Assessment and Evaluation Flashcards

A diagnostic test correctly identifies 90 of 100 participants who truly have a disease. What is the test's sensitivity?

Answer: 90%

Sensitivity equals true positives divided by all people with the disease, so 90/100 = 90%.

Which measure tells you the proportion of people without a condition who correctly test negative?

Answer: Specificity

Specificity is true negatives divided by all people without the condition.

As disease prevalence in a study population increases, what generally happens to a test's positive predictive value (PPV)?

Answer: PPV increases

PPV depends on prevalence and rises as the condition becomes more common in the tested population.

A research assistant notices that participants score better on a cognitive test at the third visit simply because they have seen it before. This is an example of what?

Answer: Practice (learning) effect

Improvement from repeated exposure to the same test is a practice or learning effect.

Most participants score the maximum possible value on a quality-of-life scale, making it impossible to detect improvement. What problem is this?

Answer: Ceiling effect

A ceiling effect occurs when scores cluster at the top of a scale, limiting the ability to detect higher values or improvement.

Participants with extremely high blood pressure at screening tend to have lower readings at the next visit even without treatment. What phenomenon explains this?

Answer: Regression to the mean

Extreme values on one measurement tend to be closer to the average on repeat measurement, known as regression to the mean.

A new anxiety scale correlates strongly with an established anxiety scale but weakly with a measure of physical height. Together these findings support which type of validity?

Answer: Construct validity

Convergent and discriminant evidence together support construct validity.