Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
31 Cards in this Set
- Front
- Back
How many peaks does a biomodal curve have?
|
2
|
|
What is validity?
|
The ability of a test or measurement to correctly identify the variable or disease it is supposed to measure (the accuracy)
|
|
What is reliability?
|
The degree to which the repeated results of a measurement will be the same (the repeatability)
|
|
What are the two components of validity?
|
Sensitivity and Specificity
|
|
What is sensitivity?
|
The ability of a test to correctly identify those who have a disease. (the percent of cases correctly identified as cases)
|
|
What is specificity?
|
The ability of a test to correctly identify those who do not have a disease (percent of non-case correctly identified as non-cases)
|
|
What is a gold standard test?
|
A more definitive test or procedure that will accurately determine whether a person actually has the disease or not
|
|
What is the true and false negatives/positives calculation for Sensitivity?
|
TP/(TP+FN)
|
|
What is the true and false negatives/positives calculation for Specificity?
|
TN/(FP+TN)
|
|
Sensitivity is the percent of those whose outcome is:
|
people with the disease for which the test is positive
|
|
Specificity is the percent of those whose outcome is:
|
those without the disease for which the test is negative
|
|
Cut off levels need to be made for health screening tests with what type of variables?
|
Continuous
|
|
In continuous variables, if sensitivity is increased, what happens to specificity?
|
Decreases
|
|
In continuous variables, if the specificity is increased, what happens to the sensitivity?
|
Decreases
|
|
What is PPV?
|
Positive Predictive Value
|
|
What is the PPV of a test?
|
The proportion of patients who test positive on a test who actually have the disease in question
|
|
What is the calculation for PPV?
|
PPV = true positives/total positives (meaning both true and false positives)
|
|
NPV can be calculated by:
|
NPV = true negatives/total negatives (meaning both true and false negatives)
|
|
Reliability refers to what?
|
Whether the results obtained on a test can be replicated if the test is repeated
|
|
3 factors that contribute to lack of reliability:
|
1. Intrasubject variation
2. Intraobserver variation 3. Interobserver variation |
|
What is intrasubject variation?
|
Variation of biological characteristics within individual subjects
|
|
What is intraobserver variation?
|
Variation that occurs when the same person (observer) interprets the same test results on separate occasions.
|
|
The greater the subjective element in the reading, the greater the what?
|
Intraobserver variation in the readings is likely to be
|
|
What is interobserver variation?
|
Variation between observers. Two examiners may not interpret a test result in the same manner
|
|
Overall percent agreement is a way to evaluate what?
|
Reliability
|
|
What is the calculation for overall percent agreement?
|
(a+b)/(a+b+c+d) x 100
|
|
What is the calculation for percent positive agreement?
|
(a)/(a+b+c) x 100
|
|
What does the Kappa statistic do?
|
It helps to explain to what extent does the agreement between two observers exceed the level of agreement that would result just from chance
|
|
What does > 0.75 state in the kappa statistic?
|
That there is excellent agreement beyond chance
|
|
What does 0.40 to 0.75 state in the kappa statistic?
|
Intermediate to good agreement
|
|
What does < 0.40 state in the kappa statistic?
|
Poor agreement
|