PRACTICAL RESEARCH II:

LESSON X: RESEARCH INSTRUMENTS:

PART 1. VALIDITY AND RELIABILITY
PART 2. TYPES OF INSTRUMENTS

Midge Seiman F. Maines

Subject Teacher
OUTLINE
PART I
• Ways in Developing Research Instruments
• Relationship bet. Validity and Reliability
• Validity and its forms
• Reliability and its methods
PART II
• Quantitative Research Instruments
– Questionnaires
– Scales
– Interview
– Observation
 PART I
Ways in Developing Research Instruments
Relationship bet. Validity and Reliability
Validity and its forms
Reliability and its methods
 DEVELOPING INSTRUMENTS
Research Instrument is what you use to MEASURE
whatever variable you intend to measure and
gather from the respondents. BEFORE planning to
develop your own instrument, you must first be
able to set your mind on this:

“WHAT CONSTRUCTS* DO I NEED TO

MEASURE FROM MY RESPONDENTS?”
*A construct is basically the equivalent of a variable but in a more specific sense. It is the
abstract idea / matter or simply, that “thing” you intend to measure.
DEVELOPING INSTRUMENTS
There are three (3) ways you can consider in
developing the research instrument for your study:

a) adopting an instrument from the already utilized

instruments from previous related studies.
b) modifying an existing instrument when the
available instruments do not meet the exact
data needed to answer the research questions.
c) researcher making his own instrument that
corresponds to the variable and scope of his
current study.
RELATIONSHIP OF V&R
Validity concerns accuracy of test, while reliability
concerns consistency. A good research instrument
should possess both validity and reliability.

For a test to be valid, If a test is unreliable, A reliable test does

it must be reliable. it cannot be valid. not make it valid.
 WHAT IS VALIDITY
VALIDITY
• Refers to the degree to which the instrument
measures what it intends to measure.
• This speaks of the usefulness of an instrument for a
given purpose.
• This is the MOST IMPORTANT criterion for a good
research instrument.
 FORMS OF VALIDITY
1. FACE VALIDITY
This is the extent to which a test appears valid to
examinees who take it, personnel who administer it,
and other untrained observers. This is not a
technical test of validity.

For example:
Respondents might have negative reactions to
an IQ test that doesn’t seem to measure their IQ.
 FORMS OF VALIDITY
2. CONTENT VALIDITY
This is the degree to which an instrument has
an appropriate sample of items for the
construct being measured (Polit & Beck, 2004).
This is done through a critical examination of
the test items so that it reflects the research
questions and objectives of the research.
 FORMS OF VALIDITY
2. CONTENT VALIDITY
This is validated through experts’ rating of each item
in a questionnaire called Content Validity Index
(Lynn, 1986). Example of calculation of CVI:
FORMS OF VALIDITY
3. CONSTRUCT VALIDITY
It refers to the validity of instruments as it
corresponds to other related theoretical
constructs. It is concerning IF a specific measure
relates to other measures.
For example:
You want to establish the construct validity of your test for Academic
performance. IQ test is a related measure for AP. You administered both
tests. The high scoring students scored high in IQ test, while low scoring
students scored low in IQ test. The direct correlation means your test is valid.
 FORMS OF VALIDITY
4. CONCURRENT VALIDITY
When the instrument can provide results similar to
those similar standardized or validated tests, it has
concurrent validity.

For example:
Your test measuring “Science Abilities” has concurrent
validity if it yields results that has high correlation to results
of a validated Science Exam.
FORMS OF VALIDITY
5. PREDICTIVE VALIDITY
When the instrument is able to produce results that
can predict future performance in another test or
performance, then the instrument has predictive
validity. This is common in entrance tests.
For example:
You administered a test that measures the ability of “to-be”
HUMSS students. You found out after 2 years that those who
yielded high scores all graduated with honors, while those with
low scores either shifted or dropped out.
 WHAT IS RELIABILITY
RELIABILITY
• This refers to the ability of the instrument to
produce the same results under the same
conditions (Consistency)
• This is the second most important criterion of a
good research instrument.
METHODS OF TESTING RELIABILITY

1. TEST-RETEST METHOD
The same (one) test is administered at two
separate times in the same respondents. Then the
correlation of two results are tested.
Reliability Score Interpretation
.90 and above Excellent reliability; level of standardized tests
.80 to .89 Very good for a classroom test
.70 to .79 Good for a classroom test; some items needs improvement
.60 to .69 Average; most needs improvement
.50 to .59 Low; needs major revision
Below .50 Questionable reliability
METHODS OF TESTING RELIABILITY

2. PARALLEL FORMS METHOD

Two similar tests are administered at two separate
times in the same respondents (e.g. Set A, Set B).
Then the correlation of two results are tested.
METHODS OF TESTING RELIABILITY

3. SPLIT HALF METHOD

Two sets are combined into one test then
administered in one time. Commonly this is done
by dividing the test into odd and even items. All
even items are SET A, and all odd items are SET B.
Items are similar but not identical.
METHODS OF TESTING RELIABILITY

4. INTER-RATER RELIABILITY
This is attained when the decisions from different
raters are compared to each other to see how
consistent the raters’ decisions are.
METHODS OF TESTING RELIABILITY

5. INTERNAL CONSISTENCY
This tests the correlation of each item from each
other. It is done when the test is administered only
once. This helps determine whether a collection of
items in a construct consistently measures the
same characteristic. Cronbach alpha is used for
this test. An alpha of >.70 is considered
acceptable instrument with good internal
consistency.
 PART II
Quantitative Research Instruments
Questionnaires
Scales
Interview
Observation
 TYPES: RESEARCH INSTRUMENTS
QUESTIONNAIRES
A questionnaire consists of a series of questions
about a research topic to gather data from the
participants. It consists of indicators that is aligned
to the research questions. This method is
inexpensive and can cover a wide area in a shorter
span of time. It can be done thru email, face-to-
face, messenger, or online forms.
 TYPES: RESEARCH INSTRUMENTS
QUESTIONNAIRES
“It consists of indicators that is aligned to the
research questions.”
NOTE: The research
questions are DIFFERENT
from a questionnaire’s
questions. The RQs are
answered by you; the
questionnaire questions
are answered by them.
 TYPES: RESEARCH INSTRUMENTS
Questionnaires often employ Scales (usually Likert
scales or Likert-type) which converts responses into
numerical values: strongly as 4, agree as 3,
disagree as 2, and strongly disagree as 1.
 TYPES: RESEARCH INSTRUMENTS
There are three structures of making a
questionnaire:
▪ Structured – contains close-ended questions
▪ Unstructured – consists of open-ended questions
▪ Semi-structured – combination of both
Structured type is commonly used in quantitative
studies because it is easier to code, interpret
objectively, and, most of all, easier to standardize.
 LIKERT SCALE vs. LIKERT-TYPE
In Likert scales, the data is treated as interval.
Meaning that the responses for each section or for
the entire questionnaire can be summated (added)
or averaged (mean). This is applicable when each
construct has several statements in the
questionnaire and the interest of the researcher is
the total score.
For example, in measuring the writing skills of the
students, you made 5 Likert scale statements.
 LIKERT SCALE vs. LIKERT-TYPE
Meanwhile, in Likert-type, each statement or item is
crafted to measure ONE particular trait or
construct. Technically, it means that the responses
in the entire questionnaire cannot be summated or
averaged (it’s like adding the colors of the rainbow).

In Likert-type, the data is treated as either nominal

or ordinal data. Mode is the most applicable
measure of central tendency for this.
 TYPES: RESEARCH INSTRUMENTS
ADVANTAGES OF QUESTIONNAIRES:
1. Inexpensive and practical
2. Cover wide range of respondents in a short time
DISADVANTAGE OF QUESTIONAIRES:
1. The questions can be interpreted differently by
the participants.
2. Some participants will not be able to complete
the required responses and lacks depth
Guidelines in Using Questionnaires
1. Choose the method of administering the
questionnaire. You can opt for face-to-
face or online whichever is more
practical.
NOTE: Online forms may lessen validity as it
cannot control how many responses are
given by each respondent.
Guidelines in Using Questionnaires
2. Divide your questionnaire into two or
three parts.
a. Personal information. This section which
contains background information.(Names
are optional)
b. Main section. This lists the specific questions
c. Open-ended question section. This contains
additional information that might be
needed. This part is optional.
 Guidelines in Using Questionnaires
3. Make sure to craft questions and
choices that are aligned with specific
research questions or objectives.

4. Provide specific and clear directions for

respondents in the manner of answering
the questionnaire.
 Guidelines in Using Questionnaires
5. Use routing (directing) technique if there is a
need to skip some items in the questionnaire.

6. Begin with the general questions first

followed by the specific ones.

7. Prefer to have brief, clear, and concise

questionnaire. Use simple terms.
 Guidelines in Using Questionnaires
8. Predetermined responses or choices should
match the nature of the questions.
a. If the content is about belief, use agreement
(strongly agree , agree…)
b. If the question is about behavior, use extent
(very great extent, great extent…)
c. If questions are about frequency, use frequency
(always, frequently, seldom, never)
d. If the content is about quality, use quality
(excellent, very good, good, poor)
 Guidelines in Using Questionnaires
9. Avoid negative statements unless necessary
(e.g. Are you NOT…)

10. Avoid leading and biased, double-

barreled questions (e.g. How bright did your skin
become after using myGluta?)

11. Do not split the same questions or choices

over two pages.
 Guidelines in Using Questionnaires
12. Schedule an appointment before
distributing the questionnaires. Make sure to
have secured proper authorities’ approval.

13. Tally and encode the data carefully once

you have collected them and archive them
digitally. Destroy them after the research is
published (for data privacy).
 TYPES: RESEARCH INSTRUMENTS
TESTS
Tests are used for assessing various skills and types
of behavior and for describing some characteristics.
Standardized tests are scored uniformly across
different respondents and are expert-validated. It is
considered as more reliable and valid. Examples
are Achievement test, University Entrance Exam,
Personality Tests, and the likes.
TYPES: RESEARCH INSTRUMENTS
TYPES OF TEST
TYPES: RESEARCH INSTRUMENTS
TYPES OF TEST
TYPES: RESEARCH INSTRUMENTS
TYPES OF TEST
 TYPES: RESEARCH INSTRUMENTS
INTERVIEW
Seldomly, interview is also employed by
quantitative research in certain cases. It is
collecting the quantitative data in a face-
to-face dialogue-type of questioning.
TYPES: RESEARCH INSTRUMENTS
QUANTITATIVE VS. QUALITATIVE
TYPES: RESEARCH INSTRUMENTS
QUESTIONNAIRE VS. INTERVIEW
The questionnaire and quantitative interview
are both highly structured, but here’s a
distinction between the two:
 TYPES: RESEARCH INSTRUMENTS
OBSERVATION
Observation is another qualitative method
that is employed in quantitative research.
This can be used ONLY for observing
quantitative or numerical data. This method
is more exhausting and time-consuming as
it demands anecdotal records or narrative
reports together with the research results.
TYPES: RESEARCH INSTRUMENTS
TYPES OF OBSERVATION
1. CONTROLLED OBSERVATION. It is
usually used in experimental
research and is done under a
standard procedure.
 TYPES: RESEARCH INSTRUMENTS
TYPES OF OBSERVATION
2. NATURAL OBSERVATION. It is carried out in
a non-controlled setting. It has greater
ecological validity (i.e. ability of the findings to
represent real-life contexts).
NOTE: A major limitation is its strength to
establish a causal relationship due to
the presence of extraneous variables
which can affect the behavior of the
participants without your knowledge.
 TYPES: RESEARCH INSTRUMENTS
TYPES OF OBSERVATION
3. PARTICIPANT OBSERVATION. It allows the
observer to become a member of the group
or community that the participants belong to.
METHODS: It can be performed
covertly (i.e. participants are
not aware) or overtly, wherein
participants know the intention
or objectives of the observation.
ASSIGNMENT

CRAFT YOUR RESEARCH INSTRUMENT

Due: November 28, 2022 (Monday)

SUBMIT THESE THREE:

1. Letter of Request for Conduct of Study
(addressed to School Principal)
2. Informed Consent Form
3. Research Instrument