Chapter 4

Validity (Construct Validity):

The accuracy of a measurement tool—whether it accurately measures what it was constructed to measure.

Reliability

The consistency of a measurement tool—whether it provides the same results each time a specific variable is measured under identical conditions.

Feasibility

The practical usability of an instrument, considering cost, time, sample limitations, and training requirements.

Readability

The clarity of language in an instrument, ensuring subjects can comprehend and complete it accurately.

Content Validity

Ensures a tool contains all major elements relevant to the measured concept. Established via a literature review and expert panel feedback.

Convergent Validity

comparing a new instrument to an existing validated instrument measuring the same concept ($r \ge 0.40$ strengthens validity).

Divergent Validity

Assessed by demonstrating a strong negative correlation between a new instrument and an existing validated instrument measuring an opposing concept

Validity from Contrasting Groups

Tests whether an instrument can detect known differences between distinct groups.

Predictive Validity

Demonstrates an instrument's ability to forecast future outcomes or concurrent events (e.g., Braden Scale or Fall Risk Screen).

Stability

Consistency over time, evaluated using test-retest methods and correlation coefficients

Homogeneity (Internal Consistency):

Degree to which items on a multi-item scale correlate with one another. Commonly measured using Cronbach’s alpha ( r ) , where r ≥ 0.80 is typically required.

Equivalence

Consistency across different forms or different observers. Assessed via Inter-rater Reliability when multiple observers administer the tool.

What is true positive (A)

accurately identifies the presence of a disease

What is a false positive? (B)

test indicates the presence of a disease but there is no actual disease

What is a true negative (C)

accurately identifies lack of disease

What is a false negative (D)

test indicates disease is not a present but it actually is

Sensitivity

probability of testing positive given disease presence

What is the formula for Sensitivity?

A / A+C

Specificity

Probability of testing negative given disease absence

What is the formula for specificity?

D / B+ D

Positive Predictive Value (PPV)

Probability of not having disease given a positive test

What is the formula for PPV?

A / A + B

Negative Predictive Value (NPV)

Probability of not having disease given a negative test

What is the formula for NVP?

D / C + D

Efficiency (EFF)

Proportion of all test results that are correct

What is the formula for EFF?

A + D / A + B + C + D