Practical

Research 2

K to 12
APORBO, JERELYN C.
Basic Education Instructor
Curriculum
 Research Designs

 Sampling Designs/Plans and

Sampling Techniques
 Research design is a very important aspect of
research methodology which describes the
research mode (whether it is a qualitative
research or quantitative research, or if the
researcher will use a specific research type e.g.,
descriptive, survey, correlational, experimental,
etc.).
 Experimental Designs Non-experimental Designs

True Experimental Designs Action Studies

 Pretest-posttest control Comparative Studies
group design
Correlational Studies
 Posttest only control group
 Solomon four-group Developmental Studies
Evaluation Studies
Quasi-experimental Designs Meta-analysis Studies
 Non equivalent Methodological Studies
 Time series Needs Assessment Studies
Secondary Analysis Studies
Survey Studies/ Descriptive
Important Terminologies:

 Population – composed of persons or objects

that possess some common characteristics that
are of interest of the researcher.
 Target population – consist of the entire group of
people of which the findings of the study generally
apply.
 Accessible population – the specific study
population
 Parameter – numeric characteristic of the
population
Important Terminologies:

 Sample – subset of the entire population or the

individuals that represent the population and
serves as the respondent of the study.
 Statistic – numeric characteristic of a sample
 Element – single member of sample
 Sample (194)

Accessible
Population (500)

Target
Population
(815)

Population
(1,800)

*Sample Only
POPULATION: RadTech Students in Davao City - 1,800
TARGET POPULATION: RadTech Students in Davao Doc- 815
ACCESSIBLE POPULATION: RadTech Students in DDC S.Y 2019-2020 - 500
SAMPLE: RadTech Students - 194
Why specify the sampling plan?

 it provides an outline on the bases of which

research is conducted

 the researcher is well informed about which

category to survey, what the appropriate sample
size is, and how the samples/respondents should
be chosen from the whole population
Sampling plan three (3) major decisions

1. What should be the sampling unit?

 The researcher must choose the category of

population to be surveyed.

 In choosing the sampling unit, the researchers

must see to it that it is suitable to the research
objective/problem.
Sampling plan three (3) major decisions

2. What should be the sample size?

 Researchers must decide the sample size or the

number of respondents to include in the study.

 Generally, “the larger the sample size, the more is

the reliability”.

 On the other hand, acceptable number of samples

must be considered (Slovin’s Formula, Calmorin’s
Formula, or G Power software)
Slovin’s Formula Calmorin’s Formula

𝐍
𝐧=
𝟏 + 𝐍𝐞𝟐
𝑺𝒔 = sample size
n = sample size N = population size
N = population V = standard value (2.58)
size of 1% level of probability
e = desired margin with 0.99 reliability
of error P – largest possible
proportion
Sampling plan three (3) major decisions

3. What should be the sampling procedure?

 the researchers must decide what sampling

method to utilize: probability or non-
probability sampling (depending on the research
topic/problem)
Sampling Techniques

There are two major types of

sampling techniques: Probability
Sampling and Non-probability
Sampling (Baraceros, 2016).
Sampling Techniques

I. Probability sampling or Scientific Sampling -

This is a sampling method that make the
researcher base their selection of respondents on
pure chance.

II. Non-Probability Sampling – the respondents

under this technique are chosen purposefully. Not
randomized, they are susceptible to bias.
I. Probability sampling or Scientific Sampling

A. Simple-random sampling – is made when all the

members of the population are given a chance to
be selected. Selection is done by draw lot, table of
random numbers, and roulette wheel.
I. Probability sampling or Scientific Sampling

B. Systematic sampling – picking out from the list

every nth element member listed in the sampling
frame until the completion of the desired total
number of respondents

How to identify the nth element?

 Divide the total population by the desired sample
size to get the sampling interval.
 Example: 500/194 = 2.57 or 3rd element
I. Probability sampling or Scientific Sampling

C. Stratified sampling – choosing a sample that

will later on be subdivided into strata, subgroups,
or sub-samples during the stage of the data
analysis

D. Cluster sampling – selecting respondents in

clusters, rather than in separate individuals such as
choosing 5 classes of 40 students each from a
whole population of 5,000 students.
II. Non-Probability Sampling

A. Quota sampling – choosing specific samples that

you know correspond to the population in terms of
one, two, or more characteristics

B. Voluntary sampling – selecting people who are

very much willing to participate as respondents in
the research project
II. Non-Probability Sampling

C. Purposive sampling or Judgmental Sampling –

choosing respondents whom you have judged as
people with good background knowledge or with
great enthusiasm about the research

D. Availability sampling or Convenience Sampling

– picking out people who are easy to find or locate
and willing to establish contact with you
II. Non-Probability Sampling

E. Snowball sampling – selecting samples from

several alternative samples like drug dependents,
human traffickers, street children, and other
wayward and homeless people whose dwelling
places are not easily located for they are like
nomads moving from place to place
End of Unit IV, Lesson 1

 Practical
Research 2

K to 12
APORBO, JERELYN C.
Basic Education Instructor
Curriculum
 Instrumentation, Validity,

and Reliability
 The most used quantitative research
technique is the survey.

 There are various question formats that

can be adapted according to the research
needs.
1. Dichotomous Question
2. Multiple Choice Questions
3. Rank Order Scaling
4. Rating Scale
1. Dichotomous Question

This type of questions is generally answered

“Yes/No”.

Example:
Have you traveled to Guatemala? Yes or No
2. Multiple Choice Questions
For this type of question, it is important to consider including
an “other” category because there may be other avenues by
which the person first heard about your site that you might
have overlooked (Question Pro Survey Software, 2017).

Example:
Where do you get the news from?
Television
Radio
Newspaper
Magazine
Word of mouth
Internet
Other: Please Specify_________
3. Rank Order Scaling
Its questioning allows a certain set of brand or products to be
ranked based upon a specific attribute or characteristic.

Example:
Rank the following brands of cold drinks according to your
preference. Begin with 1 as the most preferred to 5, least
preferred.

 Coca Cola - _________

 Pepsi Cola - _________
 RC Cola - _________
 7 Up - _________
 Mountain Dew - _________
4. Rating Scale

This question requires a person to rate a product or brand

along a well-defined, evenly spaced continuum. Rating scales
are often used to measure the direction and intensity of
attitudes.

Commonly use scales:

A. Likert Scale
B. Semantic Differential Scale
4. Rating Scale

A. Likert Scale
5 4 3 2 1
Strongly Agree Agree Disagree Strongly
Agree nor Disagree
Disagree

1. I am interested in solving
numbers and equations.

2. I enjoy using calculators.

3. I am so engrossed in reading
too many instructions.
4. Rating Scale

B. Semantic Differential Scale

 The respondents are asked to rate concepts in series
of bipolar adjectives.

Example: Description of the class presidents

Competent 5 4 3 2 1 Incompetent
Punctual 5 4 3 2 1 Not punctual
Pleasant 5 4 3 2 1 Unpleasant
 Characteristics of a Good Data-Collection Instrument

1. It must be concise yet able to elicit the needed data (must

be 2-4 pages, must be answered in 10 minutes maximum, less
than 20 words per question).

2. It seeks information that cannot be obtained from other

sources like documents that are available at hand.

3. Questions must be arranged from simple to complex.

4. It must be arranged according to questions posted in SOP.

5. It should pass validity and reliability.

6. It must be easily tabulated and interpreted.

 Validity refers to the quality of the
instrument of being functional only
within its specific purpose.

 An instrument is valid if it
measures what it is supposed to
measure.
Types of Validity

1. Face Validity (also known as Logical Validity)

 The procedure calls only for intuitive judgment.

 It includes the font size, spacing, the size of the

paper used, and other necessary details that will
not distract respondents from answering the
questionnaire.
Types of Validity

2. Content Validity

 It relies on logical judgment as to whether the

test measures its intended subject

 An instrument with high content validity has to

meet the objectives of the research.

 It is subject to content validation by 3-5

experts.
Types of Validity

3. Construct Validity

 This type of validity refers to whether the test

corresponds with its theoretical construct.

 The degree to which a test measures what it

claims to be measuring

 The process of construct validation is theory-

laden
Types of Validity

4. Criterion-Related Validity or Equivalent Test

 This type of validity is an expression of how

scores from the test are correlated with an
external criterion.

 2 Types: Concurrent Validity and Predictive

Validity
Criterion-Related Validity or Equivalent Test

A. Concurrent Validity

 Criterion validity evaluates how closely the results

of your test correspond to the results of a different
test.

 To evaluate criterion validity, you calculate

the correlation between the results of your
measurement and the results of the criterion
measurement. If there is a high correlation, this
gives a good indication that your test is measuring
what it intends to measure.
Criterion-Related Validity or Equivalent Test

A. Concurrent Validity

Example:
The Stanford-Binet V, a widely accepted
standardized IQ test is used to determine the IQ of
nursing students. A researcher published a design
for a shorts screening test that measures the same.
The scores on the Standard-Binet V and the short
screening test are compared to assess the
relationship between scores.
Criterion-Related Validity or Equivalent Test

B. Predictive Validity

 It refers to how well the test predicts the future

behavior of the examinees.

 This is particularly useful in aptitude tests, which

are tests to predict how well test-takers will
perform in some future setting.
Criterion-Related Validity or Equivalent Test

B. Predictive Validity

 It is advised that when a drafted questionnaire is

to be subjected for validation, a rating sheet of
the acceptability of the indicators must be
provided for the experts to mark and give his
judgment. The markings and comments of the
experts that validated the proposed
questionnaire will be the basis of the revision of
the proposed instrument or questionnaire.
When can you
call someone
“reliable”?
 Reliability refers to the consistency of the
results of an instrument in repeated trials.

 A reliable instrument can also be used to verify

the credibility of the subject if the latter yield
the same results in several tests.

 This is only true if the instrument used is valid

 A valid instrument is always reliable, a

reliable instrument is not always necessarily
valid
Methods in Establishing Reliability

1. Test – Retest or stability

 The same test is given to a group of respondents
twice.
 The scores in the first test are correlated with
the scores in the second test.
 When there is a high correlation index, it means
that there is also a high reliability of the test.
 Weaknesses: person’s mental recollection of
his/her responses and time interval
Methods in Establishing Reliability

2. Internal Consistency

 If the test in question is designed to measure a

single basic concept, it is reasonable to assume
that a respondent who gets one item right is
likely to be right in another similar item. In other
words, items should to be correlated with each
other and the test ought to be internally
consistent.
 2 Types: Split Half and Kuder-Richardson Test
Internal Consistency

A. Split Half

 The test is given once

 Example, test is 100 items, it is divided into first

half (odd-numbered items) and second half
(even-numbered items).
Internal Consistency

A. Split Half

 The scores of the two halves are then correlates

using Spearman-Brown prophecy formula:

Where:
r - correlation coefficient computed for split half
𝑟𝑆𝐵 − 𝑒𝑠𝑡𝑖𝑚𝑎𝑡𝑒𝑑 𝑟𝑒𝑙𝑖𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑜𝑓 𝑡ℎ𝑒 𝑡𝑒𝑠𝑡

2𝑟
𝑟𝑆𝐵 =
1+𝑟
Internal Consistency

B. Kuder-Richardson Test (item total correlation)

 This measures the extent to which items in one

form of test share commonalities with one
another
 Requires one administration of the test
 Determine whether an individual test-taker
correctly answers each item or not and the
computation of the standard deviation of the
distribution
Internal Consistency

B. Kuder-Richardson Test (item total correlation)

 When the reliability coefficient is high, the test is
homogenous.
 Kuder-Richardson Formula 20
End of Unit IV, Lesson 2

 Practical
Research 2

K to 12
APORBO, JERELYN C.
Basic Education Instructor
Curriculum
 Data Collection Techniques
Presentation, Analysis and
Interpretation of Data

 Statistical Methods
 The application of appropriate data
collection technique results in the
production of accurate data sufficient to
render your study as valid.

Different techniques
1. Observation
2. Survey
3. Experiment
4. Physiological Measures
5. Questionnaires (Test)
1. Observation

 Involves the use of sensory organs and

express the sensory experiences through
numerical data

 Seeing, touching, and hearing the sources of

data personally, you engage yourself in
direct observation
1. Observation

 Indirect observation – observing by means

of technological and electronic gadgets like
audiotapes, video records, and other
recording devices used to capture earlier
events, images, or sounds

 The tool used in this technique is called

observation guide or observation
checklist.
2. Survey

 A data-gathering technique that makes the

researchers obtain facts or information about
the subject or object of the study through
the data gathering instruments: interview
and questionnaire.
3. Experiment

 An experiment is a scientific method of

collecting data whereby you give the
subjects a treatment or condition then
evaluate the results to find out the manner
by which the treatment affected the subjects
and to discover the reasons behind the
effects of such treatment on the subjects.
3. Experiment

 This quantitative data-gathering technique

aims at manipulating or controlling
conditions to show which condition or
treatment has effects on the subjects and to
determine how much condition or treatment
operates or functions to yield a certain
outcome.
4. Physiological Measures

 This involves the collection of physical data

from the subjects
 It is considered more accurate and objective
than other data collection method.
 However, skills and expertise are needed to
enable the researcher to use and manipulate
the measurement devices.
 Examples: thermometer, stethoscope,
weighing scale, tape measure, etc.
5. Questionnaire (Test)

 It contains list of questions on a particular

topic in which spaces are provided for the
respondents’ answers.

 It is less expensive, yields more honest

responses, guarantees confidentiality, and
minimizes biases based on question-phrasing
modes.
Presentation

This part features the data in the form of

graphs, charts, tables, and/or figures with
minimal textual representations (e.g. legends).
1. Tabular Presentation of Data
2. Graphical Presentation of Data
6

4 Sales
3

0
Category 1 Category 2 Category 3 Category 4
Series 1 Series 2 Series 3

1st Qtr 2nd Qtr 3rd Qtr 4th Qtr

Analysis

In analyzing the data, the following must be

considered:
 The highest numerical value such as scores,
weighted means, percentages, variability,
etc.
 The lowest numerical value such as scores,
weighted means, percentages, variability,
etc.
Analysis

In analyzing the data, the following must be

considered:

 The most common numerical values like

mode or values that appear repeatedly.

 The final numerical value like the average

weighted mean, total, chi-square value,
correlation index, etc.
Interpretation and Discussion of the Data

 In interpreting the data, the researcher

must explain the statistical and textual data
found in the table and analysis respectively.

 Sample guide questions for further

interpretation:
What does the result imply?
What does “very high/very low” mean?
Interpretation and Discussion of the Data

 The discussion of the results must include

the comparison and contrast with previous
studies cited in the RRL and RRS.

 Additionally, this should include the

implications, inferences, and other
important information.
 are ways of gathering, analyzing, and
interpreting variable or fluctuating
numerical data

 Two types:
1. Descriptive Statistics
2. Inferential Statistics
Descriptive Statistics

 It involves tabulating, depicting, and

describing the collected data.

 The data are summarized to reveal overall

data patterns and make them manageable.

 Kinds: Frequency distribution, Proportion,

Percentage, Measures of central tendency
(mean, median, mode), and Variability or
dispersion (Range, average deviation,
variance, standard deviation
Inferential Statistics

 It involves making generalizations about

the population through a sample drawn
from it.

 It also include hypothesis testing and

sampling
Inferential Statistics

 Concerned with higher degree of critical

judgment and advanced mathematical
modes such as parametric (interval and
ratio scale) and non-parametric (nominal
and ordinal) statistical tools.
Inferential Statistics

 Parametric – T-test, Z-test, F-test, Pearson r,

Simple linear regression, Multiple regression
analysis (interval and ratio scale)

 Non-parametric – Chi-square test (test of

goodness of fit, test of homogeneity, test of
independence), Spearman’s Rank Order
Correlation Coefficient (nominal and ordinal
data)
End of Unit V