antecedent) has no
effect on the Y (dependent variable: effect or outcome).
 A null hypothesis is symbolized by Ho.
 (e.g., The number of books owned by a student does not affect his academic
performance)
 Research hypothesis
 also known as alternative or affirmative hypothesis.
 this hypothesis explicates that a relationship exists between the dependent and
the independent variable.
 It may also show that the X (independent variable: cause or antecedent) has an
effect on the Y (dependent variable: effect or outcome).
 (e.g., Exposure to music affects the level of anxiety)
 Directional versus non-directional hypothesis
 Non-directional hypothesis
 a type of research (alternative) hypothesis which state that a relationship or
differences exists between the variables but the direction of that relationship or
difference is not explicated.
 (e.g., Health affects the level of stress among senior high school students.)
 Directional hypothesis
 is a type of research (alternative) hypothesis which state that a relationship
exists between the variables and it also explicates the direction of that
relationship, hence, directional.
 This is a prediction made by a researcher regarding a positive or negative
change, relationship, or difference between two variables of a population.
 Key words that distinguish a directional hypothesis are: higher, lower, more, less,
increase, decrease, positive, and negative.
 (e.g., The health of the students decreases as their level of stress increases.)
Guidelines in Formulating hypothesis:
 Hypotheses are written in declarative form.
 The hypotheses and research problem must be aligned.
 The hypotheses must state the predicted relationship between or among the variables under
study.
 Hypotheses must be based on existing knowledge like previous study results. It may also be
based on the experience and observation of the researcher.
 Be direct to the point. Avoid wordiness and run-on statements

Definition of Terms

 In a research study, concepts or variables need to be defined based on how they will be used in
the study because a definition from the dictionary will usually not suffice.
 This is to further clarify the purpose of the study.

Two types of definitions are relevant in research:

 Conceptual definition
 what a concept means in abstract or theoretical terms; may be taken from the
dictionary.
 Operational definition
 links a concept to the concrete world by telling you how to observe and/or measure the
concept; this is a definition made by the researcher based on how the term(s) will be
used in a particular field of study.
 specifies the operations that researchers must perform to collect the required
information.
 In quantitative studies, researchers need to define the concepts at the beginning of the
research endeavor. This is imperative because quantitative researchers must indicate how
the variables will be observed and measured in the actual research situation.
 Variables differ in the ease with which they can be operationally define.

Research Methodology

 is a way to systematically solve the research problem. It may be understood as a science of

studying how research is done scientifically. (C.R. Kothari, 2004)

Guidelines in writing research methodology:

 The Research Methodology section is written with two purposes in mind:

1) replicate
2) evaluate.
 In this section, the researcher writes each section concisely yet completely to provide enough
detail for a competent reader to replicate the study and reproduce the results.
 The scientific method requires that the results be reproducible, and the researcher must provide
a basis for repetition of the study by others.
  this ensures that the study has undergone scientific process and that the tools utilized in the
study are valid and reliable.
 Methods section
 is also known as Subjects and Methods, Research Methodology or simply Methods.
 Although this part usually appears in the middle section of the manuscript, this is one of
the parts that is usually written first.
 The sequence on how you will write it is dependent on how the study was conducted.
 This section has several subsections. The number of subsections will sometimes depend on the
format of the institution or the target journal of the researcher.
 To ensure that no section of this section will be missed, it is advisable to follow the sections
explicated in this manual.

Research design

 Discuss the approach (qualitative/ quantitative) and design (phenomenology, experimental,

descriptive, etc.) used in the study.
 The reason why the design was chosen must be justified.
 Just like in any problem or any question, there are several possible solutions or answers, but the
most appropriate one must be chosen.
 Refers to an overall strategy that a researcher uses to logically and coherently integrate the
various components of the study.

Types of Research designs:

 Descriptive Research
 aims to observe and report on a certain phenomenon, type of behavior, or trait as it takes
place or manifests itself.
 The researcher achieves this objective by using rating scales and other means to measure
the variables as they occur.
 One limitation is its inability to establish causal relationship, that is, one variable cannot be
claimed as the cause of another variable. This is why the descriptive research design is used
when little is known about a topic or when the study is exploratory in nature.
 To observe and report on a certain phenomenon
 Correlation Type
 The aim of the correlational research design is to determine whether an increase or
decrease in one variable corresponds to the increase or decrease in another.
 It does not seek to establish a cause-effect relationship but mere association among
variables. Thus, like in the descriptive type, experimental manipulation is not used in the
correlational research design.
 Variables are still measured as they occur.
 To determine the nature of the relationship between variables without looking into the
cause
 Ex Post Facto Type
 aims to infer a cause from the already existing effects
  Although this research design attempts to establish a causal relationship between
variables, the research design does not use experimental manipulation. Thus, it cannot
be said that a change in the variables takes place in the actual study.
 Like the descriptive type, the ex post facto research design is used when the study being
conducted is exploratory and little is known about the phenomenon or behavior being
studied.
 To infer the causes of a phenomenon which have already occurred
 Quasi-experimental Type
 aims to establish a causal relationship between two variables.
 This effect is presumed to have occurred during the study itself.
 This means that experimental manipulation is applied to the subjects to some extent.
 It should be noted that this divides the subjects into intact groups.
 As its name suggests, an intact group has already been established before the study
takes place.
 For instance, it may be a group of individuals with the same educational background,
same nationality, or age bracket. Because of this, it is necessary to ensure matching
between the two groups based on relevant observable characteristics such as education,
aptitude, age, and wealth.
 Since participants are not randomly assigned to either the treatment or control group,
there is a lack of randomness in this type of research design. Because of this, the quasi-
experimental design provides limited conclusiveness in establishing the causal
relationship between variables.
 Its goal is to establish cause-and-effect relationships
 Experimental Type
 Also known as true experimental.
 Like the ex post facto and the quasi-experimental designs, the experimental type also
aims to establish a cause-effect relationship.
 Unlike the quasi-experimental research design, however, the experimental type applies
variable manipulation more extensively. Moreover, it does not only assign groups but
specific individuals to the control and treatment groups.
 This ensures greater control on the part of the researcher and less threats to the validity
of the study. Despite the rigidness of the experimental design, it still has some
limitations.
 Hawthorne effect – refers to the observed change in the behavior of participants who
know that they are being observed.
 Its goal is to establish cause-and-effect relationships

Research Locale

 Describe the geographic characteristics of the place of study.

 In this section, anonymity must always be observed.
 It is also imperative to state the reasons why the specific locale was chosen.
 The locale or the place where the study will be conducted must be fit to address the needs of
the study.
Population and Sampling/ Key Informant Selection

 Describe the demographic characteristics of the respondents/participants.

 Describe the sampling technique used.
 Enumerate the inclusion and exclusion criteria used in the selection of the participants.
 For animal samples, the genus and species must be specified. The researchers also need to
specify the condition of the animals (i.e. castrated, pregnant, etc.)., the manner on how they
were fed, and their environment (temperature, lighting) during the experiment.

Research Ethics

 This is the section where the researcher can attest that the study was conducted with
consideration to the rights of the human subjects they will involve in the study.
 In this section, the researchers must enumerate the ethical principles maintained in the study,
and how it was maintained, including ethical board reviews or permissions on animal usage.

Research Instruments

 Each instrument or questionnaire used in the study must be described in detail here.
 Mention the number of parts, the types of questions, the number of items, and which item or
part will answer specific question.
 Whether the instrument is borrowed or made by the researcher, it must be stated in this section.
 For borrowed questionnaires, permission to use must be secured from the original author.
 The researcher also needs to mention how validity and reliability testing were done.
 If equipment and materials were use, just like in experiments, those available off the shelf
should be described exactly and the sources of materials or specimens should be given.
Modifications to equipment or equipment constructed specifically for the study must be
carefully described in detail.

Data Collection
 The step-by-step process must be explained comprehensively by the researcher.
 For experimental studies, the methods used to prepare reagents, fixatives, and stains should be
stated exactly, though often, references to standard recipes in other will suffice.
 For studies where subjects are exposed to a certain intervention, the intervention must be
described in detail.
 The type of intervention, how it was designed, who designed it, the duration and frequency of
exposure, the manner on how observations will be measured or tested, and who will measure
the observations need to be explained in this section.
 The usual order or presentation of methods may need to be described together and strict
chronological other cannot always be followed.
 If the methods are new, the researcher must provide all of the details required to repeat the
methods. However, of a method has been previously published in standard journal, only the
name of the method and a literature reference need to be cited.

Data Analysis

 The statistical tests used in the study will be mentioned here.

  When and how each statistical test was used must be specified. Like, which variables were
treated using a specific statistical and for which purpose (e.g. ANOVA to determine significant
difference on the level of student satisfaction among the four group of respondents).
 The researcher must be precise in describing measurements and he must include errors of
measurements.
 Ordinary statistical methods could be used without citations, while advanced or unusual
methods may require a literature citation.
 Basic formulas are not needed to be included, unless originally created by the researcher, or the
formula is unusual.
 If a statistical software was utilized, it is advisable to specify the software used and the version in
this section

 There are usually existing tools or research instruments which are commonly available for use of
researchers in a specific field. However, there are times that there are no available instruments that
will measure the constructs of your interest.

Technique created by D.L. Streiner and G. Noorman in 2008:

 What are the requirements in developing an instrument?

 Clearly define the construct of the measurement instrument;
 Conduct a pilot study to test the measurement instrument;
 Determine the validity of the measurement instrument.
 What do I need to document as I develop the instrument?
 Clear description of the construct or attribute that you want to measure
 Several (old and new) versions of items
 Formulation why certain scorings were chosen
 Results of pilot testing
 Final version of the measurement instrument

Steps in Instrument Development:

Step 1 Definition and elaboration of the construct intended to be measured
o Conceptualization
 The first step in instrument development
 involves defining the construct and the variables to be measured.
Step 2 Choice of measurement method
o Some constructs form an unbreakable alliance with a measurement instrument
Step 3 Selecting and formulating items
o To get input for formulating items for a multi-item questionnaire you could examine
similar existing instruments from the literature that measure a similar construct
Step 4 Scoring issues
o How do you intend to score each item? What is the scale that you are going to use?
Step 5 Pilot study
o Be aware that the first version of the instrument you develop will (probably) not be the
final version.
o It is sensible to (regularly) test your instrument in small groups of people.
 o Pilot study
 is intended to test the comprehensibility, relevance, and acceptability and
feasibility of your measurement instrument.
 the developer can determine whether there are unclear or flawed items that
must be revised or removed.
 This can be done to a group of 10-20 people who have the same characteristics
as your target respondents. However, the people involved in the pilot testing
must not be included in your final set of respondents.
Step 6 Field-testing
o This is when you will finally administer the questionnaire in the field.
o Tallying and computing will follow it.

Data Collection

 is the process of gathering and measuring information on variables of interest, in an established

systematic fashion that enables one to answer queries, stated research questions, test
hypotheses, and evaluate outcomes.
 The manner of collection depends on several factors like the type or nature of data to be
collected, the goal of the research, or even the specific discipline of the research study.
 There are also several approaches as to the application of the methods of data collection. The
important thing to consider is that one must collect data without compromising their integrity,
accuracy and reliability.

Two main types of data that users work with – and have to collect:
 Qualitative Data
 Deals with quality; Descriptive rather than numerical
 Generally, not measurable; usually subjective in nature.
 Does not require a big sample.
 Quantitative Data
 Deals with quantities, values or numbers; Measurable
 Expressed in numerical form (price, amount, duration, weight); Uses statistics
 Objective
 A larger sample size is usually required when collecting

Ways to collect quantitative data:

 Surveys
 Ask close-ended questions with provided options.
 The respondents will have to choose their answer among the choices provided on the
questionnaire.
Advantage:
 ideal for large number of respondents, questions are standardized making it easier
for researchers to make generalizations.
Disadvantage:
 limiting to the respondents
 Interviews
 are not just for qualitative researches. However, in this case, interview questions are
more structured. It means that there is already a prepared set of questions.
 Personal one-on-one interviews may also be used for gathering quantitative data. In
collecting quantitative data, the interview is more structured than when gathering
qualitative data, comprised of a prepared set of standard questions.
Advantage:
 allows the researcher to make clarifications on any answer given by the interviewee.
Disadvantage:
 not realistic for a large number of samples. Interviewing a big number of
respondents requires a lot of time, effort and money
 Observation
 Systematic observation may be used to collect data.
 you may do this by counting the frequency of a specific observation that you want to
see.
 This technique involves the use of the senses.
Advantage:
 simple, easy to use, cheap
Disadvantage:
 Bias may be present; senses are not always reliable
 Experiments
 involve manipulation of independent variables while maintaining varying degrees of
control over other variables, most likely the dependent ones.
 This is usually employed to obtain data that will be used later on for analysis of
relationships and correlations.
 Quantitative researches often make use of experiments to gather data.

Experiments may be done in:

 Laboratory experiments
 is conducted in a confined, closed and controlled environment (the laboratory), with the
data collector being able to have strict control over all the variables.
 In this setting, researcher can fully and deliberately manipulate the independent
variable.
 Field experiments
 takes place in the “field” where the data collector may still control the variable up to a
certain extent.
 Manipulation is still possible, although not as deliberate as in a laboratory setting
 Natural experiments
 the data collector has no control over the independent variable whatsoever, which
means it cannot be manipulated.
 The data collector can only gather data by letting the independent variable occur
naturally, and observe its effects.