VALIDITY AND

RELIABILITY
By
Dr. Sharmila Ghodke
 INTRODUCTION

• Validity and reliability are two important concepts in research

methodology, particularly in the field of social sciences. They
are used to assess the quality and trustworthiness of research
findings.
 VALIDITY

• Validity refers to the extent to which a study measures what it

intends to measure or the accuracy of the inferences,
interpretations, and generalizations made based on the research
results. In other words, it evaluates whether a study is actually
measuring the concept or phenomenon it claims to be studying.
 TYPES OF VALIDITY
 Internal Validity: Internal validity refers to the extent to which a causal
relationship can be established between the independent variable(s) and
the dependent variable(s) within a research study. In other words, it
assesses whether the observed effects can be attributed to the
manipulated variables and not to other confounding factors. Researchers
employ various techniques such as control groups, random assignment,
and counterbalancing to enhance internal validity.
 TYPES OF VALIDITY CONT…

 External Validity: External validity, also known as generalizability,

refers to the extent to which the findings of a study can be generalized to
other populations, settings, or time periods. Researchers strive to
enhance external validity by using representative samples, employing
diverse settings, and replicating studies across different contexts.
 TYPES OF VALIDITY CONT…

Construct Validity: It is a theoretical concept that is not directly

measurable. It measures how well the test, approach or instrument
measures the concept it is intended to measure. E.g. student satisfaction
survey (to verify construct validity, you can compare your measuring
method to others that measure similar qualities). Ideally you should
compare your test to several others to determine its construct validity.
 TYPES OF VALIDITY CONT…

Content Validity: Content validity examines the extent to which a

measurement instrument covers the entire range of the construct being
measured. It ensures that the measurement tool adequately represents all the
relevant aspects of the concept. E.g. knowledge of students regarding
vaccination. High content validity means the test covers the topic extensively.
Low content validity shows the test is missing important measurement
elements.
 TYPES OF VALIDITY CONT…
Criterion Validity: Criterion validity refers to the extent to which a measure or
test is correlated with an external criterion that is considered the gold standard.
It assesses whether the measurement instrument accurately predicts or correlates
with an established criterion. There are two types of criterion validity:
• Concurrent Validity: Concurrent validity is assessed by comparing the scores
obtained from a new measurement instrument with those obtained from an existing,
well-established instrument that measures the same construct. The two sets of scores
should be highly correlated if the new instrument has concurrent validity.
• Predictive Validity: Predictive validity examines how well a measurement
instrument predicts future outcomes or behaviors. It assesses the extent to which the
scores obtained from a measurement instrument can accurately forecast future events
or performance.
 TYPES OF VALIDITY CONT…

 Face Validity: Face validity refers to the extent to which a measurement

instrument or research procedure appears, on the surface, to measure the
construct it intends to measure. It is a subjective assessment that
considers whether the items or questions in a measurement instrument
seem relevant and appropriate to measure the construct based on their
face value. While face validity is not a strong indicator of validity.
 TYPES OF VALIDITY CONT…

 Ecological Validity: Ecological validity refers to the extent to which the

findings of a study can be generalized to real-world settings or
ecological contexts. It assesses whether the conditions and variables
manipulated in a research study accurately represent the complex and
dynamic nature of the real-world phenomenon being studied.
 THREATS TO VALIDITY

• Selection Bias: When the sample used in a study is not representative of

the target population, it can lead to biased conclusions that may not
generalize to the broader population.

• Measurement Bias: If the measurement instrument used in a study is

not accurate or does not capture the full range of the construct, it can
affect the validity of the findings.
 THREATS TO VALIDITY CONT…
• Social Desirability Bias: Participants may provide responses that they
believe are socially desirable, rather than their true beliefs or behaviors,
leading to distorted results.
• Hawthorne Effect: Participants may alter their behavior simply because
they are aware that they are being observed or studied, leading to an
artificial effect.
• Maturation: Over time, participants may naturally change or develop,
which can confound the results of longitudinal studies.
 STRATEGIES TO ENHANCE THE
VALIDITY
• Careful Study Design: A well-designed research study with clear
objectives, appropriate sampling techniques, and rigorous measurement
tools can enhance the validity of the findings.

• Multiple Measures: Using multiple measures or methods to assess the

same construct can strengthen construct validity by triangulating the
evidence.
 STRATEGIES TO ENHANCE THE
VALIDITY CONT…
• Randomization: Random assignment of participants to different groups
or conditions helps reduce selection bias and enhances internal validity
in experimental designs.

• Pilot Testing: Conducting a pilot study allows researchers to identify

and address potential issues with measurement instruments, procedures,
or participant recruitment before the main study.
 RELIABILITY

• Reliability refers to the consistency, stability, and repeatability

of measurements or research findings. It evaluates whether a
study produces consistent results when the same measurement
is repeated under similar conditions.
 TYPES OF RELIABILITY
ASSESSMENT
Test-Retest Reliability: Test-retest reliability assesses the consistency of
measurements over time by administering the same test or measurement
instrument to the same group of participants on two separate occasions.
The scores obtained should be highly correlated if the measurement is
reliable.
Inter-Rater Reliability: Inter-rater reliability is relevant when multiple
observers or raters are involved in measuring or coding a phenomenon. It
examines the consistency of ratings or judgments made by different
observers.
 TYPES OF RELIABILITY
ASSESSMENT CONT…
Split-Half Reliability: It assesses the internal consistency of a
measurement instrument by splitting it into two halves and examining the
correlation between the scores obtained from each half.
Parallel forms reliability: it is a measure of reliability obtained by
administering different versions of an assessment tool (both must contain
items that probe the same construct, skill, knowledge base etc.) to the
same group of individuals. The scores from the two groups can then be
correlated to evaluate the consistency of results across alternate version.
E.g. critical thinking assessment
 THREATS TO RELIABILITY
• Measurement Error: Measurement error refers to any discrepancy
between the true value of a construct and the observed measurement. It
can occur due to equipment malfunction, human error, or inconsistencies
in the measurement process.
• Inter-Observer Variability: In studies involving multiple observers or
raters, differences in judgment or interpretation of observations can
introduce inconsistencies and reduce inter-rater reliability.
• Temporal Variability: If the phenomenon being measured is subject to
change over time, such as mood or physical conditions, it can affect the
reliability of repeated measurements.
• Both validity and reliability are crucial for ensuring the quality and
integrity of research findings.

• A study can be reliable but not valid if it consistently measures something

that is not actually related to the construct of interest.

• Conversely, a study can be valid but not reliable if it measures the intended
construct accurately but produces inconsistent results.

• Researchers strive to maximize both validity and reliability to enhance the

credibility of their findings.
PILOT STUDY
 PILOT STUDY

• Pilot study is miniature trial run of the methodology planned

for the major research study, which facilitate to improve the
methodology of the study, can assess the feasibility of the
research study, & may identify the problems that may be faced
by the researcher in actual large research project.
 PURPOSES
• To study feasibility & practicability of research study.
• To assess the availability of study subjects.
• To assess validity & reliability of research study.
• To ensure appropriateness of methods & procedures of data collection.
• To understand the study variables & other confounding variables.
• To estimate the actual time & potential problems researcher may
encounter during the actual large research study.
• To refine methodology.
• To plan for data analysis & interpretation of final study.
THANK YOU