You are on page 1of 29

RELIABILITY AND VALIDITY

PRESENTED BY
SMITA Y. BHAGAT

SMT. KISHORITAI BHOYAR COLLEGE OF PHARMACY
BEHIND RAILWAY STATION, KAMTPEE.
CONTENTS
Reliability
Validity
Quantitative studies in research
Qualitative studies in research
RELIABILITY
o Reliability is degree of consistency
that the instrument or procedure
demonstrate
o Whatever it is measuring, it does so
consistently.
RELIABILITY
Unreliable measurement tool introduce error
Reliability improve with new tool or method
Test retest is the simplest way to assess reliability
Test with correlation of first with second score
RELIABILITY PARALLEL FORM AND TEST
RETEST
Testing situation requires the use of different form
of the same
Example 1 . school and licensing exam
2. Learning occur in testing, so it can be
repeated.
Test by computing correlation of two or more form,
taken under same circumstances
RELIABILITY INTERNAL CONSISTENCY
Abstract or complex diamension cant be measured
directly
Several related item or observation are more likely
to an accurate
Need to verify that all the items related to the same
diamension
RELIABILITY EFFECTIVE RANGE
o Measurement process need accuracy across all
possible outcomes.
o Ceiling effect :- process cannot measure extreme
high score.
o Floor effect :- process cannot measure extreme
low score.
o Both are a scale attenuation problem.
RELIABILITY PARALLEL FORM AND TEST
RETEST
Testing situation requires the use of different form
of the same
Example 1 . school and licensing exam
2. Learning occur in testing, so it can be
repeated.
Test by computing correlation of two or more form,
taken under same circumstances
INCREASING RELIABILITY
A. All researcher should use identical instruction.
B. A larger number of items will provides a more stable
measure of complex diamension.
C. Some question will be eliminated because they evoke
varied and inconsistent responses.
D. The items need to cover the entire range of diamension
in order to observe the extreme value.
E. Reliability may change if observation are made in very
different population situation.

VALIDITY
Validity is that quality of a data
gathering instrument or procedure
that enables its to measure what it is
supposed to measure.
VALIDITY
Two meaning of validity
Validity is an over arching concern of research
Measurement are the observation directly and truly
linked to the diamension or concept claimed.
Research design The research problem is the
preparation of the design of the research project,
popularly known as the research design.

In this course, we consider validity in measurement
now and validity in research design later.
CONSTRUCT VALIDITY
1. The diamension to be measured is a construct ,
an abstract idea related to a group of interrelated
variables.
2. The construct itself might be socially constructed
Classic studies in obedience are being re-
interpreted.
Some culture lack a word or idea for shizophrenia




3. Researcher make their case for the diamension for
validity, but must be open to reconsideration
CONTENT VALIDITY
Are all aspect of the diamension or concept
covered?
Are any aspect over- or under emphasized?
Does the measure differentiate this diamension
from other similar ones?
Improving content validity
Through search of the literature.
Consult with expert who disagree with your
perspective.
CRITERION VALIDITY
A measure is valid if it has a strong relationship to
an external criterion.
example :-1. A music audition is valid if it select the
better players over those with less ability. 2.The
GRE is a valid measure if people who do well on the
GRE succeed in graduate school.
It is an often as hard to demonstrate the link be
criterion as between the test and the diamension.

RELIABILITY AND VALIDITY
RELIABILITY VALIDITY
Does the value observed and
recorded accurately reflect the
true value of the object?
Does the value observed reflect
the concept and diamension of
interest?
The by measuring the object
multiple times or ways.
Test by comparing with other
data or similar process.
Every researcher must either
use a known instrument, or test
demonstrate the reliability of a
new tool .
Every researcher must either
use a known instrument , or test
and demonstrate the validity of
a new tool.
a) The literature search is a huge
labor saving device.
a) The literature search is a huge
labor saving device.
b) Using a known instrument
improve research quality.
b) Using a known instrument
improve research quality.
WHY DO RELIABILITY AND VALIDITY MATTER?
All of our research use data
a) Data is gathered through measurement
procedure.
b) The score only have meaning if they measure
what they are supposed to measure (valid) and
do so with accuracy and consistency (reliability).
Evaluating whether data are reliable valid is key
element in applying research finding.
We use statistical techniques in evaluating the
reliability and validity of data.
QUANTATIVE STUDIES IN RESEARCH
Scale clarify the characteristics of measurement process.
Scale indicate which statistical procedures are
appropriate.
NOMINAL ORDINAL INTERVAL RATIO
Categories
without order
Colors, genders,
political party,
nationality.
Categories
with order.
Size (
S,M,L) ,
social class,
agreement.
Distance is
meaningful
between
categories.
Temperature
, ACT score,
shoe sizes,
IQ.
Scale of
categories
has absolute
zero.
Age, income,
all rates and
percent,
vacation
time.
QUALITATIVE STUDIES INRESEARCH

Qualitative research, broadly defined, means "any kind
of research that produces findings not arrived at by
means of statistical procedures or other means of
quantification".
Reliability and validity are treated separately in
quantitative studies, these terms are not viewed
separately in qualitative research.
Qualitative research focuses on gathering of mainly
verbal data rather than measurements. Gathered
information is then analyzed in an interpretative manner,
subjective, impressionistic or even diagnostic.


1. GOAL OR AIM OF THE RESEARCH

The primary aim of a Qualitative Research is to
provide a complete, detailed description of the
research topic. It is usually more exploratory in
nature.
Quantitative Research on the other hand focuses
more in counting and classifying features and
constructing statistical models.


2. Usage
Qualitative Research is ideal for earlier phases of
research projects while for the latter part of the
research project, Quantitative Research is highly
recommended.
Quantitative Research provides the researcher a
clearer picture of what to expect in his research
compared to Qualitative Research.

3. DATA GATHERING INSTRUMENT

The researcher serves as the primary data gathering
instrument in Qualitative Research.
the researcher employs various data-gathering strategies,
depending upon the thrust or approach of his research.
Examples of data-gathering strategies used in Qualitative
Research are individual in-depth interviews, structured and
non-structured interviews, focus groups, narratives, content
or documentary analysis, participant observation and
archival research.
On the other hand, Quantitative Research makes use of
tools such as questionnaires, surveys, measurements and
other equipment to collect numerical or measurable data.


4. TYPE OF DATA

The presentation of data in a Qualitative Research
is in the form of words (from interviews) and images
(videos) or objects (such as artifacts).
If you are conducting a Qualitative Research what
will most likely appear in your discussion are figures
in the form of graphs.
However, if you are conducting a Quantitative
Research, what will most likely appear in your
discussion are tables containing data in the form of
numbers and statistics.
5. APPROACH

Qualitative Research is primarily subjective in approach
as it seeks to understand human behavior and reasons
that govern such behavior. Researchers have the
tendency to become subjectively immersed in the
subject matter in this type of research method.
In Quantitative Research, researchers tend to remain
objectively separated from the subject matter. This is
because Quantitative Research is objective in approach
in the sense that it only seeks precise measurements
and analysis of target concepts to answer his inquiry





THANK YOU