VALIDITY AND RELIABILITY IN RESEARCH

Credibility of research instruments.

• Research credibility increases the truthfulness of the research
instrument and reduces the possibility of getting wrong
answers.
• For a research instrument to be credible, it must be VALID and
RELIABLE.
• Validity:- refers to the degree to which a test measures that
which it is supposed to measure.
• If, in a Biology test, the teacher subtracts marks for spelling
mistakes, the test will not be valid, because it is no longer
• There are two types of validity:- internal validity
:- external validity
Internal Validity
- It is defined as the degree to which internal variables that
might have influenced the research results have been
controlled.
- To what extent is the instrument measuring what it is
supposed to measure.
- Internal validity types:- content validity, face validity,
criterion validity, predictive validity etc. ( read more about
• Threats to Internal Validity:
- Historical events during the research which may affect
respondents attitudes, opinions, and behavior. E.g. Operation Restore
Legacy
- The effects of pretesting on the test subject: it may sensitize the
subjects to the material and help improve their post test scores.
- Maturation: respondent’s changes in growth during the course of
study i.e. the process of getting mature (differentiation towards
adulthood).
- Instrumentation- also known as instrument decay:- instrument
deteriorates due to ambiguous, misleading, or double-barreled
questions.
• Threats contd…
- Sample selection:- sample size & the type of people
included in a research project is obviously very important.
- Demand characteristics:- ‘prestige bias’ e.g. respondents
providing answers they think the researcher wants to hear
because the research situation ‘demanded’ answers.
- Experimenter bias:- researcher knowingly or unknowingly
influencing results of a project by mistakes in observation,
data recording, interpretation or otherwise.
- Bias:- the researcher is influenced by a client who wants a
research study to produce specific results.
• Threats cont…
- Evaluation apprehension- emphasizes the point that
respondents are usually afraid or hesitant about being
measured or tested.
- Diffusion or imitation of treatments:- respondents
being influenced by other respondents e.g. focus groups.

• Ways to Ensure Internal Validity:-

Consult subject or area specialists
Carry out a Pilot Study.
• External Validity:-
- It refers to the degree to which research results can be
generalized to respondents outside your sample.
- If you conduct your research study and find that your results only
apply to your sample and no one else, then you have a problem
with external validity.
- Two types of external validity:
1) Population external validity- refers to the extent to which
results may be generalized to other people.
2) Ecological external validity- environmental circumstances of
research and the extent to which the results could be
• Threats To External Validity:-
- Sample size:- the smaller is the sample size, the less results are
generalizable to the entire population.
- Hawthorn effect:- subjects preform differently when they know they
are being studied.
- Pretesting subjects in a study may cause them to react strongly to
treatment than they would have had they not experienced the pretest.
- Setting:- the performance of subjects in some studies may be a
reaction to the experimental setting.
- Interaction of history (..to everything there is a time..) caution
should be taken to generalize to a different time period. Conditions
change with time passage.
• Ways To Ensure External Validity
- Use random samples.
- Select a sample that is representative of the group
to which the results will be generalized.
- Repeat the study several times.
RELIABILITY

• Reliability refers to the degree to which a measurement

technique can be depended upon to secure consistent
results upon repeated application.
• If we measure a student’s height with a measuring tape,
we would expect that the student’s height would be the
same at each subsequent measurement. Therefore, the
tape is reliable.
• If we were to measure the length of a field track using the
stretch of our feet, the length would not be the same at
each subsequent measurement. Therefore the instrument
Reliability contd.
• Reliability can be assessed by posing 3questions:-
1. Will the measure yield the same results on other
occasions of measurement?
2. Will similar observations be reached by other
observers?
3. Is there transparency in interpreting the raw data?

So, reliability is about yielding consistent findings

in data collection and analysis.
Types of Reliability:-
1) Test- retest:- same study is administered twice to
same subjects over an interval of less than six months-
and is established by correlation analyses.
2) Parallel forms:- the degree to which alternative forms
of the same instrument produce same results- by
correlation analyses.
3) Internal consistency:- the extent to which instrument
items (questions) reflect same constructs- established by
Threats To Reliability

a) Subject/respondent reliability:- factors as a result of the

research respondent (e.g. patient fatigue, mood, hunger).
b) Observer reliability:- factors due to the observer/ rater/
interviewer. E.g. ability of the interviewer.
c) Situational reliability:- conditions under which measurements
are made (e.g. examination day in the school, closing day, strike
day)
d) Instrument reliability:- the research instrument or
measurement approach itself (e.g. poorly worded questions,
ambiguity etc.)
e) Data processing reliability:- manner in which data are handled
-TATENDA-